Search

Extraneous growth of scientific information over the Internet makes the searching task non-trivial and as a consequence researchers are facing difficulties in finding relevant papers from the millions of research papers in digital repositories. The research paper recommendation systems have been advocated to address this problem. The existing research paper recommendation systems lack in exploiting prominent information of papers, such as relevancy with the current time, novelty, scientific contribution, writing complexity of the papers, etc. Further, the existing models emphasize only on user's preference rather than user's intention that may change with time. Furthermore, the existing models do not consider a sound ranking strategy to unleash the personalization aspect and relevancy of papers. This work aims to address the existing limitations and proposes a systematic hidden attribute-based recommendation engine (SHARE). SHARE utilizes a feature engineering technique to unfold valuable insights of papers through multiple hidden features. These features are used as a context for users as well as multiple criteria for ranking papers. Additionally, SHARE predicts a user's intention beyond the user's preference to capture the dynamic notion of a user. Finally, a novel ranking strategy is proposed to retrieve personalized and the most important papers. SHARE is flexible for recommending both old and new users. In order to evaluate the effectiveness of SHARE both user studies and system evaluations were performed. Experimental results substantiate the efficacy of the proposed approach and are comparable to the existing systems. [ABSTRACT FROM AUTHOR]

Currently, text documents from multiple sources have become available in many fields. It is of great interest to study the relationship between documents from different sources and uncover the underlying causality. Zhu et al. (2021) proposed a joint dynamic topic model (JDTM). They classified all topics into three groups and used the "shared topics" with a fixed time lag order to characterize the shared information between two corpora. Although JDTM is a powerful tool for discovering the lead-lag relationship, there are two potential shortcomings. First, different shared topics should have distinct meanings, which should lead to different time lag orders between the two corpora. Second, for dynamic documents, not all topics are represented in each time slice, and thus topic sparsity should be considered. To address these two problems, we propose a sparse joint dynamic topic model (SJDTM) with a flexible lead-lag order. We assume a birth-and-death mechanism for all topics and a flexible lead-lag order for different shared topics. The performance of SJDTM is evaluated using both synthetic data and two real text corpora consisting of conference papers and journal papers. [ABSTRACT FROM AUTHOR]

The ranking of decision makers (DMs)' preferences for feasible states in the graph model for conflict resolution (GMCR) is crucial for accurately determining stability results. This paper addresses the issue of subjective ranking methods lacking theoretical foundation and causing ambiguity when the number of feasible states is high by proposing the implementation of the multi-attribute decision-making (MADM) method in the GMCR. The paper utilizes the average level to choose evaluation based on distance from average solution (EDAS) method for determining the DM's preference ranking, which can effectively reduce the impact of anomalous evaluations. Further, the PUL-EDAS method based on probabilistic uncertainty linguistics (PUL) is developed, which overcomes the shortcomings of the traditional EDAS method, which only applies to the simple evaluation of information. The PUL aligns with DMs' daily evaluation practice by providing an interval for the quality of qualitative linguistic evaluations. Furthermore, it utilizes an objective aggregation method to calculate comprehensive evaluation information from all DMs. In addition, the four fundamental stability definitions, applicable solely under crisp preferences, are extended to the PUL context, providing related extended definitions. Finally, to ensure the scientific validity and practicality of the proposed theory, this paper selects digital rural governance as the research context for conflict calculus analysis, comparing it with other MADM methods in the preference ranking section. [ABSTRACT FROM AUTHOR]

Exam paper generation is an indispensable part of teaching. Existing methods focus on the use of question extraction algorithms with labels for each question provided. Obviously, manual labeling is inefficient and cannot avoid label bias. Furthermore, the quality of the exam papers generated by the existing methods is not guaranteed. To address these problems, we propose a novel approach to generating exam papers based on prediction of exam performance. As such, we update the quality of the initially generated questions one by using dynamic programming, as well as in batches by using genetic algorithms. We performed the prediction task by using Deep Knowledge Tracing. Our approach considered the skill weight, difficulty, and distribution of exam scores. By comparisons, experimental results indicate that our approach performed better than the two baselines. Furthermore, it can generate exam papers with adaptive difficulties closely to the expected levels, and the related student exam scores will be guaranteed to be relatively reasonable distribution. In addition, our approach was evaluated in a real learning scenarios and shows advantages. [ABSTRACT FROM AUTHOR]

Abstract: In the present paper, we introduce the Euler sequence space consisting of all sequences whose Euler transforms of order r are in the space ℓ p of non-absolute type which is the BK-space including the space ℓ p and prove that the spaces and ℓ p are linearly isomorphic for 1⩽ p ⩽∞. Furthermore, we give some inclusion relations concerning the space . Finally, we determine the α-, β- and γ-duals of the space for 1⩽ p ⩽∞ and construct the basis for the space , where 1⩽ p <∞. [Copyright &y& Elsevier]

To compute the similarity of scientific papers, text-based similarity measures, link-based similarity measures, and hybrid methods can be applied. The text-based and link-based similarity measures take into account only a single aspect of scientific papers, content or citations, respectively. The hybrid methods consider both content and citations; however, they do not carefully consider the relation between the content of a pair of papers involved in a citation relationship. In this paper, we propose a novel method, SimCC (similarity based on content and citations), that considers both aspects, content and citations, to compute the similarity of scientific papers. Unlike previous methods, SimCC effectively reflects both content and authority of scientific papers simultaneously in similarity computation by applying a new RA (relevance and authority) weighting scheme. Also, we propose an RA+R weighting scheme to consider the recency of papers and an RA+E weighting scheme to take into account the author expertise of papers in similarity computation. The effectiveness of our proposed method is demonstrated by extensive experiments on a real-world dataset of scientific papers. The results show that our method achieves more than 100% improvement in accuracy in comparison with previous methods. [ABSTRACT FROM AUTHOR]

Abstract: In this paper we introduce a notion of a t-filter on residuated lattices which is a generalization of several special types of filters. We provide some basic properties of t-filters and show how particular results about special types of filters (e.g. Extension property, Triple of equivalent characteristics, and Quotient characteristics) are uniformly covered by this simple general framework. [Copyright &y& Elsevier]

Abstract: The task of assessing the similarity of research papers is of interest in a variety of application contexts. It is a challenging task, however, as the full text of the papers is often not available, and similarity needs to be determined based on the papers’ abstract, and some additional features such as their authors, keywords, and the journals in which they were published. Our work explores several methods to exploit this information, first by using methods based on the vector space model and then by adapting language modeling techniques to this end. In the first case, in addition to a number of standard approaches we experiment with the use of a form of explicit semantic analysis. In the second case, the basic strategy we pursue is to augment the information contained in the abstract by interpolating the corresponding language model with language models for the authors, keywords and journal of the paper. This strategy is then extended by revealing the latent topic structure of the collection using an adaptation of Latent Dirichlet Allocation, in which the keywords that were provided by the authors are used to guide the process. Experimental analysis shows that a well-considered use of these techniques significantly improves the results of the standard vector space model approach. [Copyright &y& Elsevier]

In a very recently presented paper, Turky and Abdullah [5] proposed a novel multi-population harmony search with external archive (MHSA-ExtArchive) for dynamic optimization problems. In the experimental results, the authors claimed that their approach could outperform several state-of-the-art algorithms. They also showed the superiority of their method by means of numerical experiments on Moving Peaks Benchmark (MPB). Despite the interesting idea of applying multi-population scheme on harmony search and using a new type of external archive for dealing with dynamic problems, we believe that there are two very important shortcomings in the result analysis, which we point out in this short note. The main motivation of the present note is to contribute toward preventing the same mistakes from happening by the other researchers. [ABSTRACT FROM AUTHOR]

Condition-based maintenance (CBM) policy can avoid premature or late maintenance and reduce system failures and maintenance costs. Most existing CBM studies cannot solve the dimensional disaster problem in multi-component complex systems. Only some studies consider the constraint of maintenance resources when searching for the optimal maintenance policy, which is hard to apply to practical maintenance. This paper studies the joint optimization of the CBM policy and spare components inventory for the multi-component system in large state and action spaces. We use Markov Decision Process to model it and propose an improved deep reinforcement learning algorithm based on the stochastic policy and actor-critic framework. In this algorithm, factorization decomposes the system action into the linear combination of each component's action. The experimental results show that the algorithm proposed in this paper has better time performance and lower system cost compared with other benchmark algorithms. The training time of the former is only 28.5% and 9.12% of that of PPO and DQN algorithms, and the corresponding system cost is decreased by 17.39% and 27.95%, respectively. At the same time, our algorithm has good scalability and is suitable for solving Markov decision-making problems in large-scale state and action space. • Considering minor and major repair, we model the joint optimization of CBM and spare ordering for large multi-component systems based on MDP. • An improved DRL algorithm is presented to deal with the MDP model in large-scale discrete state and action space. • We validate our DRL algorithm has good time performance and optimal decision-making series solution via comparisons with DQN and PPO algorithm. [ABSTRACT FROM AUTHOR]

This paper aims to contribute to the extension of classical Formal Concept Analysis (FCA), allowing the management of unknown information. In a preliminary paper, we define a new kind of attribute implications to represent the knowledge from the information currently available. The whole FCA framework has to be appropriately extended to manage unknown information. This paper introduces a new logic for reasoning with this kind of implications, which belongs to the family of logics with an underlying Simplification paradigm. Specifically, we introduce a new algebra, named weak dual Heyting Algebra, that allows us to extend the Simplification logic for these new implications. To provide a solid framework, we also prove its soundness and completeness and show the advantages of the Simplification paradigm. Finally, to allow further use of this extension of FCA in applications, an algorithm for automated reasoning, which is directly built from logic, is defined. [ABSTRACT FROM AUTHOR]

Implementations that follow the functional programming paradigm are being used in more and more domains. As functional programming paradigm has mathematical reference transparency, refinement to functional programs contributes to improving the reliability of the transformation process and simplifying the refinement steps. However, it is a challenge to generate functional programs from specifications. Most existing transformation methods refine specifications into abstract algorithm-level programs based on loop invariants rather than functional programs. This paper proposes a novel functional program generation method based on the partition-recursion refinement rule. It establishes a novel program refinement framework based on functional theory for the first time. This is the first study to regard the whole program refinement process as a composition of abstract functions. This paper designs a recurrence-based algorithm design language (Radl+) and implements a software prototype to map Radl+ algorithms into executable Haskell programs. To prove the feasibility and efficiency of this method, this paper transforms the polynomial multiplication problem from a specification into an executable Haskell program. This case shows that compared with existing approaches, the proposed method can simplify the transformation steps and reduce the number of lines of generated code from 38 to 10. • Novel refinement framework provides a new approach to generating a functional program. • The composition of abstract functions explains the program refinement process. • Substitution rule and Recursion rule have none of the side effects. • Software prototype transforms the polynomial multiplication problem into Haskell program. [ABSTRACT FROM AUTHOR]

Large-scale optimization problems (LSOPs) become increasingly ubiquitous but complicated in real-world scenarios. Confronted with such sophisticated optimization problems, most existing optimizers dramatically lose their effectiveness. To tackle this type of problems effectively, we propose a heterogeneous cognitive learning particle swarm optimizer (HCLPSO). Unlike most existing particle swarm optimizers (PSOs), HCLPSO partitions particles in the current swarm into two categories, namely superior particles (SP) and inferior particles (IP), based on their fitness, and then treats the two categories of particles differently. For inferior particles, this paper devises a random elite cognitive learning (RECL) strategy to update each one with a random superior particle chosen from SP. For superior particles, this paper designs a stochastic dominant cognitive learning (SDCL) strategy to evolve each one by randomly selecting one guiding exemplar from SP and then updating it only when the selected exemplar is better. With the collaboration between these two learning mechanisms, HCLPSO expectedly evolves particles effectively to explore the search space and exploit the found optimal zones appropriately to find optimal solutions to LSOPs. Furthermore, to help HCLPSO traverse the vast search space with promising compromise between intensification and diversification, this paper devises a dynamic swarm partition scheme to dynamically separate particles into the two categories. With this dynamic strategy, HCLPSO gradually switches from exploring the search space to exploiting the found optimal zones intensively. Experiments are executed on the publicly acknowledged CEC2010 and CEC2013 LSOP benchmark suites to compare HCLPSO with several state-of-the-art approaches. Experimental results reveal that HCLPSO is effective to tackle LSOPs, and attains considerably competitive or even far better optimization performance than the compared state-of-the-art large-scale methods. Furthermore, the effectiveness of each component in HCLPSO and the good scalability of HCLPSO are also experimentally verified. [ABSTRACT FROM AUTHOR]

Some cognitive and decision making experiments have demonstrated the classical decision theory may be violated. Recently, the interference effects of quantum theory have attracted a strong interest in applying some fields outside physics. It can be also used to explain the paradox in decision models. Existing some experiments and studies attribute the main reason for the existence of interference effects to uncertain information in decision process. Dempster-Shafer evidence theory extends the framework of discernment to power sets so it can describe unknown and imprecise information. This paper proposes evidential Markov decision-making model based on belief entropy to quantitatively predict and determine the value of interference effects. In new model, the frame of discernment is extended by introducing hesitant or unknown states which could be hidden by participants. Moreover, new model assumes there is no input of any information at initial states so it has the most chaotic states and is determined according to the maximum belief entropy. Finally, this paper discusses the effectiveness of new model by comparing with other methods as studying the interference effects of decision process. [ABSTRACT FROM AUTHOR]

Forgery of a signature with the aim of deception is a serious crime. Machine learning is often employed to detect real and forged signatures. In this study, we present results which argue that robotic arms and generative models can overcome these systems and mount false-acceptance attacks. Convolutional neural networks and data augmentation strategies are tuned, producing a model of 87.12% accuracy for the verification of 2,640 human signatures. Two approaches are used to successfully attack the model with false-acceptance of forgeries. Robotic arms (Line-us and iDraw) physically copy real signatures on paper, and a conditional Generative Adversarial Network (GAN) is trained to generate signatures based on the binary class of 'genuine' and 'forged'. The 87.12% error margin is overcome by all approaches; prevalence of successful attacks is 32% for iDraw 2.0, 24% for Line-us, and 40% for the GAN. Fine-tuning with examples show that false-acceptance is preventable. We find attack success reduced by 24% for iDraw, 12% for Line-us, and 36% for the GAN. Results show exclusive behaviours between human and robotic forgers, suggesting training wholly on human forgeries can be attacked by robots, thus we argue in favour of fine-tuning systems with robotic forgeries to reduce their prevalence. • Development of a computer vision-based system for signature spoofing attack detection. • A Conditional GAN can generate "real" and "fake" signatures. • Two robots can physically replicate human signatures with pen and paper. • The GAN and both robots can fool the model and mount false-acceptance attacks. • Verification model can be defended by fine-tuning on generative and robotic forgeries. [ABSTRACT FROM AUTHOR]

Data augmentation strategies have always been important in machine learning techniques and play a unique role in model performance optimization processes. Therefore, in recent years, these techniques have become popular in the artificial intelligence field. In this paper, a new data augmentation strategy is proposed based on the interpretation algorithm of deep convolutional neural networks, i.e., constructing new training samples by deeply exploiting key features extracted from interpretable networks to achieve sample augmentation. Thus, a novel supervised data augmentation approach known as Supervised Data Augmentation–Key Feature Extraction (SDA-KFE) was proposed. By introducing the Neural Network Interpreter-Segmentation Recognition and Interpretation (NNI-SRI) algorithm, an augmentation strategy is proposed that can balance the high accuracy and high robustness of the final model while ensuring a large amount of data augmentation. The advantages of the SDA-KFE algorithm are mainly reflected in the following aspects. First, it is easy to implement. This algorithm is implemented based on the lightweight NNI-SRI algorithm, which lays the foundation for the implementation of SDA-KFE so that it can be easily implemented on convolutional neural networks. Second, this model, which is widely applicable, can be applied to almost any deep convolutional network. Through research and experiments on this proposed algorithm, SDA-KFE can be applied in graphical image binary classification and multiclassification models. Third, SDA-KFE can rapidly construct data samples with diverse variations. Under the premise of determining the classification labels of the generated samples, the distribution of the feature unit composition of the samples can be controlled. Compared with traditional data augmentation methods, SDA-KFE can control the direction of the model performance, i.e., the balance between the pursuit of high accuracy and robust performance of the model. Therefore, the novel supervised augmentation approach proposed in this paper is relevant for optimizing deep convolutional neural networks, solving model overfitting, augmenting data types, etc. The data augmentation algorithm proposed in this paper can be regarded as a useful supplement to traditional data augmentation methods, such as horizontal or vertical image flipping, cropping, color transformation, extension and rotation. [ABSTRACT FROM AUTHOR]

• EKRS is an intelligent research assistance system to recommend knowledge to scholars. • EKRS is formed through mapping two sets of IR and CRD. • IR and CRD were reconstructed based on the VSM. • LRA improving the solution process and decreasing the complexity of the UKVSM. Expert Knowledge Recommendation System (EKRS) is an intelligent research assistance system. The system is formed by mapping two sets of conceptual spaces through Institutional Repository (IR) and Core Resource Dataset (CRD) in 2018. The user knowledge pattern matching (UKPM) of EKRS has problems such as uncertain user knowledge text matching, slow update of expert knowledge, and inability to accurately track user knowledge. This paper establishes a user knowledge vector space reconstruction model (UKVSM) through the following steps to solve the above problems. Firstly, the text feature items of IR and CRD are reconstructed and the depth and density correction coefficient matrix of the original node of the text semantic meaning is calculated based on the similarity of feature items of the semantic layer. Secondly, in order to improve the efficiency of UKPM exact matching, the Lagrangian relaxation algorithm (LRA) is used to optimize the two sets of knowledge matching strategies. Finally, the real data set is extracted from the EKRS platform, and the model and algorithm proposed in this paper are tested and verified respectively, and compared with other methods. Experiments show that reconstruction model can improve the accuracy of user knowledge task assignment in EKRS, while LRA can improve the efficiency of model solving. [ABSTRACT FROM AUTHOR]

Existing hierarchical clustering (HC) algorithms generally depend on the Euclidean characteristic metric (Euclidean distance, Manhattan distance, Chebyshev distance, etc.) on Euclidean space to describe the similarity between objects, which makes the clustering process oriented to data sets with uniform and regular distribution in Euclidean space. Although such methods can visually distinguish the cluster distribution of data, it is not effective for the data sets which are densely distributed, interlaced and complex in Euclidean space. As a scalable, efficient and robust method, granular computing generally analyzes data from the perspective of similarity and proximity. In consideration of the advantages of granular computing in extracting data information from a multi-level perspective, in order to reduce the limitations of HC methods based on Euclidean features on non-Euclidean data, this paper proposes a novel HC method based on non-Euclidean feature structure. First, this paper constructs the similarity between objects based on K -dominance granularity and neighborhood search, and considers the environmental information of data points from both global and local perspectives. Secondly, a new HC method based on non-Euclidean feature structure is designed on the basis of the similarity measurement constructed in this paper. Finally, through comparative analysis, the experimental results prove that our method can more accurately identify the densely distributed and interlaced data sets in Euclidean space; it is significantly better than comparison algorithms using different Euclidean features to measure similarity; it has good robustness when additional Gaussian noise is added. [ABSTRACT FROM AUTHOR]

In fuzzy large group decision making methods, an effective clustering method can greatly reduce the complexity of decision making, and it is an important ingredient for reaching a group consensus. In this paper, a novel fuzzy large group decision making method is established using three-way clustering and an adaptive exit-delegation mechanism. Traditional clustering approaches group together individuals (isolated points) that deviate from the whole. The individuals (edge points) may exist and wander in between two or more classes. Both circumstances can lead to unstable and unreasonable clustering results. To overcome both setbacks, we propose a three-way clustering method based on the k -means clustering algorithm. The method first applies k -means clustering to perform an initial division of the universe of decision-makers. Then, in the spirit of three-way clustering, the edge points and outliers are separated from the clustering results by resorting to the three-way relationships between individuals and classes. The final clustering stems from an adaptive exit-delegation mechanism, and a consensus measure-based model determines the intra-group individual weight and inter-individual trust weight. Finally, the feasibility and effectiveness of the methodology that arises from the model designed in this paper are verified by comparative analyses. [ABSTRACT FROM AUTHOR]

This paper concerns a new incremental approach to mining data streams. It is known that patterns in a data stream may evolve over time. In many cases, we need to track and analyze the nature of these changes. In the paper, the probabilistic neural networks are considered as basic models for tracking changes in data streams. We present globally convergent stream data mining algorithms applied to problems of regression, classification, and density estimation in a time-varying (drifting) environment. The algorithms are derived from the Parzen kernel-based probabilistic neural networks working in the online mode. For each problem, a theorem is presented ensuring the L 2 convergence of the algorithm designed for tracking drifting regression, density, or discriminant functions. Illustrative examples explain in detail how to choose the bandwidth of the Parzen kernel and the learning rate of the online algorithm. The performance of all algorithms is shown in exemplary simulations. It should be noted that this paper is one of very few, in the existing literature, presenting mathematically justified stream data mining algorithms. • The incremental version of the Generalized Regression Neural Network (IGRNN) able to track drifting regression functions. • The incremental version of the Probabilistic Neural Network (IPNN) working in non-stationary environments. • Application of IPNN for tracking drifting discriminant functions. • Mathematical proofs of the L 2 convergence of all the proposed estimators. [ABSTRACT FROM AUTHOR]

Interval-valued fuzzy preference relations (IVFPRs) have been applied to many real-life decision-making problems. However, most definitions of consistency of IVFPRs do not satisfy invariability to compared objects' labels. To overcome this drawback, this paper mainly focuses on the multiplicative consistency analysis of interval-valued fuzzy preference relations (IVFPRs). Firstly, this paper proposes a new multiplicative consistency of complete IVFPRs. It is proved that this new multiplicative consistency is robust and invariable to compared objects' labels. Then, the definition of acceptable incomplete IVFPRs (In-IVFPRs) is presented. To make full use of all direct and indirect evaluations of decision-makers, an algorithm is devised to evaluate the missing elements of an acceptable incomplete In-IVFPR. To comprehensively describe the closeness between any two complete IVFPRs, the total deviation of two complete IVFPRs is defined based on the p -norm of a vector. By minimizing the total deviation of two complete IVFPRs, a programming model is built to determine an interval weight vector from a complete IVFPR. Subsequently, a novel decision-making method with an In-IVFPR is proposed. Lastly, three practical and numerical examples and simulation-based comparative analyses are provided to further validate the practicability and advantages of the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a unified event-triggered sliding-mode control framework to attain the finite/fixed-time reachability of practical sliding-mode band. In event-triggered sliding-mode control, the practical sliding mode makes the size of the sliding-mode band dependent on the event function rather than the disturbance bound and sampling interval and provides better control performance due to this advantage. Under this paper's unified framework, the predesigned practical sliding-mode band can be respectively reached within a finite/fixed time by choosing different parameters. Then, different from the asymptotical convergence obtained in other investigations, the ultimate finite-time stability of the controlled system can be guaranteed. In the sliding phase, by adjusting the initial value of integration for settling time from initial value of the controlled system to the point where the sliding phase starts, a more precise estimation to settling time is obtained and can be generalized to different kinds of systems. In addition, in comparison to other results in finite-time event-triggered sliding-mode control, signum function is subtracted from the measurement error which eliminates the Zeno phenomenon and ensures the reliable operation of the digital controller in reality. Finally, a numerical example is given to verify the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

Three-way decision, an essential granular computing research tool, provides an efficient solution to complex and uncertain problems. Behavioral decision theory can analyze the risk preferences of decision-makers effectively. Scholars have conducted preliminary exploration on the fusion of these two theories, but it is still challenging to describe the different types of risk preferences of decision-makers. This paper combines prospect theory with regret theory and studies the compound risk preference modeling of three-way decision to address this issue. Because three attitudes of conflicts coincide with three-way decision, many scholars have conducted multi-dimensional research on three-way conflict analysis and accomplished remarkable results. However, few relevant studies consider psychological factors and risk attitudes of decision-makers, and it is more appropriate to describe agents' attitudes on issues using linguistic terms. This paper applies the proposed three-way decision model based on compounded risk preference and probabilistic linguistic term sets to the conflict analysis problem. We utilize examples to explain the decision-making process of the proposed model and three-way conflict analysis method with the influence of the compounded risk preference under the action of reference point and regret avoidance coefficient. The illustrative example illustrates that the proposed three-way decision model can effectively solve the software development conflict analysis problem for different decision-makers and the comparative analysis shows the advantages of the proposed model and method compared with the two existing methods. Finally, we verify the performance of the three-way decision model based on compounded risk preference by UCI data sets in parameter experiments. The changes of the reference point from 10 to 0 and regret avoidance coefficient in 0, 0.15 and 0.3 respectively demonstrate the trend rule of the model's thresholds and delay-decision rate index. [ABSTRACT FROM AUTHOR]

• This paper presents a lightweight and efficient spatial–temporal transformer network to learn collaboratively and efficiently to detect epileptic seizures. • A hierarchical FL framework is introduced to enable resource-efficient training of the detection network. • The proposed Fed-ESD mitigates the risk of a single point of failure by alleviating reliance on a centralized authority. Epilepsy is a predominant paroxysmal neurological disturbance that is usually recognized as the incidence of impulsive seizures rarely seen in medicine. Automatic detection of epileptic seizures from electroencephalogram (EEG) signals is viewed as an effective diagnosis of patients on the Internet of Medical Things (IoMT). To design a robust detection service in an IoMT environment, the EEG signals of different patients are collected from geographically distributed patients to a centralized server. However, this makes the patient's privacy prone to exposure and adds to the energy and communication costs. Also, the central server can be subject to malevolent attacks, resulting in non-efficient solutions. In this regard, for the first time, this paper presents a privacy-preserving federated learning framework for epileptic seizure detection (called Fed-ESD) from EEG signals in the fog-computing-based IoMT. A lightweight and efficient spatiotemporal transformer network is introduced to collaboratively learn spatial and temporal representations from the local data of each participant. The proposed Fed-ESD employs geographically situated fog nodes as local aggregators to enable sharing of location-based EEG signals for comparable IoMT applications. Moreover, a greedy method is introduced for deciding on the ideal fog node to be the coordinator node responsible for global aggregation during the training, thereby decreasing the reliance on the central server in the IoMT. Experimental evaluations demonstrate the efficiency of the proposed Fed-ESD in terms of detection performance, resource-efficiency, stability, and scalability for deployment in the IoMT. [ABSTRACT FROM AUTHOR]

In this paper, a new two-dimensional gaussian hierarchical priority fuzzy system (TGHPFS) is proposed to handle interval-valued data. TGHPFS first performs hierarchical clustering of the average value of interval-valued data in each dimension to generate two-dimensional gaussian membership functions of two-level rules. The two levels of rules are associated by calculating the activation strength of the second-level rules to the first-level rules and setting the connection threshold. The regularized least squares method is used to optimize the consequents of the second-level rules. The two-dimensional gaussian membership function designed in this paper is used to model the antecedents of interval-valued data, solving the correlation problem between the left and right values of interval-valued data. The effectiveness of TGHPFS is validated using real-world datasets, and the proposed method is compared with other latest methods to show the superiority of TGHPFS. [ABSTRACT FROM AUTHOR]

Federated Continual Learning (FCL) approaches exist two major problems of the probability bias and the imbalance in parameter variations. These two problems lead to catastrophic forgetting of the network in the FCL process. Therefore, this paper proposes a novel FCL framework, Federated Probability Memory Recall (FedPMR), to mitigate the probability bias problem and the imbalance in parameter variations. Firstly, for the probability bias problem, this paper designs the Probability Distribution Alignment (PDA) module, which consolidates the memory of old probability experience. Specifically, PDA maintains a replay buffer and uses the probability memory stored in the buffer to correct the offset probabilities of the previous tasks during the two-stage training. Secondly, to alleviate the imbalance in parameter variations, this paper designs the Parameter Consistency Constraint (PCC) module, which constrains the magnitude of neural weight changes for previous tasks. Concretely, PCC applies a set of adaptive weights to subsets of the regularization term that constrains parameter changes, forcing the current model to be sufficiently close to the past model in parameter space distance. Experiments with various levels of task similitude across clients demonstrate that our technique establishes the new state-of-the-art performance when compared to previous FCL approaches. [ABSTRACT FROM AUTHOR]

This paper proposes a novel algorithm twice optimization for interval type-2 fuzzy neural networks with asymmetric membership functions (TOIT2FNN-AMF), for nonlinear system identification problems. The proposed TOIT2FNN-AMF uses an asymmetric Gaussian interval type-2 membership function to enhance the network's ability to describe and solve nonlinear and uncertain problems. The twice optimization algorithm consists of structure learning and parameter learning. Firstly, this paper proposes a multi-strategy adaptive differential evolution (MSADE) algorithm as the first optimization algorithm, which is used to determine the structure and the initial values of the parameters of the TOIT2FNN-AMF. It applies the root mean square error (RMSE) of the TOIT2FNN-AMF as the fitness function to determine the structure (number of rules) and initial parameters of the IT2FNN by searching for the RMSE values under different structures. When the fitness value reaches the minimum, that is, the RMSE value of the TOIT2FNN-AMF, the corresponding number will become the optimal one of fuzzy rules of the TOIT2FNN-AMF. Then, the second optimization algorithm of the TOIT2FNN-AMF turns into a hybrid optimization algorithm composed of an adaptive moment estimation (Adam) algorithm and recursive least squares (RLS) algorithm. Adam is used to optimize the antecedent parameters of TOIT2FNN-AMF rules, so as to maintain rapid convergence without generating oscillation during the training process; RLS is used to optimize the consequent parameters of TOIT2FNN-AMF rules, so that the network parameters can be optimized rapidly. In this way, the problems of excessive parameters to be adjusted and excessive slow convergence of the network can be solved. Finally, this paper evaluates the proposed TOIT2FNN-AMF by testing on problems of nonlinear system identification and chaotic time-series prediction. The simulation results are compared with those of similar methods in the existing literatures, which demonstrates that the proposed TOIT2FNN-AMF model yields a lower RMSE value and a simpler network structure than the other type-2 fuzzy neural networks (T2FNNs). [ABSTRACT FROM AUTHOR]

• The finish time and total costs are extracted as the optimization objectives based on problem characteristics. • The dynamic task disassembling mechanism (DTDM) and four technician scheduling modes are novelly proposed. • A flexible time is introduced into DTDM to provide decision-makers with a larger pool of choices to meet specific needs. • A new solution method suitable for both AMTS model and ATMS-DTDM model is designed based on PSO and MOPSO algorithms. This paper focuses on the aviation maintenance technician scheduling (AMTS) problem and formulates AMTS and AMTS-DTDM model with a practical dynamic task disassembly mechanism (DTDM) and arrange maintenance technicians across shifts in short-term maintenance situations (less than 24–48 h). In DTDM, four technician scheduling modes are devised to flexibly disassemble the overtime work or reassigned it to other maintenance technicians according to work efficiency and progress, which could shorten the maintenance time and save the total cost. Moreover, a flexible time interval is designed to adjust the boundary of task disassembly. To further study the effectiveness of DTDM in reducing maintenance time and total costs, this paper divides both the AMTS and AMTS-DTDM models into three sub-models (i.e., two single-objective models and one multi-objective model), respectively. After that, we design solution methods as well as the encoding schemes compatible with both the AMTS model and the AMTS-DTDM model for different problem scales. Finally, to verify the effectiveness of DTDM, four groups of experiments are set up and particle swarm optimization (PSO) and multi-objective particle swarm optimization (MOPSO) are applied to compare AMTS and AMTS-DTDM sub-models. The experimental results show that the AMTS-DTDM model can effectively shorten the maintenance time and reduce the total costs for different scaled problems. Furthermore, the flexible time interval can facilitate more options for airlines to adjust the two above objectives to a small extent. The increase in flexible time may weaken the advantages of the AMTS-DTDM model while improving the rationality of the ultimate technician scheduling scheme. [ABSTRACT FROM AUTHOR]

Stochastic configuration networks (SCNs) have universal approximation capability and fast modeling properties, which have been successfully employed in large-scale data analytics. Based on SCNs, Stochastic configuration networks with block increments (BSC) use the node block increments mechanism to improve training speed but increase the complexity of the model. This paper presents a parallel configuration method (PCM), develops an extension of the original BSC with chaos theory and proposes stochastic configuration networks with chaotic maps (SCNCM), and establishes a hierarchical learning strategy (HLS) to enhance the compactness and construction speed of the model. Firstly, PCM randomly assigns the input weights w and biases b of hidden layer nodes by using uniform and normal distributions. In PCM, an iterative learning algorithm is intended to generate the scope control set and improve configuration efficiency. Secondly, the paper presents two kinds of stochastic configuration networks with chaotic maps, which are SCNCM-I and SCNCM-II. SCNCM-I adjusts block size by using multiple error values and chaotic maps to improve the training speed. Based on SCNCM-I, SCNCM-II utilizes node removal mechanism to enhance the compactness. Finally, HLS integrates with SCNCM-I, SCNCM-II, and the Harris-hawks optimization algorithm (HHO). The purpose of training is to enhance the training speed and compactness for three algorithms. The experiments are conducted on four benchmark data sets and an industrial application shows its effectiveness. [ABSTRACT FROM AUTHOR]

Many real-life problems can be formulated as numerical optimization problems. Such problems pose a challenge for researchers when designing efficient techniques that are capable of finding the desired solution without suffering from premature convergence. This paper proposes a novel evolutionary algorithm that blends the exploitative and explorative merits of two main evolutionary algorithms, namely the Stochastic Fractal Search (SFS) and a Differential Evolution (DE) variant. This amalgam has an effective interaction and cooperation of an ensemble of diverse strategies to derive a single framework called Iterative Cyclic Tri-strategy with adaptive Differential Stochastic Fractal Evolutionary Algorithm (Ic3-aDSF-EA). The component algorithms cooperate and compete to enhance the quality of the generated solutions and complement each other. The iterative cycles in the proposed algorithm consist of three consecutive phases. The main idea behind the cyclic nature of Ic3-aDSF-EA is to gradually emphasize the work of the best-performing algorithm without ignoring the effects of the other inferior algorithm during the search process. The cooperation of component algorithms takes place at the end of each cycle for information sharing and the quality of solutions for the next cycle. The algorithm's performance is evaluated on 43 problems from three different benchmark suites. The paper also investigates the application to a set of real-life problems. The overall results show that the proposed Ic3-aDSF-EA has a propitious performance and a reliable scalability behavior compared to other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Compared with single-task learning, multi-tasks can obtain better classifiers by the information provided by each task. In the process of multi-task data collection, we always focus on the target task data in the training process, and ignore the non-target task data and unlabeled data that may be contained in the target task. In response to this issue, this paper introduces auxiliary or Universum into semi-supervised multi-task problem, and proposes a multi-task support vector machine (SU-MTLSVM) method based on semi-supervised learning to handle the case where each task contains the labeled, unlabeled, and Universum samples in the training set. This method introduces Universum as prior knowledge and provides high-dimensional information for semi-supervised learning, and builds a unique classifier from a large amount of unlabeled data. We then use KKT conditions and Lagrangian method to optimize the formulation of the model, and get the model parameters. Finally, we collect different data sets in the experiment part, and compare the performance of multiple baselines with the proposed method. Experiments prove that the method proposed in this paper is more effective for multi-task applications. [ABSTRACT FROM AUTHOR]

This paper addresses the bearing-only distributed localization, which is more accurate and more reliable than traditional localization technologies. A new bearing-only distributed localization framework is proposed to solve localization problems for both static sensor networks and mobile multi-agent systems (MASs). Based on the complex coordinate representation, a novel bearing-only distributed localization algorithm for sensor networks is proposed. The algorithm combines the orientation estimation and the position estimation to solve the orientation alignment problem, which makes the compasses no longer needed for the localized networks. The localization for the mobile MASs is also studied and the corresponding localization algorithm is designed, which is more general and more challenging. The key to obtaining positions of moving agents, is the velocity estimator in the proposed localization algorithm which makes the estimated positions and velocities converge to the true value simultaneously. A distinctive advantage of the localization framework proposed in this paper is that the bearing-only localization algorithms can be applied to more general systems, such as sensor networks and MASs. Simulations and experiment are presented to verify the proposed algorithms. [ABSTRACT FROM AUTHOR]

Nowadays, cybersecurity challenges and their ever-growing complexity are the main concerns for various information technology-driven organizations and companies. Although several intrusion detection systems have been introduced in an attempt to deal with zero-day cybersecurity attacks, computer systems are still highly vulnerable to various types of distributed denial of service (DDoS) attacks. This complicated cyber-attack caused many system failures and service disruptions, resulting in billions of dollars of financial loss and irrecoverable reputation damage in recent years. Considering the nonnegligible importance of business continuity in the Industry 4.0 era, this paper presents a comprehensive, systematic survey of DDoS attacks. It also proposes a hierarchy for this severe cyber threat, besides conducting deep comparisons from various perspectives between the studies published by reputed venues in this area. Furthermore, this paper recommends the most effective defensive strategies, with a focus on recently offered fuzzy-based detection methods, to mitigate such threats and bridge the gaps existing in the current intrusion detection systems and related works. The outcomes and key findings of this survey paper are highly advantageous for private companies, enterprises, and government agencies to be implemented in their local or global businesses to significantly improve business sustainability. [ABSTRACT FROM AUTHOR]

In this paper, a novel adaptive generalized Nash equilibrium (GNE) seeking algorithm is designed, in order to address the non-cooperative game with private inequality constraints under high-dimensional input dead-zone. That is to say, the dead-zone dynamics may be thought of as a generic high-dimensional convex set, and the introduction of two methods distinguishes our works in seeking the GNE of non-cooperative games. On the one hand, a two-time-scale structure based on singular perturbation method is led into the design of GNE seeking algorithm, where the fast dynamics part rapidly eliminates the influence of input dead-zone, and the slow dynamics part drives the players' action to the GNE. On the other hand, adaptive penalty method is utilized to ensure the player's action enters the inequality constraints set without a prior estimation of centralized information for penalty parameters. The algorithm in this paper realizes complete distribution and parameter independence, making it easy to apply in practical programming. At last, several numerical examples regarding the electricity markets are employed to verify the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

Surrogate-assisted multi-objective evolutionary algorithms have been paid much attention to solve expensive multi-objective problems in recent years. However, with the number of objectives increasing, an improper solution may be picked for expensive objective evaluation due to the accumulation error of approximated values on objective functions. Furthermore, the time to construct surrogate models for all objectives will significantly increase. Thus, in this paper, Gaussian process (GP) models are proposed for performance indicators instead of for objective functions. Furthermore, solutions are selected from either of two ways to be evaluated using the expensive objective function. When there are non-dominated solutions found so far that are approximated, they will be exactly evaluated using the objective function. Otherwise, the solution with the maximum approximation uncertainty among the current population will be evaluated using the real objective functions. The efficiency of the presented approach is validated on the DTLZ test suite with 3, 6, 10, 15, and 20 objectives, MaF benchmark problems with 3, 6, 10, 15, and 20 objectives, and a real-world optimization problem called filter design. The experimental results show that the method proposed in this paper is competitive compared to recently proposed peer algorithms for expensive many-objective problems. [ABSTRACT FROM AUTHOR]

In this paper, we present a connectivity-preserving performance function approach for the distributed output-feedback synchronized tracking of uncertain heterogeneous nonlinear multiagent systems in a nonstrict-feedback form. Compared with existing output-feedback cooperative control results using neural networks, this paper contributes to developing a universal output-feedback synchronized control methodology that uses a connectivity-preserving performance function to ensure both initial network connectivity and preselected synchronization performance with a designable convergence time. To this end, a neural-network-based adaptive observer for each follower is designed to ensure the boundedness of estimation errors of unmeasurable states. Then, local event-triggered synchronized trackers using only relative output information and the connectivity-preserving performance function are constructed to guarantee the closed-loop stability in a low-complexity sense, where no adaptive neural networks and command filters are not required in the local trackers. Finally, a purely academic example and a practical platoon-control problem of multiple uncertain vehicular systems are considered to clarify and verify the proposed connectivity-preserving performance function approach in the simulation. [ABSTRACT FROM AUTHOR]

• The paper is the first batch that tries to inquiry the GPS of the PDIMNNs. Furthermore, unlike the previous literature [11,21,35] , the nonlinear substitution that converts the PDs system to a constant delays system is not used. Because the subsequent pro-cessing of the converted system is complicated, this paper directly performs on the original PDs system. • The paper employs the non-reduced-order method, which r-efrains the double-dimensional problem after reduced-order [3–5,23,24]. In practical applications, the method is more ponderable and si-gnificative for second-order scheme under controller. • In the paper, devise both the feedback controller and the adaptive controller for the first time to achieve the GPS of the PD-IMNNs. The advantages of the two types of controllers are compar-ed through numerical examples and simulations. The mathematical model is closer to reality, and selecting the appropriate controller in application can further reduce control expenses. This article probes into the global polynomial stabilization (GPS) of proportional delayed inertial memristive neural networks (PDIMNNs). Here, ruling out the reduced-order way, discuss the GPS of PDIMNNs under the second-order scheme directly. Firstly, a feedback controller is designed to make the system self-stabilizing. By designing suitable Lyapunov functional with adjustable parameters and combining with inequality techniques, two algebraic criteria are obtained to realize the GPS of the PDIMNNs. Owing to the conservatism caused by the ineluctable inequality scaling, it is worth noting that the controller gains are greater than the actual requirements. To further save control expenses, employing an adaptive controller to make the system stabilized. Finally, three numerical examples which sustain the usability of the obtained theoretical conclusions are shown. [ABSTRACT FROM AUTHOR]

• Algorithmic trading using self-attention based recurrent reinforcement learning is developed. • Self-attention layer reallocates temporal weights in the sequence of temporal embedding. • Hybrid loss feature is incorporated to have predictive and reconstructive power. Algorithmic trading based on machine learning has the advantage of using intrinsic features and embedded causality in complex stock price time series. We propose a novel algorithmic trading model based on recurrent reinforcement learning, optimized for making consecutive trading signals. This paper elaborates on how temporal features from complex observation are optimally extracted to maximize the expected rewards of the reinforcement learning model. Our model incorporates the hybrid learning loss to allow sequences of hidden features for reinforcement learning to contain the original state's characteristics fully. The self-attention mechanism is also introduced to our model for learning the temporal importance of the hidden representation series, which helps the reinforcement learning model to be aware of temporal dependence for its decision-making. In this paper, we verify the effectiveness of proposed model using some major market indices and the representative stocks in each sector of S&P500. The augmented structure that we propose has a significant dominance on trading performance. Our proposed model, self-attention based deep direct recurrent reinforcement learning with hybrid loss (SA-DDR-HL), shows superior performance over well-known baseline benchmark models, including machine learning and time series models. [ABSTRACT FROM AUTHOR]

Telemedicine provides remote online services for digital diagnosis and treatment via the Internet. However, there is a risk of data leakage during transmission. Therefore, data protection is an important challenge for telemedicine. Chaos is widely used in image, audio, and EEG encryption because of its unique characteristics of unpredictability, nonlinearity, and sensitivity to an initial state. However, some chaotic maps have various security issues. To solve these problems, this paper proposes a K-sine-transform-based coupled chaotic system (K-STBCCS), combining any two one-dimensional chaotic mappings to generate a new chaos mapping. To demonstrate the reliability of the system, this paper generates three new chaotic mappings using K-STBCCS and analyzes their performance. Using the chaotic mapping generated by K-STBCCS, this paper further proposes an EEG signal encryption scheme based on the confusion-diffusion principle. The purpose of confusion is to separate adjacent EEG signals, while the purpose of diffusion is to change the value of EEG signals. Among them, the diffusion operation uses positive and negative diffusion to reduce the correlation between the ciphertext and the original signals. The experimental results and security analysis show that the proposed EEG signal encryption scheme performs well and passes the rigorous cryptographic security test. [ABSTRACT FROM AUTHOR]

Negation is an important operation in evidence theory, whose idea is to consider the opposite of events, can deal with some problems with uncertainties from the opposite side and obtain information behind probability distribution. In classical D-S theory (Dempster-Shafer's theory), there are already many negation methods existed on real number field and many properties of which have been discovered. However, in complex evidence theory, which based on complex number field, negation is still an open problem. In order to deal with some problems like those in D-S theory, a new negation method for CBBA (Complex Basic Belief Assignment) should be proposed. In this paper, a new negation method called CBBA exponential negation will be presented, which can be seen as a generalization from BBA (Basic Belief Assignment) to CBBA. This proposed negation transforms a CBBA to another one with the entropy increased simultaneously. Also, some properties of this negation will be discussed such as invariance, convergence, fixed point, distribution of Pascal triangle, convergence speed, impact on negation convergence and so on. Besides, most among them will be strictly proved in this paper. Furthermore, a new entropy for CBBA and some numerical examples will be presented, and we will study the proposed negation from the view of entropy. Finally, an application of CBBA exponential negation will be shown in the end. [ABSTRACT FROM AUTHOR]

• An overlapping community finding method based on node/link information is proposed. • A new representation is introduced to encode and decode overlapping communities. • A novel two-phase mutation and a new double-point crossover are presented. • A metric is proposed to evaluate overlapping/non-overlapping partitions. • The proposed method shows better performance than the 15 other relevant methods. Community detection is one of the most important and interesting issues in social network analysis. Most of the current community detection algorithms tend to find communities in social networks with just considering the topological structures of the networks. In recent years, simultaneously considering of nodes' attributes and topological structures of social networks in the process of community detection has attracted the attentions of many scholars, and this consideration has been recently used in some community detection methods to increase their efficiencies and to enhance their performances in finding meaningful and relevant communities. But the problem is that most of these methods tend to find non-overlapping communities, while many real-world networks include communities that often overlap to some extent. In order to solve this problem, an evolutionary algorithm called MOBBO-OCD, which is based on multi-objective biogeography-based optimization (BBO), is proposed in this paper to automatically find overlapping communities in a social network with node attributes with synchronously considering the density of connections and the similarity of nodes' attributes in the network. In MOBBO-OCD, an extended locus-based adjacency representation called OLAR is introduced to encode and decode overlapping communities. Based on OLAR, a rank-based migration operator along with a novel two-phase mutation strategy and a new double-point crossover are used in the evolution process of MOBBO-OCD to effectively lead the population into the evolution path. In order to assess the performance of MOBBO-OCD, a new metric called alpha_SAEM is proposed in this paper, which is able to evaluate the goodness of both overlapping and non-overlapping partitions with considering the two aspects of node attributes and linkage structure. Quantitative evaluations, based on three extensive experiments on 14 real-life data sets with diverse characteristics, reveal that MOBBO-OCD achieves favorable results which are quite superior to the results of 15 relevant community detection algorithms in the literature. [ABSTRACT FROM AUTHOR]

In the era of big data, the data in many business scenarios are characterized by a small number of labelled samples and a large number of unlabelled samples. It is quite difficult to classify and identify such data and provide effective decision support for a business. A commonly employed processing method in this kind of data scenario is the disagreement-based semisupervised learning method, i.e., exchanging high-confidence samples among multiple models as pseudolabel samples to improve each model's classification performance. As such pseudolabel samples inevitably contain label noise, they may interfere with the subsequent model learning and damage the robustness of the ensemble model. To solve this problem, a semisupervised classification algorithm based on noise learning theory and a disagreement cotraining framework is proposed. In this model, first, the probably approximately correct (PAC) estimation theory under label noise conditions is applied, the relationship between the label noise level and model robust estimation in the process of multiround cotraining is discussed, and a disagreement elimination algorithm framework based on multiple-model (feature argument and select (FANS) algorithm and L1 penalized logistics regression (PLR) algorithm) cotraining is constructed based on this theoretical relationship. The experimental results show that the algorithm proposed in this paper gives not only a high-confidence sample set that meets the upper bound constraint of the label noise level but also a robust ensemble model capable of resisting sampling bias. The work performed in this paper provides a new research perspective for semisupervised learning theory based on disagreement. [ABSTRACT FROM AUTHOR]

Telemedicine provides remote online services for digital diagnosis and treatment via the Internet. However, there is a risk of data leakage during transmission. Therefore, data protection is an important challenge for telemedicine. Chaos is widely used in image, audio, and EEG encryption because of its unique characteristics of unpredictability, nonlinearity, and sensitivity to an initial state. However, some chaotic maps have various security issues. To solve these problems, this paper proposes a K-sine-transform-based coupled chaotic system (K-STBCCS), combining any two one-dimensional chaotic mappings to generate a new chaos mapping. To demonstrate the reliability of the system, this paper generates three new chaotic mappings using K-STBCCS and analyzes their performance. Using the chaotic mapping generated by K-STBCCS, this paper further proposes an EEG signal encryption scheme based on the confusion-diffusion principle. The purpose of confusion is to separate adjacent EEG signals, while the purpose of diffusion is to change the value of EEG signals. Among them, the diffusion operation uses positive and negative diffusion to reduce the correlation between the ciphertext and the original signals. The experimental results and security analysis show that the proposed EEG signal encryption scheme performs well and passes the rigorous cryptographic security test. [ABSTRACT FROM AUTHOR]

Negation is an important operation in evidence theory, whose idea is to consider the opposite of events, can deal with some problems with uncertainties from the opposite side and obtain information behind probability distribution. In classical D-S theory (Dempster-Shafer's theory), there are already many negation methods existed on real number field and many properties of which have been discovered. However, in complex evidence theory, which based on complex number field, negation is still an open problem. In order to deal with some problems like those in D-S theory, a new negation method for CBBA (Complex Basic Belief Assignment) should be proposed. In this paper, a new negation method called CBBA exponential negation will be presented, which can be seen as a generalization from BBA (Basic Belief Assignment) to CBBA. This proposed negation transforms a CBBA to another one with the entropy increased simultaneously. Also, some properties of this negation will be discussed such as invariance, convergence, fixed point, distribution of Pascal triangle, convergence speed, impact on negation convergence and so on. Besides, most among them will be strictly proved in this paper. Furthermore, a new entropy for CBBA and some numerical examples will be presented, and we will study the proposed negation from the view of entropy. Finally, an application of CBBA exponential negation will be shown in the end. [ABSTRACT FROM AUTHOR]

• An overlapping community finding method based on node/link information is proposed. • A new representation is introduced to encode and decode overlapping communities. • A novel two-phase mutation and a new double-point crossover are presented. • A metric is proposed to evaluate overlapping/non-overlapping partitions. • The proposed method shows better performance than the 15 other relevant methods. Community detection is one of the most important and interesting issues in social network analysis. Most of the current community detection algorithms tend to find communities in social networks with just considering the topological structures of the networks. In recent years, simultaneously considering of nodes' attributes and topological structures of social networks in the process of community detection has attracted the attentions of many scholars, and this consideration has been recently used in some community detection methods to increase their efficiencies and to enhance their performances in finding meaningful and relevant communities. But the problem is that most of these methods tend to find non-overlapping communities, while many real-world networks include communities that often overlap to some extent. In order to solve this problem, an evolutionary algorithm called MOBBO-OCD, which is based on multi-objective biogeography-based optimization (BBO), is proposed in this paper to automatically find overlapping communities in a social network with node attributes with synchronously considering the density of connections and the similarity of nodes' attributes in the network. In MOBBO-OCD, an extended locus-based adjacency representation called OLAR is introduced to encode and decode overlapping communities. Based on OLAR, a rank-based migration operator along with a novel two-phase mutation strategy and a new double-point crossover are used in the evolution process of MOBBO-OCD to effectively lead the population into the evolution path. In order to assess the performance of MOBBO-OCD, a new metric called alpha_SAEM is proposed in this paper, which is able to evaluate the goodness of both overlapping and non-overlapping partitions with considering the two aspects of node attributes and linkage structure. Quantitative evaluations, based on three extensive experiments on 14 real-life data sets with diverse characteristics, reveal that MOBBO-OCD achieves favorable results which are quite superior to the results of 15 relevant community detection algorithms in the literature. [ABSTRACT FROM AUTHOR]

In the era of big data, the data in many business scenarios are characterized by a small number of labelled samples and a large number of unlabelled samples. It is quite difficult to classify and identify such data and provide effective decision support for a business. A commonly employed processing method in this kind of data scenario is the disagreement-based semisupervised learning method, i.e., exchanging high-confidence samples among multiple models as pseudolabel samples to improve each model's classification performance. As such pseudolabel samples inevitably contain label noise, they may interfere with the subsequent model learning and damage the robustness of the ensemble model. To solve this problem, a semisupervised classification algorithm based on noise learning theory and a disagreement cotraining framework is proposed. In this model, first, the probably approximately correct (PAC) estimation theory under label noise conditions is applied, the relationship between the label noise level and model robust estimation in the process of multiround cotraining is discussed, and a disagreement elimination algorithm framework based on multiple-model (feature argument and select (FANS) algorithm and L1 penalized logistics regression (PLR) algorithm) cotraining is constructed based on this theoretical relationship. The experimental results show that the algorithm proposed in this paper gives not only a high-confidence sample set that meets the upper bound constraint of the label noise level but also a robust ensemble model capable of resisting sampling bias. The work performed in this paper provides a new research perspective for semisupervised learning theory based on disagreement. [ABSTRACT FROM AUTHOR]

• Proposes a new manner of spectral clustering to decrease the sensitivity • Gives an algorithm to calculate information entropy so as to value the risk ranks. • Evaluates SC-RBAC by the datasets and it is robust and efficient Access control has been widely adopted by distributed platforms, and its effectiveness is of great importance to the quality of services provided by such platforms. However, traditional access control is difficult to apply to scenarios where authorization changes frequently and to extremely large-scale datasets with limited resources. This paper proposes an access control model based on spectral clustering (SC) and risk (SC-RBAC), which is more suitable for big data medical scenarios. Based on user history access data, an improved SC algorithm is used to cluster doctor users. Then, the user classification is introduced as a parameter into the information entropy to improve the accuracy of quantifying the user's access behavior risk. Finally, based on the accurate risk value of access behavior, we assign access rights to users through the access control function constructed in the paper. Experimental results show that in three different situations, the model proposed in this paper can distinguish the two types of doctors well, the accuracy of the model can reach more than 90%, and it outperforms other access control models. [ABSTRACT FROM AUTHOR]

• In the framework of finite-time command filter control, this paper constructs a quadratic function in the controller. Compared with [23, 24, 25], the presented adaptive finite-time control algorithm not only solves the "explosion of complexity" problem effectively, but also circumvents the singularity problem. • In contrast to the literatures on finite-time control [43, 44, 45], the cases of faults happening during transmission phase of system are rarely considered. Moreover, nonlinear faults may exist in many real systems, which necessitates the design of fault-tolerant controllers to enhance the system reliability and guarantee consistent control performance. In this paper, nonaffine nonlinear faults are taken into account, which is more complex than linear faults studied in [37, 39, 46]. • Different from the results [28, 29, 47] which used the trial-and-error method to validate the observation gain matrix, this paper skillfully introduces the differential mean value theorem and the convex combination theorem to transform the acquisition of the observation gain matrix from solving a nonlinear matrix inequality to solving a set of LMIs. Meanwhile, the solvability of LMIs guarantees the stability of the observer and simplifies the algorithm. The present work deals with the consensus issue for nonlinear multiagent systems (MASs) subject to nonaffine nonlinear faults and unmeasurable states. First, the Butterworth low-pass filter (BLPF) is exploited to eliminate the algebraic loop problem arising from nonaffine nonlinear faults. In light of the convex combination theory, a neural observer is established to estimate the unmeasured states, which improves the efficiency of solving the observer gain. Then, with the help of the adaptive backstepping algorithm, an observer-based neural finite-time control protocol is proposed in which a quadratic function is constructed to circumvent the singularity problem. The finite-time stability criterion and Lyapunov stability theorem are utilized to demonstrate that all signals of the closed-loop system are bounded in finite time. Finally, a simulation experiment is applied to show the effectiveness of the present method. [ABSTRACT FROM AUTHOR]

This paper studies an adaptive fuzzy resilient control strategy for switched systems with deception attacks and state constraints. With the deception attacks on both the sensors and actuators, the feedback data is unreliable and the direction of control is unknown, which make it difficult to design the adaptive resilient control for switched systems. By combining Nussbaum-based adaptive control, fuzzy control and a two-step backstepping approach, a novel adaptive resilient controller and mode-dependent switching law are designed to against deception attacks. Considering the buffeting problem triggered by the Nussbaum function, the states are constrained in this paper and the barrier Lyapunov function is utilized. Based on the designed adaptive fuzzy resilient control method, both the asymptotic stability and the state constraints of the switched systems under deception attacks can be guaranteed. The feasibility of the proposed resilient control strategy is demonstrated through an application of the strategy to an attacked single-link robot arm (SLRA) model. [ABSTRACT FROM AUTHOR]

Perceptron Neural Networks (PNNs) are essential components of intelligent systems because they produce efficient solutions to problems of overwhelming complexity for conventional computing methods. Many papers show that PNNs can approximate a wide variety of functions, but comparatively, very few discuss their limitations and the scope of this paper. To this aim, we define two classes of Boolean functions – sensitive and robust –, and prove that an exponentially large set of sensitive functions are exponentially difficult to compute by multi-layer PNNs (hence incomputable by single-layer PNNs). A comparatively large set of functions in the second one, but not all, are computable by single-layer PNNs. Finally, we used polynomial threshold PNNs to compute all Boolean functions with quantum annealing and present in detail a QUBO computation on the D-Wave Advantage. These results confirm that the successes of PNNs, or lack of them, are in part determined by properties of the learned data sets and suggest that sensitive functions may not be (efficiently) computed by PNNs. [ABSTRACT FROM AUTHOR]

In this short note, we briefly present and discuss an example of page rank algorithm given in [Information Sciences 150 (2003) 165-176]. [ABSTRACT FROM AUTHOR]

Multimodal emotion recognition, that is, emotion recognition uses machine learning to generate multi-modal features on the basis of videos which has become a research hotspot in the field of artificial intelligence. Traditional multi-modal emotion recognition method only simply connects multiple modalities, and the interactive utilization rate of modal information is low, and it cannot reflect the real emotion under the conflict of modal features well. This article first proves that effective weighting can improve the discrimination between modalities. Therefore, this paper takes into account the importance differences between multiple modalities, and assigns weights to them through the importance attention network. At the same time, considering that there is a certain complementary relationship between the modalities, this paper constructs an attention network with complementary modalities. Finally, the reconstructed features are fused to obtain a multi-modal feature with good interaction. The method proposed in this paper is compared with traditional methods in public datasets. The test results show that our method is accurate in It performs well in both the rate and confusion matrix metrics. [ABSTRACT FROM AUTHOR]

This paper focuses on the use of differential evolution to improve the approximation properties of function approximation models based on fuzzy partitions. Two cases are considered: Fuzzy transform and Fuzzy projection, and the design of hybrid evolutionary fuzzy systems, is studied. Even though function approximation techniques based on fuzzy partitions have been well studied, few papers consider the problem of centroid selection of the basis functions. Thus, in most cases uniform fuzzy partitions are considered. By using an evolutionary algorithm a systematic approach on the selection of the partition, is provided. The optimisation problem involves the determination of the model parameters, which in our case are the fuzzy partition's membership functions' locations. The proposed method is tested on the scattered data approximation problem, in a regression sense, that is given a set of sparse data the latent function is approximated. Numerical studies on one and two-dimensional test functions demonstrate that the evolutionary algorithm based fuzzy projection displays high performance in terms of approximation error. Moreover, the proposed approach shows high approximation capabilities with a small number of basis functions. Comparison results, with uniform fuzzy partition models, neural networks and support vector machines, are provided. [ABSTRACT FROM AUTHOR]

The optimal balance and dispatch of power plants in a smart grid require an accurate short-term forecast of photovoltaic (PV) power generation. The climatic condition may have an impact on the PV output, but it is difficult to be used in forecasting due to untimely sampling of meteorological data. To this end, this paper presents an incremental learning using privileged information (LUPI) paradigm for PV power forecasting by using stochastic configuration network. This novel algorithm can employ the meteorological data as privileged information for building PV power forecasting model in the training stage. Additionally, the model performance has been fully discussed in this paper. Finally, experimental results indicate that the proposed model indeed performs favorably in PV power forecasting. [ABSTRACT FROM AUTHOR]

• The event-triggered mechanism in this paper does not involve any global information. • This paper assumes this sub-graph is directed and the control input of leader is derivable. The main obstacle is the complex and unpleasant interaction between the non-linear function used to handle the control input of leader and the directed sub-graph between followers. • This paper designs a fully distributed event-triggered controller, thus, only needs discrete communication among neighboring agents, which is more suitable to be utilized in practical engineering. This article studies the design method of fully distributed event-triggered output feedback protocol for linear multi-agent systems with a derivable leader under directed graphs. The research on such problems in the existing reference needs complete state feedback and the state variable of the adaptive law used in the literature controller is monotonic and non decreasing, which may make the control input exceed the actual saturation value, thus affecting the practical application. How to design a completely distributed event-triggered adaptive output feedback protocols for multi-agent systems with a derivable leader on directed graphs is an open issue. In order to overcome the difficulty of designing the controller without complete state information, we design the event-triggered output feedback protocol, and with the help of σ -modification techniques, ensure the boundedness of the adaptive law in proposed protocol. The conditions to ensure the realization of the leader–follower consensus and exclude Zeno behavior are given. Furthermore, the control protocol is fully distributed and uses neighbor information only when the event trigger conditions are satisfied. Finally, the availability of the proposed protocol is illustrated by simulation examples. [ABSTRACT FROM AUTHOR]

In this paper, the communication network associated with a linear heterogeneous clustered multi-agent system (CMAS) contains several clusters, each of which is modeled by a strongly connected digraph and contains a leader. Intra-cluster agents are in continuous communication with their intra-cluster neighbors during the communication period, whereas only the inter-cluster leaders can communicate with other leaders at a series of discrete moments, known as the reset time. Thus this paper presents a reduced-order observer-based reset output feedback controller that solves the output synchronization problem associated with the linear heterogeneous CMAS. Specifically, a reset internal model is built to solve the output synchronization for each agent, and a reset reduced-order observer is developed to estimate the unavailable states of each agent. Then an output feedback control strategy is developed using only the output information, internal model state, and observer state. Sufficient conditions are also obtained for ensuring the output synchronization of the CMAS. Finally, an illustrative example is provided to demonstrate the efficiency of the proposed control strategy. [ABSTRACT FROM AUTHOR]

• This paper presents MASK, a multilevel algorithm for approximate similarity search • MASK can distribute the index over as many computing nodes as we can afford. • Experimental results show the applicability of this novel indexing method • MASK achieves superior performance with high-dimensional and high-sparsity datasets. Similarity search based on a distance function in metric spaces is a fundamental problem for many applications. Queries for similar objects lead to the well-known machine learning task of nearest-neighbours identification. Many data indexing strategies, collectively known as Metric Access Methods (MAM), have been proposed to speed up these queries. Moreover, since exact approaches to solving similarity queries can be complex and time-consuming, alternative options have emerged to reduce query execution time, such as returning approximate results or resorting to distributed computing platforms. In this paper, we introduce MASK (Multilevel Approximate Similarity search with k -means), an unconventional application of the k -means algorithm as the foundation of a multilevel index structure for approximate similarity search suitable for metric spaces. We show that this method leverages inherent properties of k -means for this purpose, like representing high-density data areas with fewer prototypes. An implementation of this new indexing procedure is evaluated using a synthetic dataset and two real-world datasets in high-dimensional and high-sparsity spaces. Experimental tests show that MASK performs better than alternative algorithms for approximate similarity search. Results are promising and underpin the applicability of this novel indexing method in multiple domains. [ABSTRACT FROM AUTHOR]

• Temporal information is effectively integrated into the representation model. • A new prediction model is proposed to gain temporal information. • The memory capacity of the replay buffer is smaller than the existing methods. • The policy lag is proven to be decreased quickly in maximum-entropy reinforcement learning. Partially observable Markov decision process (POMDP) is a key challenging problem in the application of reinforcement learning since it comprehensively describes real agent-environment interactions. Recent works mainly utilize conventional reward signals to train a representation that converts POMDPs to MDPs. However, rewards alone are not enough for a good representation without temporal information. In this paper, we first introduce a novel Recurrent Prediction Model to integrate temporal information into the representation that solves POMDP problems by training three additional unsupervised prediction models, named transition model, reward recovery model, and observation recovery model. This paper secondly makes a modification of the data structure of vanilla replay buffer to reduce the memory usage and thirdly proposes an off-policy correction algorithm to decrease the policy lag in POMDPs. The experiments show that our model achieves better performance in partially observable environments on both stand-alone and distributed training systems. [ABSTRACT FROM AUTHOR]

As an unsupervised learning method, clustering does not need to know prior knowledge of the datasets in advance. How determining the optimal number of clusters becomes an important method to judge the quality of clustering results. For fuzzy clustering algorithms, the introduction to fuzzy partition makes it more consistent with the structure of real datasets than hard clustering algorithms. Therefore, it is necessary to carry out the research on the validity evaluation methods of fuzzy clustering. At present, the research on fuzzy clustering validity mainly focuses on the fuzzy clustering validity index (FCVI) and the combined fuzzy clustering validity evaluation method (CFCVE). From these two aspects, this paper reviews fuzzy clustering validity functions and combined fuzzy clustering validity evaluation methods. Then FCVI and CFCVE are discussed in details from different points on fuzzy clustering validity functions, and the research status and construction strategies of different fuzzy clustering validity evaluation methods are analyzed. The accuracy and stability of each fuzzy clustering validity evaluation method are analyzed through comparative experiments. Finally, the paper summarizes the shortcomings and advantages of the current research on fuzzy clustering validity and looks forward to the research direction and improved methods of the evaluation methods. [ABSTRACT FROM AUTHOR]

• Many ML algorithms are used to identify the main determinants of a bank default. • We use of a graph neural network that has never been used in a financial context. • We obtain a balanced dataset by customizing the heuristic oversampling method. • Like previous literature, we show that neural network outperforms other approaches. • We include, for the first time, competition among the possible default determinants. The financial sector is very interested in Artificial Intelligence due to the opportunities that it offers, especially those related to methods of machine-learning. The aim of this paper is to employ a variety of machine-learning algorithms to identify the main determinants of bank default and to understand the impact of each variable on it. Bank default is one of the most studied topics in financial literature because of the severity of its consequences on the whole economic system. However, little attention has been paid to the identification of the major determinants of bank failures via machine-learning approaches. This paper employs several machine-learning algorithms, including a graph neural network that has never been used in a financial context. Another novelty is the implementation of a balanced dataset by customising the heuristic oversampling method based on k-means and synthetic minority over-sampling technique. This paper also deals with the inclusion of competition among the possible default determinants. The dataset consists of all the banks in the Euro Area in the period 2018–2020. The results obtained are useful from both micro- and macro-economic points of view. [ABSTRACT FROM AUTHOR]

• A novel approach is proposed to evaluate health based on body area networks. • A multi-sign parameter fusion health assessment model is developed based on BPNN. • The effect of the number of nodes and activation function on the model is explored. • The optimized model is validated by comparing it with other machine learning methods. The widespread application of technologies such as the Internet of Things (IoT) and wireless sensors has promoted the development of body area networks (BAN) in the area of intelligent monitoring. However, current health assessment methods based on BAN still have problems such as a high false alarm rate and low efficiency in identifying signs and states, which not only increase the psychological burden of the ward but also bring unnecessary troubles to the medical staff. In response to this problem, this paper proposes a multi-sign parameter fusion health assessment model based on BP neural network (BPNN). Firstly, the blood pressure, heart rate, pulmonary hypertension, respiration rate, blood oxygen, and body temperature are obtained by sensors in real-time, and then these six parameters are fused by the BPNN. In addition, aiming at the problems of slow convergence speed and easy falling into a local minimum in BPNN, the structure of this model is optimized, and the influence of the number of neurons and activation function of the hidden layer on the performance of the model is explored. Results show that when the number of neurons in the hidden layer is 13 and the activation function is Logsit, the performance of the model is optimal. Among them, the recognition accuracy of the model is 95 %, and the running time is 2.798 s. Finally, comparing the recognition results of this model with support vector machines (SVM), genetic BP neural networks (GA-BPNN), and fuzzy neural networks (FNN), it is found that the accuracy of these three methods is 70 %, 70 % and 80 % respectively, which verifies the validity of the model proposed in this paper. [ABSTRACT FROM AUTHOR]

This paper studies model predictive security control (MPSC) for networked switched systems under denial-of-service (DoS) attacks. Most of existing works only adjust the triggering scheme when being attacked. Different from them, this paper proposes a novel timing-response event-triggering scheme (TR-ETS) to reduce the impact of attacks on system performance, which can not only configure system resources adaptively, but also accurately detect attack information and compensate the attacked data. Specifically, the proposed scheme includes two event-based triggers, which can dynamically and jointly regulate the communication/calculation ability, generate virtual attack sequences and acquire the number of passive packet loss. Then, based on the triggered states, a class of model predictive controllers is designed to optimize the control action. Due to possible strong attacks, a security control framework including network and local loops be introduced and a permissable type-switching mechanism (PTM) is used. Under the permissable controllers (i.e., network and local controllers), sufficient conditions for the stability of closed-loop switched systems are derived. In addition, a set of model predictive optimization algorithm using linear matrix inequalities (LMIs) technique is addressed. Finally, the effectiveness of the proposed method is verified by illustrative examples. [ABSTRACT FROM AUTHOR]

This paper presents a method to generate preference ordering relations on interval space based on a family of automorphisms on the bidimensional Euclidean space. This method generates a family of order relation with which many order relations presented in the literature can be obtained as particular cases. This family of preference order relations is used to provide a formulation for a family of interval optimization problems that unifies those formulations whose solution concepts are a Pareto-type. The elements belonging to this family are called φ -interval optimization problems. An advantage of the proposed method is that decision makers can consider a suitable interval optimization problem, choosing an appropriate order relation, which is obtained by choosing an automorphism. Moreover, this paper shows that each φ -interval optimization problem is equivalent to a biobjective optimization problem. Some optimality conditions for the φ -interval optimization problems are obtained. The method, concepts and results presented herein are illustrated by several examples. [ABSTRACT FROM AUTHOR]

• A many objective evolutionary algorithm based on decomposition and moth search is proposed. • Random and adaptive weights is used to break the limitation of uniform distribution weights. • Mutual evaluation value is used to evaluate the optimal individual in the neighborhood. • Improving scale factor α in MSA is to improve the performance of the proposed algorithm. Decomposition-based multi-objective evolutionary algorithm (MOEA/D) has good performance in solving multi-objective problems (MOPs) but poor performance in solving many-objective optimization problems (MaOPs). The weight vectors in MOEA/D are relatively fixed, which results in poor performance when dealing with complex MaOPs. In this paper, random and adaptive weights are introduced into MOEA/D to break the limitation of fixed weight vectors. And the moth search algorithm (MSA) is used as an operator to improve global search ability. The updating strategies in MSA are more consistent with the neighborhood learning strategy adopted in MOEA/D. In addition, to enable MSA to find the optimal solution in the neighborhood on the MaOPs to update other individuals. This paper introduces mutual evaluation value for evaluating the optimal individual in the neighborhood, and the proposed algorithm is abbreviated as MOEA/DMS. In comparative experiments on the MaF test suite, hypervolume (HV) and inverted generational distance (IGD) are used to measure MOEA/DMS and other many-objective evolutionary algorithms (MaOEAs). The results show that MOEA/DMS has an excellent performance in dealing with MaOPs. Besides, MOEA/DMS is compared with other state-of-the-art MaOEAs on two combinatorial MaOPs. The results show that MOEA/DMS also has significant advantages in dealing with combinatorial MaOPs. [ABSTRACT FROM AUTHOR]

Heterogeneous multi-criteria group decision making (MCGDM) is a hot topic in the decision analysis field. This paper proposes a fairness-concern-based LINMAP (Linear Programming Technique for Multidimensional Analysis of Preference) method for heterogeneous MCGDM with hesitant fuzzy linguistic (HFL) truth degrees. Heterogeneous evaluation information includes crisp numbers, interval numbers, intuitionistic fuzzy values (IFVs), trapezoidal fuzzy numbers (TrFNs) and hesitant fuzzy sets (HFSs). This paper introduces the fairness concern to calculate the HFL consistency and the HFL inconsistency indices. Based on the framework of LINMAP, a bi-objective HFL programming model is built to derive the criteria weights, the positive ideal fairness vector (PIFV) and the negative ideal fairness vector (NIFV) for each decision maker (DM) simultaneously. Based on the TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution), a multi-objective programming model is built to obtain DMs' weights. The alternatives ranking is derived by comprehensive collective relative closeness degrees. Finally, a real example is applied to verify effectiveness and superiority of this heterogeneous MCGDM method. The proposed heterogeneous MCGDM method provides a very useful approach for MCGDM with heterogeneous information. [ABSTRACT FROM AUTHOR]

This paper introduces the Ulimisana Optimisation Algorithm enabled Population Based Training (PBT-UOA) framework which allows for hyperparameters to be fine-tuned using a population based meta-heuristic algorithm at the same time as parameters are being optimised. Models are trained until near-convergence on the updated hyperparameters and the parameters of the best performing model are shared to warm start the other models in the next hyperparameter tuning iteration. In the PBT-UOA, all models are trained using the same dataset. This framework performed better than the Bayesian Optimisation algorithm. This paper also introduces the Ulimisana Optimisation Algorithm enabled Federated Learning (FL-UOA) framework which is an extension of the PBT-UOA. This framework is introduced to address the challenges of scattered datasets and privacy that is presented by the increase in connected end-devices. The FL-UOA learns on local data in scattered end-devices without sending datasets to a central server. The training datasets in local end-devices are used to evaluate models trained in other end-devices. The performance metrics are used to update the Social Trust Network (STN) of the FL-UOA framework. The FL-UOA outperformed the classic Federated Learning framework. This STN updating technique was tested in Machine Learning (ML) Unfairness to see how well it functioned as a regularisation term. This was achieved by training different models on subsets that contained datasets representing only specific sensitive groups. Results showed that by updating the hyperparameters while learning the parameters on the dataset scattered across different devices, the FL-UOA, takes advantage of diversified learning and reduces the ML Unfairness for models trained on group specific datasets. [ABSTRACT FROM AUTHOR]

• Introduced the signal-to-noise ratio distance metric in metric learning to the PSO community. • A new adaptive strategy selection framework is proposed, named ESE-SNR. • Nonlinear acceleration coefficient based on singer mapping is used to better balance diversity and convergence. • A global best perturbation mechanism is employed to help the population escape from the local optimum. • The results show the algorithm outperforms or is comparable to other PSO variants and meta -heuristic evolutionary algorithms. This paper proposes an adaptive multistrategy ensemble particle swarm optimization (PSO) with signal-to-noise ratio (SNR) distance metric called AMSEPSO, which aims to solve the problems of a single learning mode of PSO and easy premature convergence when solving complex problems. In AMSEPSO, an evolutionary state estimation (ESE) strategy selection framework is proposed based on the SNR distance metric, named ESE-SNR. The appropriate learning strategy is adaptively selected through the ESE-SNR framework. To balances diversity and convergence better, nonlinear acceleration coefficient based on Singer mapping is adopted. Finally, a global best perturbation mechanism is employed to help the population escape from the local optimum. On the CEC2017 benchmarks, comparison with other advanced PSO variants and meta -heuristic algorithms show that AMSEPSO achieves remarkable performance in solving functions with different characteristics, ranking first in the results. The results show that the ESE-SNR framework can effectively evaluate the search state of the population and can greatly save the computational time of the evaluation. The ESE-SNR framework proposed in this paper provides an innovative idea for the development of multistrategy ensemble learning, and the introduction of metric learning into the PSO community helps further promote the organic integration of machine learning and swarm intelligence. [ABSTRACT FROM AUTHOR]

• This paper presents a soft and hard hybrid qualitative balanced clustering (SHHQBC). • Qualitative balancing produces clusters with the lowest cardinality and highest value which are very practical. • Creating value criterion with the SHHQBC method enhanced quantitative and qualitative clustering criteria. K-means is a popular clustering method that has consistently failed to produce a balanced cluster structure. While changes in cardinality, variance, and density have arisen due to the importance of balancing in different fields, balancing has never been viewed from a qualitative viewpoint. The current paper takes a new look at cluster balancing by presenting a soft (balance-driven) and hard (balance-constrained) hybrid qualitative balanced clustering (SHHQBC). It starts by identifying and prioritizing key features using a random forest algorithm and the mean decrease in the Gini coefficient criterion. It then uses a weighted linear combination of features with the importance of above 25%, 50%, and 75% to construct a feature called value criterion. The developed clustering approach is then implemented to establish clusters with the highest value with the least cardinality or a value similar to other clusters. By implementing the SHHQBC on 14 different datasets, first soft clustering is implemented for all three cases and balanced conditions are checked. Hard clustering is then performed to make balanced conditions. Finally, the best-balanced case with the least objective function is selected. Formulating the value criterion facilitates the interpretation and labeling of clusters, and quantitative clustering criteria are improved. [ABSTRACT FROM AUTHOR]

The present paper introduces two models of three-way decision with ranking and reference tuple on hybrid information tables. One is the model with an importance ratio, and the other is the model with any importance ratio, where importance ratio describes the quantitative comparison of importance between two attribute subsets. A unique measure is proposed to assess the trisections generated by the two models and, correspondingly, the concepts of local optimal and global optimal trisections are proposed respectively. The two models have good properties which enable the algorithms provided in this paper to compute the optimal trisections in finite steps. Through comparison and experiments on real data, we show that the two models have strong expressive power and capture two different types of trisecting problems on hybrid information tables, and demonstrate the feasibility and practicality of our method in potential applications. [ABSTRACT FROM AUTHOR]

This paper studies the output feedback stabilization of the linear switched systems with quantization and time-delay. Under the coupled effect of time-delay and sampling, there is a complex mismatch between the system and the controller modes, which increases the difficulty of quantization rules design. Moreover, the switching of system modes brings challenges to the state reconstruction based on output signals. The purpose of this paper is designing a feedback controller based on a state observer to ensure the exponential convergence and Lyapunov stability of the switched systems. First, a virtual system is introduced to update the observer state to deal with the complex mismatch between the system and controller modes. Second, quantization rules are designed separately relying on the switching situations during the state reconstruction. Last, the upper bound of the system state is obtained by discussing the increasing/decreasing rate of Lyapunov function, and the system stability is guaranteed. Two-tank system is adopted to illustrate the effectiveness of the main results. [ABSTRACT FROM AUTHOR]

Evolutionary algorithms (EAs) that integrate niching techniques are among the most effective methods for multimodal optimization problems. However, most algorithmic contributions are based on empirical performance observations rather than rigorous mathematical convergence support; this makes most existing methods parameter sensitive. Inspired by a recently proposed deterministic global optimization method, granular sieving (GrS), an extended global optimization method named collaborative GrS (Co-GrS) and a novel deterministic multi-EA design framework are proposed in this paper. The innovations are threefold. (1) Existing EAs are stochastic methods, and this paper introduces the principle of deterministic global optimization into EA for the first time in the literature. (2) A deterministic multi-EA framework is designed and implemented in the paper; from the perspective of population evolution, an easy-to-operate survival-of-the-fittest strategy based on mathematical principles is established in Co-GrS. (3) Unlike existing stochastic EAs, where the reproducibility of optimal solutions is achieved in a statistical sense, Co-GrS does not involve random parameters, and it automatically runs the algorithm only once with pre-set fixed parameters to find all optimal solutions. The experimental results demonstrate the effectiveness and competitiveness of our method compared to 16 state-of-the-art multimodal algorithms on the CEC'2013 benchmark suite. [ABSTRACT FROM AUTHOR]

This paper focuses on optimal strategies and the profit allocation of the three-echelon food supply chain (FSC) formed by a farmer, a food processor and two retailers. By comparing optimal strategies in the decentralized and the centralized scenarios, we find that the centralized scenario generates the largest profit. On this basis, considering the supply chain link cycle structure and the coalition restriction caused by the technology, the division of the labor, the politics and the history reasons, this paper adopts the average tree solution to distribute the profit. To illustrate the superiority of the new distribution scheme, a numerical example is given to compare the new scheme with five previous allocation mechanisms. The results show that the new scheme is more practical and more reasonable than the previous ones. This paper proposes the first method using the cooperative game theory with the communication structure to allocate the profits of FSC with a link cycle. [ABSTRACT FROM AUTHOR]

There are two common challenges in multi-label learning (MLL), complex label relation and imbalanced class. Few studies have focused on addressing both problems at the same time. In this paper, we propose a multiple kernel learning (MKL) approach to tackle two challenges, named as Multi-Kernel Multi-Label (MKML) method. MKML contains three kernel modules. The first kernel module adopts the traditional kernel function which contains the global information, and the other two kernel modules are designed for the two problems respectively. The second kernel module learns the inter-label relation by adding supervised information. The third kernel module adjusts the imbalanced decision boundary through multi-layer fusion strategy, which is proved to improve the representation ability of kernels in this paper. Finally, the proposed joint optimization method in this MKL framework achieves good generalization ability. We conduct several related experiments using real-world datasets to evaluate the effectiveness of our method. The results demonstrate that MKML outperforms other state-of-the art methods in MLL task. [ABSTRACT FROM AUTHOR]

Although conventional dynamic surface filters can eliminate the issue of complexity explosion in backstepping design, the convergence of filter errors significantly influences the overall control performance. This paper proposes a unified design framework of an event-triggered adaptive fuzzy design scheme with fixed-time performance for unmodeled strict-feedback nonlinear systems, where the tracking performance, filter error, and parameter learning convergence are considered simultaneously. The unified framework guarantees the smoothness of all the closed-loop signals. A novel dynamic surface filter is designed to avoid the repeated differentiation of recursive virtual control while the filter error converges in fixed time. Compared with the conventional backstepping design, the proposed adaptive fuzzy controller design in this paper can guarantee fixed-time tracking performance. An event-triggered condition with intermittent feedback is developed to decrease the computational and communication burden. Two simulation examples are provided to validate the effectiveness of the unified fixed-time framework. [ABSTRACT FROM AUTHOR]

In real applications, the label information on many data is inaccurate, or a completely reliable label needs to be obtained at a high cost. The previous supervised hashing algorithms consider only the label information in the mapping process from Euclidean space to Hamming space when learning hash codes. However, there is no doubt that these algorithms are suboptimal in maintaining the relationships between high-dimensional data spaces. To overcome this problem, this paper advances a new weakly supervised discrete discriminant hashing (WDDH) to ensure a more effective representation of data and better retrieval of information. First, we consider the nearest neighbour relationship between samples, and new neighbourhood graphs are constructed to describe the geometric relationship between samples. Second, the algorithm embeds the learning of the hash function into the model and optimises the hash codes by a one-step iterative updating algorithm. Finally, it is compared with the existing classical unsupervised hashing algorithm and supervised hashing algorithm on different databases. The results and discussion of the experiments clearly show that the proposed WDDH algorithm in this paper is more robust for data representation in learning low-quality label data, coarse-grained label data and noisy data. [ABSTRACT FROM AUTHOR]

• A parallel EA with primary-auxiliary knowledge is proposed, using our improved cuckoo search algorithm as the primary knowledge and integrating several other EA as the auxiliary knowledge, which fundamentally enables the hybrid of different algorithms and greatly enhances algorithmic diversity. • The way of acting of the evolutionary strategy change from the traditional greedy selection to the balanced primary-auxiliary approach in this paper, which allows each strategy to work in iteration. • A novel knowledge migration strategy is proposed, which allows the primary knowledge to learn the excellent knowledge from the auxiliary knowledge through a novel topology designed for knowledge migration. The development of hybrid algorithms or the application of multiple strategies is one of the focal points for research on improving evolutionary algorithms. However, since most of the evolutionary equations of different algorithms can be transformed into each other, it is difficult to change the established properties of the given algorithm through a hybrid algorithm based on a mixture of evolutionary equations. In addition, multi-strategy methods tend to adopt the best strategy for the current local domain through greedy strategies in the solution process, which does not ensure validity in the global domain. Recently, Federated Learning has achieved remarkable results in machine learning, where the idea of model independence, parallelism and data sharing can essentially compensate for the weaknesses of hybrid and multi-strategy algorithms. Inspired by the idea of Federated Learning, this paper proposes an evolutionary algorithm named as parallel based Evolutionary Algorithm with primary-auxiliary knowledge. Specifically, a Spark-based primary-auxiliary knowledge model is developed, with different evolutionary algorithms used on each parallel sub-model. Then, an effective topological knowledge (individual) migration method is devised, which enables the primary knowledge model to learn the best knowledge from different auxiliary knowledge models through a topological structure. In this way, the best knowledge on the auxiliary knowledge models can be transferred to the primary knowledge model. Through a test conducted on the CEC2013 test set, it can be found out that the proposed algorithm clearly outperforms the 10 algorithms compared, which demonstrates the excellent performance of our proposed parallel based evolutionary algorithm with primary-auxiliary knowledge. [ABSTRACT FROM AUTHOR]

Fuzzy rough set theory can tackle feature redundancy in data and select more informative features for machine learning tasks. Gaussian kernel is often coupled with fuzzy rough set theory to measure fuzzy relation between data instances. However, Gaussian kernel has a serious long-tail phenomenon, which would perform poorly in modeling the fuzzy relation for high-dimensional data. Moreover, a robust feature evaluation function is also nontrivial in a fuzzy rough set model because a naive model may select those non-optimal feature subsets due to the perturbations from redundant features. This paper delves into Student- t kernel and fuzzy divergence to address these challenges for fuzzy rough feature selection. This paper proposes a new Student- t Kernelized Fuzzy Rough Set (SKFRS) model. The new model uses fuzzy divergence to evaluate uncertain information in the data. It also explores a newly-defined feature evaluation function on the biases of the dynamic relation between the relevance and indispensability of features in feature selection process. A novel forward greedy search algorithm is then presented to solve the final objective function. The selected features are subsequently evaluated on downstream classification tasks. Experimental results using real-world datasets demonstrate the effectiveness of the proposed model and its superiority against the baseline methods. [ABSTRACT FROM AUTHOR]

• A parallel EA with primary-auxiliary knowledge is proposed, using our improved cuckoo search algorithm as the primary knowledge and integrating several other EA as the auxiliary knowledge, which fundamentally enables the hybrid of different algorithms and greatly enhances algorithmic diversity. • The way of acting of the evolutionary strategy change from the traditional greedy selection to the balanced primary-auxiliary approach in this paper, which allows each strategy to work in iteration. • A novel knowledge migration strategy is proposed, which allows the primary knowledge to learn the excellent knowledge from the auxiliary knowledge through a novel topology designed for knowledge migration. The development of hybrid algorithms or the application of multiple strategies is one of the focal points for research on improving evolutionary algorithms. However, since most of the evolutionary equations of different algorithms can be transformed into each other, it is difficult to change the established properties of the given algorithm through a hybrid algorithm based on a mixture of evolutionary equations. In addition, multi-strategy methods tend to adopt the best strategy for the current local domain through greedy strategies in the solution process, which does not ensure validity in the global domain. Recently, Federated Learning has achieved remarkable results in machine learning, where the idea of model independence, parallelism and data sharing can essentially compensate for the weaknesses of hybrid and multi-strategy algorithms. Inspired by the idea of Federated Learning, this paper proposes an evolutionary algorithm named as parallel based Evolutionary Algorithm with primary-auxiliary knowledge. Specifically, a Spark-based primary-auxiliary knowledge model is developed, with different evolutionary algorithms used on each parallel sub-model. Then, an effective topological knowledge (individual) migration method is devised, which enables the primary knowledge model to learn the best knowledge from different auxiliary knowledge models through a topological structure. In this way, the best knowledge on the auxiliary knowledge models can be transferred to the primary knowledge model. Through a test conducted on the CEC2013 test set, it can be found out that the proposed algorithm clearly outperforms the 10 algorithms compared, which demonstrates the excellent performance of our proposed parallel based evolutionary algorithm with primary-auxiliary knowledge. [ABSTRACT FROM AUTHOR]

• A new nonlinear hybrid vehicle routing problem is developed. • An ambiguous equilibrium risk value objective function is defined. • An ambiguity set is constructed via the central limit theorem. • The proposed model is derived to a mixed integer second-order cone programming. • Experimental studies show the applicability of the proposed approach. A novel nonlinear hybrid vehicle routing problem is examined, and its nonlinear component is linearised considering the transportation costs associated with electricity and traditional fuel-based driving. Due to the fact that the transportation cost and fuel consumption involve the twofold uncertainty of randomness and fuzziness, and only partial probability distribution information may be available. Therefore, these two parameters are considered as random fuzzy variables with ambiguous probability distributions. An ambiguous equilibrium risk value objective function and an ambiguous equilibrium chance constraint are formulated. Accordingly, a distributionally robust equilibrium approach is proposed, in which the ambiguity sets are used to characterize the ambiguous probability distributions of the random fuzzy variables. Specifically, this paper first applies the central limit theorem to construct the ambiguity sets. Subsequently, the inner ambiguous probability constraint and the outer credibility constraint are derived into their equivalent counterparts, respectively. In this manner, the proposed model is successfully converted into a mixed integer second-order cone programming model, where the conventional branch-and-cut algorithm is adopted to obtain the optimal routing. Finally, the performance of the proposed model and its price of distributional robustness are verified in the numerical experiments. Overall, the main achievements of this paper are summarized as (1) the proposal of a distributionally robust equilibrium optimization model for a nonlinear hybrid vehicle routing problem, (2) the definitions of an ambiguous equilibrium risk value objective function and an ambiguous equilibrium chance constraint under twofold uncertainty, and (3) the derivation of an equivalent second-order cone programming model for computationally solvable. [ABSTRACT FROM AUTHOR]

Fuzzy rough set theory can tackle feature redundancy in data and select more informative features for machine learning tasks. Gaussian kernel is often coupled with fuzzy rough set theory to measure fuzzy relation between data instances. However, Gaussian kernel has a serious long-tail phenomenon, which would perform poorly in modeling the fuzzy relation for high-dimensional data. Moreover, a robust feature evaluation function is also nontrivial in a fuzzy rough set model because a naive model may select those non-optimal feature subsets due to the perturbations from redundant features. This paper delves into Student- t kernel and fuzzy divergence to address these challenges for fuzzy rough feature selection. This paper proposes a new Student- t Kernelized Fuzzy Rough Set (SKFRS) model. The new model uses fuzzy divergence to evaluate uncertain information in the data. It also explores a newly-defined feature evaluation function on the biases of the dynamic relation between the relevance and indispensability of features in feature selection process. A novel forward greedy search algorithm is then presented to solve the final objective function. The selected features are subsequently evaluated on downstream classification tasks. Experimental results using real-world datasets demonstrate the effectiveness of the proposed model and its superiority against the baseline methods. [ABSTRACT FROM AUTHOR]

Proximal policy optimization (PPO) algorithm is a deep reinforcement learning algorithm with outstanding performance, especially in continuous control tasks. But the performance of this method is still affected by its exploration ability. Based on continuous control tasks, this paper analyzes the original Gaussian action exploration mechanism in PPO algorithm, and clarifies the influence of exploration ability on performance. Afterward, aiming at the problem of exploration, an exploration enhancement mechanism based on uncertainty estimation is designed in this paper. Then, we apply exploration enhancement theory to PPO algorithm and propose the proximal policy optimization algorithm with intrinsic exploration module (IEM-PPO). In the experimental parts, we evaluate our method on multiple tasks in MuJoCo phsysical simulator, and compare IEM-PPO algorithm with PPO and PPO with intrinsic curiosity module (ICM-PPO). The experimental results demonstrate that IEM-PPO algorithm performs better in terms of sample efficiency and cumulative reward, and has stability and robustness. [ABSTRACT FROM AUTHOR]

This paper is concerned with the stability of switched systems with unstable subsystems under a novel switching signal. By establishing the free-quasi-alternative switching signal where switches are admissible between any two subsystems, the global exponential stability of the switched system is discussed. Compared with stability criteria under the quasi-alternative switching signal, switches among unstable subsystems are allowable, and the restriction that all unstable subsystems should reside for short is relaxed. The stability results are more general and less conservative in this paper, which is illustrated with a numerical example. [ABSTRACT FROM AUTHOR]

• The initial information contribution of nodes is normalized by utilizing their degree and two network properties, and the size of the initial information contribution of nodes is adjusted with the help of a free parameter. • The average degree of the intermediate nodes between the source node and destination node is considered to achieve the global information transmission between them. • The size of the initial information contribution of nodes and three ways of information transmission are applied to construct the algorithm proposed in the paper. • The proposed algorithm has great advantage in the effectiveness, robustness, and practicability of link prediction compared with most benchmark algorithms. Many link prediction algorithms have originated from the process of information transmission between nodes in recent years. Despite these algorithms can obtain great prediction results, there may be also some limitations. For instance, the size of the initial information amount of nodes is ignored when these kinds of algorithms are constructed. Aiming at this issue, a link prediction algorithm based on the initial information contribution of nodes is proposed in this paper. First of all, the initial information contribution of nodes is quantified by utilizing some topological information around them and an adjustable parameter. In the next, three ways of bidirectional information transmission between nodes are analyzed. After that, the total information amount that received by two nodes through three ways of information transmission is applied to measure the structural similarity between them, to design the link prediction algorithm. At last, the experimental results on sixteen real-world networks demonstrate that the proposed algorithm has great advantages in effectiveness and robustness, compared with ten mainstream benchmark indices. More than that, in order to verify the application performance of the proposed algorithm in the practical scenario, our algorithm is also employed in some social domains, such as the Facebook and crime networks. [ABSTRACT FROM AUTHOR]

Film evaluation is of considerable significance to the development of the film and TV industry. A film evaluation is usually a qualitative evaluation. Existing research focuses on transforming qualitative evaluation into numerical values and analyzing numerical values. However, existing methods have a semantic loss in the quantization process, and performance degradation occurs in the mass data. In this paper, a graph convolutional network based on object relationships (OR-GCN) is proposed under linguistic environment and applied to film classification and ranking. First, the dominant matrix is obtained according to the evaluation between objects, and the object relationship is constructed by using the dominant matrix. Second, the graph convolutional network is used to extract the object relationships, deeply learned the relationship between objects, and classified and sorted the objects. Finally, on film review data of Douban (douban.com), the films are classified and sorted by the OR-GCN model, and the effectiveness and the non-randomness of this method are verified by the accurate analysis and ROC. At the same time, our method is applied to the public dataset to illustrate the performance and universality. In this paper, the proposed OR-GCN model can avoid linguistic quantization and only consider the relationship between objects, and provide a new perspective for solving language term set problems. [ABSTRACT FROM AUTHOR]

The security of cyber-physical systems (CPSs) against cyberattacks is essential in critical applications. Resilient control is an effective CPS security method that aims to mitigate cyberattacks in the physical domain of the CPSs. While resilient control has been investigated for different types of attacks, actuator saturation caused by cyberattacks has not been mentioned and addressed. To tackle this issue, a resilient control strategy is presented in this paper for CPSs under actuator saturation resulting from cyberattacks. It consists of an extended state observer and an anti-saturation resilient controller. The state observer estimates unknown system states and attacks, while the controller aims to resist the actuator saturation. The controller is designed by adopting Barrier Lyapunov function, Hyperbolic tangent sigmoid function, and the Nussbaum function. The CPSs with the resilient control strategy presented in this paper not only maintain their stability but also behave with enhanced resilience against cyberattacks, Case studies on a cyber-physical robotic arm system are conducted to demonstrate the effectiveness of the designed resilient control strategy. [ABSTRACT FROM AUTHOR]

This paper proposes an adaptive dynamic multiobjective optimization algorithm for handling dynamic multiobjective optimization problems with variable environmental change types. Most of the existing dynamic multiobjective optimization problems (DMOPs) only deal with a single change type in the environment. Therefore, we design a set of DMOPs that has variable and mixed change types. Next, this paper proposes an adaptive dynamic multiobjective optimization algorithm (DMOA) focusing on the change types, to solve DMOPs with variable change types. It can detect the different types of environmental changes. The main purpose of a DMOA is to find the Pareto-optimal set (PS) of each environment. Therefore, the change types of DMOPs mainly contain two categories: PS changes over time and PS remains constant. After detecting the change type, an adaptive response strategy is activated to react to environmental changes. If PS changes over time, a classification prediction (CP) strategy is active to respond to environmental changes. If PS remains constant, a dynamic mutation (DM) strategy works to react to environmental changes. The proposed algorithm is extensively studied through comparison with several advanced DMOAs, thereby demonstrating its effectiveness in working out complex DMOPs with variable change types and on the parameter-tuning problem of PID controllers for dynamic systems. [ABSTRACT FROM AUTHOR]

• Jointly consider the task dependency and edge cloud environment. • Combine deep reinforcement learning and genetic algorithm. • Generate the initial population of genetic algorithm by DQN. Edge computing can greatly decrease the delay between users and cloud servers, which can significantly improve system service performance. However, it remains challenging for more efficient scheduling and allocation of users' application demands with dependence constraints to edge cloud servers. Due to the randomness of the initial population, traditional intelligent optimization algorithms have poor convergence speed in addressing resource scheduling. Therefore, to minimize the execution time of the application, this paper proposes a hybrid algorithm to solve the resource scheduling problem with parallelism and subtask dependency. To improve the convergence speed of the algorithm, this paper makes full use of the features of deep Q networks (DQN) and genetic algorithms (GA). The initial population of GA is generated using DQN. Finally, to evaluate the effectiveness of our proposed algorithm, this paper selects three real scientific workflows for experiments. The experimental results show that the hybrid algorithm can converge quickly and improve the optimization effect in a short time. [ABSTRACT FROM AUTHOR]

• Local and global self-attention mechanisms are used for character embedding. • CNN with multi-size filters are used to extract character information for NER. • A cross-attention method that fuses character and word embedding for NER is proposed • A modified Mogrifier LSTM is presented to improve the performance of NER. • Proposed methods integrated with a transformer-based model achieve good performance. Clinical and biomedical concept extraction is critical in medical analysis using clinical and biomedical documents from professional literature, EHRs and PHRs. Named entity recognition (NER) accurately marks essential information in the literature based on the characteristics of the target entity, providing a method for extracting clinical and biomedical concepts. The performance of NER is heavily embedding-dependent, so recent studies have proposed the method of generating word embedding from character-level information, which can strengthen the representation ability for word embedding. In this paper, we present a novel neural network model including an attention mechanism network and a convolutional neural network (CNN) to further improve character-level embedding. First, an attention mechanism is applied simultaneously to the local and global character embedding. Then, a CNN with multi-size filters is used to extract more information from the character level, which can capture more meaningful features from words with various lengths. In addition, a cross-attention method is used to leverage the interaction between word embedding and character embedding to generate the final word representation. Finally, we modified Mogrifier LSTM to make it suitable for NER tasks and integrated it into our model. Experimental results show that our method is effective and that the model performs better than the baseline models. We also apply our methods proposed in this paper to the transformer-based model and obtain a 90.36 F1-score on NCBI-Disease. [ABSTRACT FROM AUTHOR]

According to the basic principles and methods of information theory, the operation way of neural coding is studied and analyzed by using the minimum mutual information and the maximum entropy principle. This paper describes how the principles of minimum mutual information and maximum entropy are used to evaluate the amount of information in neural responses. Its main contribution is as follows: (1) that the expression of neural information is closely related to the utilization of neural energy, and it is found that the highly evolved nervous system strictly follows the two basic principles of economy and efficiency in energy consumption and utilization; (2) In order to verify the relationship between neural information processing and energy utilization, this paper uses the concept of energy-efficiency ratio to measure the economy and high efficiency of the nervous system in term of energy utilization by using the maximum entropy principle; (3) The numerical results show that the energy consumed by the nervous system reflects not only the internal law of neural information conduction and processing, but also the self-organization structure of neural information coding. The results suggest that energy neural coding, a novel neural information processing method, can be used to understand how brain activity works. Such a coding pattern can not only be extended to research the large-scale neuroscience field, but also unify brain models at all levels by use of the energy theory. This will provide a scientific theoretical basis for the exploration of how the brain works and the computational principles of brain-like artificial intelligence. [ABSTRACT FROM AUTHOR]

• The paper proposes the TCP-BAST approach for traffic congestion prediction with bilateral alternation. • Spatial-temporal alternation (STA) module and temporal-spatial module (TSA) are proposed to capture both the correlation and the heterogeneity between the spatiality and temporality simultaneously. • A spatial-temporal fusion module is proposed to fuse the multi-grained spatial-temporal features derived from the STA module and the TSA module. Accurate traffic congestion prediction is crucial for efficient urban intelligent transportation systems (ITS). Though most existing methods attempt to characterize spatial correlation and temporal correlation in traffic congestion, few of them consider spatial heterogeneity and temporal heterogeneity: spatial correlation depends on temporality, and temporal correlation depends on spatiality in traffic congestion. To address this problem, this paper proposes a novel approach called TCP-BAST with bilateral alternation to simultaneously capture both the correlation and the heterogeneity between spatiality and temporality to improve traffic congestion prediction. First, to capture spatial correlation and spatial heterogeneity, we propose a spatial–temporal alternation (STA) module with multi-head graph attention networks and temporal embedding. Second, to capture temporal correlation and temporal heterogeneity, we propose a temporal-spatial alternation (TSA) module with multi-head masked attention networks and spatial embedding. Third, to predict the traffic congestion of multiple road sections in a traffic network, we propose a spatial–temporal fusion (STF) module to fuse the multi-grained spatial-temporal features derived from the STA and TSA modules. The experimental results on a real-world traffic dataset demonstrate that the proposed TCP-BAST approach outperforms the baseline methods in terms of both the mean absolute error (MAE) and the root mean squared error (RMSE). Both spatial-temporal alternation and temporal-spatial alternation are important for improving traffic congestion prediction, with the former being more critical than the latter. [ABSTRACT FROM AUTHOR]

Dempster-Shafer evidence theory is widely used in the field of information fusion since it satisfies weaker conditions than probability theory. Nevertheless, the description space of the current evidence theory is only real space, and it cannot effectively describe and process the uncertain information in the face of multidimensional characteristic data and periodic data with phase angle changes. Thus, in this paper, evidence theory is extended to the complex Dempster-Shafer evidence theory. The mass function that is used to describe the uncertain information extends from the real space to the complex space, named as complex mass function. The modulus of the complex mass function indicates the degree of support for the proposition. Moreover, other basic concepts that are used to describe uncertainty information are also defined and discussed. To perfect the complex evidence theory, the complex Dempster rule of combination is supplemented. The complex Dempster rule of combination is an extension of Dempster rule of combination, which satisfies the commutative and associative laws just as Dempster rule of combination does, and it can degenerate into Dempster rule of combination. This paper also proposes a method to generate complex mass function and apply it to target recognition. The recognized results show that compared with the mass function, the target recognition rate is larger by using the complex mass function. [ABSTRACT FROM AUTHOR]

Due to the simplicity of the learning strategy, the original particle swarm optimization (PSO) has various deficiencies, such as entrapment in local optima, rapid loss of diversity and a poor balance between exploration and exploitation, especially for many complex optimization problems. To overcome these shortcomings, this paper proposes a hybrid particle swarm optimizer with fitness-distance balance and individual self-exploitation strategies, namely, HPSO-FDB-ISE. First, to reduce the probability of becoming trapped in a local optimum for the population, fitness-distance balance is employed to construct an alternative learning exemplar to the global best position. Second, individual self-exploitation is introduced to achieve intelligent exploitation by learning from individual current information for particles. Finally, a nonlinear time-varying inertia weight is used to efficiently balance the exploitation and exploration in the search process. The proposed HPSO-FDB-ISE is evaluated on the CEC 2017 test suite against six state-of-the-art meta -heuristics and seven state-of-the-art PSO variants. Experimental results and statistical analysis reveal that the proposed HPSO-FDB-ISE algorithm yields excellent performances compared to other algorithms that are considered in this paper in the majority of cases. [ABSTRACT FROM AUTHOR]

This paper introduces a novel methodology to perform topological regularization in multivariate probabilistic modeling by using sparse, complex, networks which represent the system's dependency structure and are called information filtering networks (IFN). This methodology can be directly applied to covariance selection problem providing an instrument for sparse probabilistic modeling with both linear and non-linear multivariate probability distributions such as the elliptical and generalized hyperbolic families. It can also be directly implemented for topological regularization of multicollinear regression. In this paper, I describe in detail an application to sparse modeling with multivariate Student-t. A specific expectation–maximization likelihood maximization procedure over a sparse chordal network representation is proposed for this sparse Student-t case. Examples with real data from stock prices log-returns and from artificially generated data demonstrate applicability, performances, robustness and potentials of this methodology. [ABSTRACT FROM AUTHOR]

In this paper, we develop a novel multiattribute decision making (MADM) approach based on Fermatean hesitant fuzzy sets (FHFSs) and the modified VIKOR method. Firstly, we propose the definition of distance measures of FHFSs and present its properties. Further, taking the effectiveness of FHFSs for dealing with ambiguous and imprecise data in MADM problems, this paper proposes the remoteness index-based Fermatean hesitant fuzzy-VIKOR (FHF-VIKOR) MADM method. The generalized distance measure for FHFSs is subsequently employed to establish the notions of remoteness indices with the positive ideal and the negative ideal remoteness indices. The objective weighting procedure is developed using the maximum deviation principle and the generalized distance measure to obtain the attributes' weights. Some examples are discussed to reveal the performance of the proposed MADM method. Finally, the advantages of the proposed MADM method in terms of the robustness and the flexibility are shown by a comparative study. The proposed MADM method based on FHFSs and the modified VIKOR method can overcome the drawbacks of the existing MADM methods. [ABSTRACT FROM AUTHOR]

• A novel random neighbor elite guided mutation strategy named "DE/current-to-rnbest/1", which is a general mutation framework. • Random neighbor region formed by several random individuals in the population. • Two special cases of "DE/current-to-rnbest/1": "DE/current-to-best/1" and "DE/current-to-pbest/1" • Adaptive neighbor size adjustment at the individual level based on the Cauchy distribution. • Exploring and exploiting the solution space appropriately to find global optima. Optimization problems not only become more and more ubiquitous in various fields, but also become more and more difficult to optimize nowadays, which seriously challenge the effectiveness of existing optimizers like different evolution (DE). To effectively solve this kind of problems, this paper proposes a random neighbor elite guided differential evolution (RNEGDE) algorithm. Specifically, to let individuals explore and exploit the solution space properly, a novel random neighbor elite guided mutation strategy named "DE/current-to-rnbest/1" is first proposed to mutate individuals. In this mutation strategy, several individuals randomly selected from the population for each individual to be updated along with the individual itself form a neighbor region, and then the best one in such a region is adopted as the guiding exemplar to mutate the individual. Due to the random selection of neighbors and the directional guidance of elites, this strategy is expected to direct individuals to promising areas fast without serious loss of diversity. Notably, it is found that two popular mutation strategies, namely "DE/current-to-best/1" and "DE/current-to-pbest/1", are two special cases of the proposed "DE/current-to-rnbest/1". Further, to alleviate the sensitivity of the proposed algorithm to the involved parameters, this paper utilizes the Gaussian distribution and the Cauchy distribution to adaptively generate parameter values for each individual with the mean value of the Gaussian distribution and the position value of the Cauchy distribution adaptively adjusted based on the evolutionary information of the population. With the above two techniques, the proposed algorithm is expected to effectively search the solution space. At last, extensive experiments conducted on one widely used benchmark function set with three different dimension sizes demonstrate that the proposed algorithm achieves highly competitive or even much better performance than several compared state-of-the-art peer methods. [ABSTRACT FROM AUTHOR]

This paper develops a practical fixed-time bipartite consensus control framework for the uncertain nonlinear multi-agent systems (MASs) via using a barrier Lyapunov function (BLF)-based approach. Distinguish from the most existing results, the unknown nonlinearities of MASs in this paper are tackled by utilizing the robustness of BLF instead of applying fuzzy logic systems/neural networks approximating. In order to avoid feasibility verification in the traditional BLF method, a piecewise and differentiable function named the shift function is skillfully inserted into the coordination transformation of the controller design process, allowing not only the initial value of MASs states to be chosen arbitrarily, but also the settling time of bipartite consensus errors can be pre-designated. According to the backstepping framework, an approximated-free control algorithm is developed by combining the shift function with BLF, which guarantees that for any initial state of MASs, the outputs of all the agents can achieve the practical fixed-time bipartite consensus tracking, and all the signals in closed-loop systems are bounded. Especially, the settling time and the tracking error accuracy can be appointed by the designer. Finally, simulation results are given to show the effectiveness of the proposed control method. [ABSTRACT FROM AUTHOR]

• An DBSCAN extension for online structural clustering is proposed. • Information granules are constructed to describe structures of shaped clusters. • Granular computing and rule-based modeling are applied for online clustering. • Good performances are achieve on accuracy and time in online structural clustering. In online structural clustering, general density-based clustering algorithms have problems of low scalability and high computation cost, especially in big data analysis, this paper proposed a DBSCAN extension algorithm with consideration of granule computing to handle these problems. This algorithm mainly makes use of advantages of DBSCAN and granular descriptors to realize effective and efficient structural online clustering. Frist, to extract structural clusters effectively, DBSCAN is considered as the basic clustering algorithm in this research. Second, since DBSCAN's results are not numerical for online testing, this paper proposes to apply granule computing (GrC) to construct information granules describing arbitrarily-shaped clusters from DBSCAN. Third, to realize an efficient online structural clustering, especially in big data analysis, a series of granular fuzzy models are built with consideration of structural information, then a rule-based model is formed for guiding online clustering of new testing data. Through the proposed method, the online clustering ability of DBSCAN is developed with reduced computation cost, meanwhile the structural clustering ability is also retained in online testing. Experiments on synthetic data, publicly available data and real-world data are discussed, online testing accuracy and computation time are evaluated to validate the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

• The paper proposes two weighted c-medoid batch SOM for dissimilarity data. • The paper extends the batch SOM with C-medoids and multi-medoids algorithms. • The training of the new batch SOM algorithms are based on suitable cost functions. • The paper gives the cluster representatives and relevance weights of the c-medoids. • The paper provides the optimal assignment of the objects to the clusters. • The paper gives a meaningful evaluation of the proposed methods. This paper proposes two new batch SOM algorithms for dissimilarity data, namely RBSOM-CWMdd and RBSOM-ACWMdd, both designed to give a crisp partition aiming to preserve the topological properties of the data on the map. RBSOM-CWMdd is a batch SOM algorithm for dissimilarity data where each cluster representative is a set of weighted objects whose cardinality is fixed, being the same for all clusters. These weights are computed according to each object relevance to the referred cluster. Likewise, RBSOM-ACWMdd is a batch SOM algorithm for dissimilarity data where each cluster representative is a vector of weighted objects selected according to its relevance to the referred cluster. Therefore, the dimensionality of the cluster representatives self adapt to the particular dataset analysed, change at each algorithm iteration and can differ from one cluster to another. Experiments with 12 datasets from the UCI machine learning repository regarding the metrics of Normalized Mutual Information, Topological error, and Silhouette Coefficient showed that the proposed methods improved, respectively, the traditional set-medoids and multi-medoids SOM methods with a competitive temporal complexity. In addition, it was performed an application study on Ecoli dataset where the proposed RBSOM-ACWMdd algorithms produced a better mapping from a clustering point of view. [ABSTRACT FROM AUTHOR]

Given a finite set of alternatives, the ranking problem statement builds a preference pre-order (partial or complete) on this set. In this paper, we are interested in multiple criteria ranking problems with a hierarchical structure of criteria; more precisely, we are interested in the existing hierarchical E lectre III method. This method requires eliciting several preference parameters (namely, the weights and the veto thresholds). A direct elicitation of such parameters can be cognitively very demanding; thus, it is adequate to define the parameters in a way that requires much less cognitive effort from the decision-maker. The model parameters can be indirectly elicited by using holistic information provided by the decision-maker; this information can be given in the form of a ranking on a set of reference alternatives and some additional preference information. This paper proposes an aggregation-disaggregation approach for inferring the model parameters of the hierarchical E lectre III based on an evolutionary algorithm. To verify the applicability and validity of the proposed preference disaggregation methodology, an illustrative example is addressed regarding the ranking of a set of universities. [ABSTRACT FROM AUTHOR]

This paper proposes a gradient neural network (GNN) to solve the repetitive motion generation scheme of the omnidirectional four-wheel mobile manipulator. The overall kinematics model of the omnidirectional mobile platform and the manipulator fixed on omnidirectional platform are established. First, the analysis of the current repetitive movement generation (RMG) scheme for the kinematic control of the manipulator can find that the position error does not theoretically converge to zero and fluctuates. This paper analyzes the phenomenon from a theoretical viewpoint and reveals that the current RMG scheme has position errors associated with joint errors. Then, to solve the shortcomings of the current solution, an orthogonal projection repetitive motion generation (OPRMG) method is proposed, which theoretically eliminates position errors and decouples joint space and Cartesian space. Using the gradient descent method to establish the corresponding GNN aided with the speed compensation, and provide theoretical analysis to reflect the stability. Moreover, the joint speed limit in the RMG scheme is extended to nonconvex constraints. The advantages of the OPRMG scheme are demonstrated by the simulation results of the omnidirectional mobile manipulator (OMM) synthesized by the current GNNRMG and the proposed GNNOPRMG. In addition, by adjusting the feedback coefficient, the high performance of the OPRMG scheme can be verified by simulation and comparison of the position error (PE) and joint error (JE) of the OMM. [ABSTRACT FROM AUTHOR]