Search

Automatic fault diagnosis in many systems is performed via the analysis of vibration data in the time or frequency domain. In the literature, many approaches for extracting featured from signals for fault diagnosis have been proposed. In this paper, we apply a variety of transform functions including Fourier, Wavelet, etc. to extract features from the vibration data, which includes the statistical features and some features automatically extracted via Convolutional Neural Networks (CNNs). For each of these feature extraction approaches, a learning algorithm is trained to diagnose the faults and their results are aggregated in an ensemble machine learning algorithm. The weights of the base learner algorithms are optimized via an evolutionary algorithm to achieve the best-weighted voting scheme. The architecture of CNNs has a significant effect on the performance of the algorithm, thus, in this paper, an evolutionary algorithm is proposed to find the best architecture for CNNs in fault diagnosis. The CNNs are trained via gradient descent algorithms which suffer from getting stuck in local optima. To manage this, we propose an evolutionary algorithm that benefits from the speed of gradient descent and the global search of evolutionary algorithms. The proposed algorithm is tested on a number of benchmark problems and the experimental results are presented. • An ensemble algorithm is proposed for fault diagnosis. • Different feature extractors are exploited. • An evolutionary training algorithm is proposed. [ABSTRACT FROM AUTHOR]

The increasing computational power of machines and more affordable robotic hardware and software offer great opportunities for developing more advanced intelligent robotic systems to perform numerous tasks in the civil infrastructure sector (CIS). More specifically, unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) are the most commonly used robots for civil infrastructure-related applications. Existing synthesized information on the applications of UAVs and UGVs mainly focused on either a specifically narrow domain or broadly summarized the current practices of robots in the CIS without providing sufficient information about the relevant sensing devices and/or data processing techniques. Therefore, there is a need to widely review, synthesize, and analyze the applications of UAVs and UGVs as well as the associated methods (e.g., data sensing techniques and data analytic methods) in the broad CIS field. To this end, this paper provides a systematic review of UAVs- and UGVs-related studies conducted in the CIS in relation to their applications, the used robotic platforms, the employed sensors, and the implemented algorithms. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology (which is a commonly used framework to objectively perform systematic literature review) and a total of 95 articles identified from 15 purposively selected journals, this paper conducted a comprehensive systematic review of the uses of UAVs and UGVs in the CIS. Analysis was performed on the information extracted from these articles to (1) collect relevant, timely information and synthesize it into a cohesive summary of existing knowledge about the applications of UAVs and UGVs, (2) synthesize the current robotic platforms, performed tasks, major robotic accessories, and onboard sensing devices of UAVs and UGVs, (3) investigate existing techniques for sensing data analytics, and (4) outline the main challenges and potential opportunities for directing future studies and engineering practices in the CIS. While this paper serves as an expert reference and guide for both researchers and practitioners working in the smart, intelligent, and automated civil infrastructure domain, it also identifies the need for additional research and efforts to improve the uses of UAVs and UGVs and facilitating their developments in the CIS to improve and digitalize the built environment. [ABSTRACT FROM AUTHOR]

Emotion assessment is a challenging task in the human–computer interaction interface. Previous studies have examined the relationship between emotion and color, but they fail to accurately analyze emotional semantics due to the numerous elements in human–computer interaction interfaces. As a result, a combination model of a backpropagation neural network (BPNN) and an artificial bee colony algorithm (ABC) was presented in this paper to predict the emotion semantics of the human–computer interaction interface. The mechanism of generating the weights and thresholds for each layer of BPNN was converted to the search for an optimal honey source. Meanwhile, according to experiment results and evaluation of elements in human–computer interaction interfaces, this paper has assessed the relationships amongst the eight key elements (ratio of graphics to text, color difference, color distribution, color harmony, theme style, white space ratio, frame style, number of colors) and emotion word pairs (moderation-fancy, calm-pleasure, confusing-clear, cold-kind, coarse-elegant). Furthermore, an emotion application database was established to determine how the amalgamation of critical elements affects the users' feelings about the human–computer interaction interface to help designers build a user-centric interface. Finally, the database can be applied to relieve mental health problems by meeting the psychological expectations of users as mental healthcare intervention during the COVID-19 pandemic. Also, it can help designers to design a pleasurable visual interaction interface for a particular element to convey health-related information and protective measures. [ABSTRACT FROM AUTHOR]

In this paper we investigate the role of self-learning agents in multi-agent models of financial markets. We develop an agent-based simulation model of a financial market and, in addition to the agents with fixed strategies used in previous research, we introduce an agent with a self-learning strategy. To model the behavior of such an agent, we use deep reinforcement learning algorithms, namely deep deterministic policy gradient (DDPG). Next, we conduct a comparative analysis of the results of the constructed model with outcomes of previously proposed models, as well as with the characteristics of real market. To conduct comparative analysis, we use stylized facts of asset returns that allow us to evaluate and compare the characteristics of the markets. Our results show that a model with a self-learning agent gives a better approximation of the real market than a model with classic agents. In particular, unlike the model with classical agents, the model with a self-learning agent turns out to be not so heavy-tailed. Thus, we demonstrate that for a complete understanding of market processes simulation models should take into account self-learning agents that have a significant presence at modern financial markets. Finally, we present the python package 1 1 https://github.com/Kiri28/Agent-Based%5fMarket%5fsimulator. , which was developed by us as part of the research implementation. This package allows to simulate the financial market, as well as create your own agents and evaluate their impact on the market. • The paper explores the role of self-learning agents in modern financial market models. • We use stylized facts based analysis to compare simulated markets with each other. • Using a comparative analysis, we show that our model better describes real markets. • The paper provides our Python package for simulating financial markets. [ABSTRACT FROM AUTHOR]

This paper provides the first review to date which gathers, describes, and assesses, to the best of our knowledge, all available publications on automating cerebral microbleed (CMB) detection. It provides insights into the current state of the art and highlights the challenges and opportunities in this topic. By incorporating the best practices identified in this review, we established guidelines for the development of CMB detection systems. We are confident that these guidelines can serve as a foundation for further research. CMB detection is a crucial but challenging task that can be laborious for radiologists. With the increasing popularity of magnetic resonance imaging (MRI), the ability to detect CMBs has improved, but there is still a need to automate this process to enhance its efficiency and accuracy. A high prevalence of CMBs is closely associated with cognitive dysfunction, diabetes, hypertension, an increased risk of stroke, and intracerebral hemorrhage. It is alarming to note that strokes, Alzheimer's disease, and Diabetes mellitus have secured their position as the second, seventh, and ninth most common causes of death worldwide, respectively. Moreover, CMBs are sometimes found in association with other pathologies and indicate a range of pathological processes in the cerebral vessels. Thus, it is essential to enhance the quality of diagnostics to facilitate prompt identification and treatment of these potentially life-threatening conditions. In this paper, we aimed to systematize the existing knowledge and best practices in automatic CMB detection, from fundamental information about CMBs and MRI image data, through employed datasets and CMB detection and verification algorithms, to methods of result evaluation. This can serve as a starting point for future research and the development of a CMB detection system that is practically applicable in medicine, leading to enhanced patient treatment outcomes. • There is a need for automatization of laborious CMB detection process. • Automatic CMB detection suffers from high production of false-positive predictions. • The scarcity of publicly available CMB datasets hinders research comparison. [ABSTRACT FROM AUTHOR]

In pharmaceutical warehousing operations, a scientific and reasonable medicine and shelf matching strategy can improve medicine shelving efficiency and manual work efficiency. However, the traditional matching strategy has the problems of static matching and low matching efficiency, so this paper proposes the matching algorithm for drugs and shelves based on the fuzzy analytic hierarchy process and Bayesian convolutional neural network (FAHP-BCNN). First, we propose a drug-shelf matching degree model and discuss the influence of the dynamic matching process on the matching results by studying two parts: the attribute matching degree and the dynamic matching influence degree. Secondly, this paper quantitatively assessed the importance of the two matches by means of the fuzzy analytic hierarchy process. Finally, we mapped the massive matching information onto Bayesian convolutional neural network nodes, constructed a dynamic matching network model, and obtained competitive matching strategies and results. The experimental results show that the FAHP-BCNN algorithm exhibits better matching results in all three scenarios with different quantity ratios of drugs and shelf matching. Compared with the fixed cargo matching strategy of the ABC classification method, the FAHP-BCNN algorithm shows excellent performance in both the manual walking distance index and fatigue index. In summary, the drug-shelf matching algorithm based on FAHP-BCNN is effective and can provide theoretical support for pharmaceutical warehousing enterprises to perform drug-shelf matching. [ABSTRACT FROM AUTHOR]

Applying machine learning (ML) methods to multi-factor authentication is becoming increasingly popular. However, there is no comprehensive methodology to evaluate biometric systems based on machine learning in the literature. This paper proposes a general methodology for evaluation the ML-based systems for impostor recognition/detection using biometric traits. This includes creation of learning and testing sets with appropriate size balance (proportion) between these sets, selecting the number of instances coming from different users, evaluation of the influence of the impostors number on their detection rate, and the impact of the number of records representing user's behavior. In addition, we propose how the real data (possibly affected by account takeover attempts) could be used to extend the enrollment data to support the impostor detection. The proposed approach was used for a systematic comparison of an extensive set of ML and statistical methods. For some of them, the false acceptance rate (FAR) close to zero and false rejection rate (FRR) smaller than 0.05 in a supervised experiment were accomplished, proving the merit of certain ML-based approaches. Moreover, using the method proposed in the paper, a classifier trained on experimental data achieved FAR below 0.05 on the real-world data collected at an actual financial web page. • General methodology for evaluating ML impostor recognition using biometric traits. • Evaluation of the influence of the impostors number on their detection rate. • Evaluation of the impact of the number of records representing user's behavior. • The proposed approach tested on ML methods reaching FAR and FRR smaller than 0.05. • Test-bed trained classifier achieved FAR < 0.05 on data from financial service. [ABSTRACT FROM AUTHOR]

Fake news refuting is an essential part of online social networks (OSNs) management. Identifying the potential voluntary fake news refuters who can spontaneously repost the fake news refutation messages on the OSNs, and intentionally exposing such messages to them can contribute a lot to fake news regulation. Therefore, to fully utilize available user features and enhance fake news refuter identification, the paper proposes a novel paradigm for refuter classification problem, which leverages the pre-trained techniques and mixture of expert system to unify the structured and unstructured data. Specifically, the unstructured text records are first understood by the pre-trained ERNIE2 model, and then feed into Chi-Merge grounded Convolutional Neural Networks, which are expert classifiers in our framework, along with the structured profile data for further transformation. Besides, features extracted from text data are used for determining weights for multiple expert classifiers. Experiments on near 60 k real-world Weibo user data prove that our framework outperforms the large-scale pre-trained deep learning methods and traditional machine learning classification models. This paper provides a novel perspective of fake news refutation from the refuter's side and sheds light on artificial intelligence-driven OSNs management. [ABSTRACT FROM AUTHOR]

Type 2 diabetic patients benefit significantly if the disease is well controlled through behavioral changes, namely adopting a healthy lifestyle. Currently, there is some evidence that technological strategies can help patient self-management. However, few studies have specifically targeted individuals who solely engage in automatic and personalized self-management practices. This study aims to synthesize the literature regarding personalized feedback recommendation systems to promote behavior change without health professionals' direct intervention for the management of type 2 diabetes and to verify if the use of these systems improves health-related outcomes. A systematic review was performed from inception to April 13, 2021, based on a search conducted in six databases. According to the defined search expression, studies addressing type 2 diabetic patients and recommendation systems were included. In total, 2186 papers were initially identified, but only 22 met the specific inclusion criteria after screening. Discrepancies in the selection of studies were discussed in consensus meetings. To assess the quality of the articles, two tools were employed according to the types of articles retrieved. Selected papers were summarized regarding specific characteristics such as clinical and technological outcomes. Studies incorporating a recommendation system into their technological solution showed a positive effect on the evaluated outcomes, except for those with longer duration, where the effect was not statistically significant. Although most studies did not report the type of system used, expert systems (rule-based) were found to be the most prevalent among those that did. As behaviors are often difficult to change quickly, it is recommended that future studies extend their follow-up timeframe. Nevertheless, the data obtained suggest that technological solutions incorporating a recommendation system show potential to improve health-related outcomes and demonstrated good usability. [ABSTRACT FROM AUTHOR]

This paper develops an efficiency-based interactive dynamic technique to design the post-disaster rescue route by combining the data envelopment analysis (DEA), traveling salesman problem (TSP) and interval-valued hesitant fuzzy constraint cone (IVHFCC). The traditional DEA potentially presumes that the weights of the input (output) criteria are unrestricted, resulting in its inapplicability to some complex decision problems. To restrict the weights of input (output) criteria legitimately, this paper constructs an IVHFCC based on expert's subjective preferences in the form of interval-valued hesitant fuzzy sets. This paper defines the additive consistent normal interval-valued hesitant fuzzy preference relation (NIVHFPR) and analyses its desirable properties. Based on these properties, three linear programming models are proposed to repair the incomplete NIVHFPR, judge the additive consistency of the repaired NIVHFPR and generate the additive consistent NIVHFPR. By incorporating the TSP, DEA and the constructed IVHFCC, an efficiency-based interactive dynamic model is originally proposed to generate the optimal rescue route for the rescue team. Some desirable properties of this efficiency-based interactive dynamic model are analyzed. The validity of this model is demonstrated with a real post-disaster rescue route planning problem of Wenchuan earthquake. Some comparative analyses are provided to show the superiorities of the proposed technique. [ABSTRACT FROM AUTHOR]

Applying artificial intelligence in education is relevant to addressing the current educational crises. Many available solutions apply Convolutional Neural Networks (CNNs) to help improve educational outcomes. Therefore, a series of works have been developed integrating techniques in different educational contexts, for instance, in online teaching practices. Given the various studies and the relevance of CNNs for educational applications, this paper presents a systematic literature review to discuss the state-of-the-art. We reviewed 133 papers from the IEEE Xplore, ACM Digital Library, and Scopus databases. Based on our revision, we discuss characteristics of studies such as publication venues, educational context, datasets, types of CNNs models, and performance of models. We evidence that the literature regarding CNNs still misses more studies discussing educational problems faced by Global South students, considering both teaching and learning perspectives. Such a population cannot be neglected during experiments due to specific educational weaknesses (for example, basic skills) demanding personalized solutions. • A systematic literature review of 133 published papers. • China covered most publications, followed by India. • There is a research gap regarding using CNNs in some regions of the Global South. • The main educational context with CNN applications is students' performance. [ABSTRACT FROM AUTHOR]

The increasing abuse of facial manipulation methods, such as FaceSwap, Deepfakes etc., seriously threatens the authenticity of digital images/videos on the Internet. Therefore, it is of great importance to identify the facial videos to confirm the contents and avoid fake news or rumors. Many researchers have paid great attention to the detection of deepfakes and put forward a number of deep-learning-based detection models. The existing approaches mostly face the performance degradation in detecting low-quality(LQ) videos, i.e. heavily compressed or low-resolution videos through some SNS (Social Network Service), resulting in the limitation in real applications. To address this issue, in this paper, a novel Spatial Restore Detection Framework(SRDF) is proposed for improving the detection performance for LQ videos by restoring spatial features. We designed a feature extraction-enhancement block and a mapping block inspired by super-resolution methods, to restore and enhance texture features. An attention module was introduced to guide the texture features restoration and enhancement stage attending to different local areas and restoring the texture features. Besides, an improved isolated loss was put forward to prevent the expansion of a single area concerned. Moreover, we adopted a regional data augmentation strategy to prompt feature restore and enhancement in the region attended. Extensive experiments conducted on two deepfake datasets have validated the superiority of the proposed method compared to the state-of-the-art, especially in the scenarios of detecting low-quality deepfake videos. • Low-quality deepfake videos lost clues due to heavy compression or low resolution. • This paper put forward a novel Spatial Restore Detection Framework for LQ videos. • A feature extraction-enhancement block was designed to restore and enhance features. • An attention module was introduced to guide the texture features restoration. • The experiments conducted on two deepfake datasets have validated the superiority. [ABSTRACT FROM AUTHOR]

In the oil and gas industry, there is a need for constructing auxiliary maintenance and storage buildings nearby exploration sites. As the initial stage for such constructing purposes, it is required to drill wells for construction piles. To this end, there is a fleet of mobile drilling rigs traveling from one exploration site to another, performing the work on drilling wells. For each site, we have a time window for completing all the work on drilling. To complete all the work among all the exploration sites in time, it may be necessary to allow several drilling rigs to perform work at the same site. Yet, in the real world, unforeseen circumstances can affect drilling time, and that, if disregarded, can lead to a disruption of the work plan. Thus, in this problem, we maximize possible deviations of drilling times from expected values when there is still a feasible solution to perform all well-drilling requests in time. At the same time, total traveling costs must be no more than a given threshold. It is a so-called threshold robustness approach. The described Drilling Rig Routing Problem (DRRP) differs from other well-studied variants of Vehicle Routing Problem (VRP) in that the work splitting affects the service time. There is a limited number of papers dealing with such problems and no papers about the robust formulation for them. This research proposes a mathematical model for the novel formulation of the DRRP with uncertainties and an Adaptive Large Neighborhood Search (ALNS) algorithm to solve it. The destruction operators work either at the route, customer, or visit level. The reconstruction operators take into account a possibility to change the work partition. Computational results for the algorithm and Gurobi solver show the dominance of the ALNS scheme for medium- and large-sized instances. • Mixed-integer linear programming model is proposed for the robust optimization. • Adaptive large neighborhood search is adapted considering split service aspect. • The number of destruct and repair operators to use is optimized. • Comprehensive computational experiments are provided. [ABSTRACT FROM AUTHOR]

In recent years, the problem of visual occlusion in optical surgical tracking system has attracted widespread attention. To solve this problem, this paper proposes a tracking system for surgical instruments based on data fusion of multicamera modules. Multicamera modules are used to track surgical instruments from different angles to solve the problem of tracking occlusion in monocular tracking. Firstly, occlusion of monocular tracking based on different fiducial marker is analyzed, and a fast calibration method of tracking system for surgical instrument based on multicamera module is proposed. The calibration of the tracking system is mainly divided into the calibration of surgical instruments and the fast calibration between multicamera modules. On this basis, the occlusion detection mechanism is proposed to screen out the data with large errors, and the fuzzy control theory is used to calculate the support degree between different modules. Finally, the serviceable data is fused based on the least square method and the position of surgical instruments is estimated. The average accuracy of static positioning and dynamic trajectory tracking is mm and mm respectively. The real-time performance of the proposed system is 35 frames per second (fps). Compared with the existing optical tracking system, the method proposed in this paper has stronger anti-occlusion and simpler operation. [ABSTRACT FROM AUTHOR]

Water as the core of Sustainable Development (SD) alongside a significant increase in the global demand for water causes the subject of Urban Water and Wastewater (U2W) management to be essential in exploring the future. As a means of future studies, MICMAC reveals the influence and dependence of a variable concerning all others by examining all interactions in the system. These interactions should be analyzed in two dimensions: "Impact" and "Time". Usually, two types of impacts are used, including direct and indirect. Also, most methods have a critical weakness in that it does not include the impact of "time" in the analysis. This paper suggests a novel approach to MICMAC (named MICMAC-T), which promotes understanding indirect cross impacts by considering the influence of "time" in analysis. This helps in particular with U2W, which faces major future challenges toward SD. The practical approach developed in this paper can be quickly and flexibly initiated because of its toolbox-based design, integrating text mining, PESTEL, MICMAC, Floyd-Warshall, and interviews in a single model. Therefore, the proposed method could also be considered a new contribution to the CIA. To demonstrate the contribution of MICMAC-T, the case of the Iranian U2W pathway toward SD is investigated to find the driving forces. The results of applying this approach in finding the driving forces for Iranian U2W include new interesting findings. The results of MICMAC-T suggest that "Legal comprehensiveness," "Urban economic development policies," "High-level policy documents," "Public social awareness in society," "Geographical location (climate)," "Law enforcement guarantee," "U2W governance", and "Urban water resources scarcity" are driving forces for the Iranian U2W. Among these variables, "Urban economic development policies" and "Public social awareness in society" were neglected in traditional MICMAC and categorized as driving forces only using MICMAC-T, which indicates the crucial influence of time on Iranian U2W. [ABSTRACT FROM AUTHOR]

Forest carbon sink project (FCSP) has received growing attention for its outstanding advantages in carbon emission reduction, environment protection, and achieving the carbon neutrality objective. Using a government-social capital cooperation model, FCSP helps to revitalize the ecological and economic benefits of the forest with standard and efficient management. However, the management and operation barriers of FCSP implementation are complex, multiple and indefinite in the long run, which requires a comprehensive barrier evaluation framework. Hence, this paper is devoted to constructing a barrier evaluation framework for FCSP implementation in China with an integrated multi-criteria decision-making (MCDM) method. To this end, critical barriers are identified and the criteria system is constructed with a two-stage systematic literature review and interaction with the experts. Later, an applicable and comprehensive barrier evaluation framework is built, wherein the interval type-2 fuzzy set (IT2FS) is used to process fuzziness and uncertain information, the best-worst method (BWM) is adopted to determine the criteria weight, and the Preference Ranking Organization Method for Enrichment Evaluations II (PROMETHEE II) is introduced for comprehensive barrier evaluation. The criteria weighting results indicate that FCSP implementation encounters challenges taking into account institutional and governance barriers (criteria weight: 0.3592), management barriers (0.2384), economic and market barriers (0.1637), knowledge barriers (0.0747), technical and infrastructure barriers (0.1639), C1 "Lack of clear leadership and policies" and C5 "Forest management performance" were determined the most significant criteria, A5 and A4 respectively performed the lowest and the highest barrier level. In sensitivity analysis, the ranking results were stable when the criteria changed, and Spearman's rank correlations of B2, B4, and B5 are significant. The results were validated by a comparative analysis with other methods with the help of Spearman's rank correlation coefficient, which reflects accepted high correlations (Spearman's pro values of BWM-IT2F-PROMETHEE II (Gaussian rule), BWM-IT2F-TOPSIS, and BWM-TFN-VIKOR are 1.00, 1.00, 1.00). The findings of the paper help the decision makers to develop more rational strategies and successfully implement the FCSP. [ABSTRACT FROM AUTHOR]

• A DRL based hyper-heuristic is proposed to solve online packing problems. • Feature fusion is employed to better characterize uncertain environments. • Results show advantages in average-case performance for two packing problems. • Visual analysis reveals that the learned strategy is stage-dependent. In recent years, deep reinforcement learning has shown great potential in solving computer games with sequential decision-making scenarios. Hyper-heuristic is a generic search framework, capable of intelligently selecting or generating algorithms to solve a class of optimisation problems with stochastic or dynamic settings. This paper proposes a new general framework for solving online packing problems using deep reinforcement learning hyper-heuristics. Although analytical approaches can address most offline packing problems successfully, their online versions have proved much more challenging and the performance of the existing methods is often not satisfactory. In this paper, we extend a recent deep reinforcement learning hyper-heuristic framework by fusing the visual information of real-time packing with distributional information of random parameters of the problem. Computational experiments show that our method outperforms the state of the art online methods with reductions in optimality gap between 2%–19% for knapsack problem and 0.7% for the online strip packing problem. In addition, a new visual analysis presentation is also devised to better interpret the learned packing strategies, which can reveal more information than the widely used landscape analysis. As online packing problems are widely available in production environments, the proposed approach can serve as an important reference to solve other similar combinatorial optimisation problems for which visual layout inputs would aid learning. [ABSTRACT FROM AUTHOR]

It is challenging for robots to detect grasps with high accuracy and efficiency-oriented to multi-object clutter scenes, especially scenes with objects of large-scale differences. Effective grasping representation, full utilization of data, and formulation of grasping strategies are critical to solving the problem. To this end, this paper proposes an antipodal-points grasping representation model. Based on this, the Antipodal-Points-aware Dual-decoding Network (APDNet) is presented for grasping detection in multi-object scenes. APDNet employs an encoding–decoding architecture. The shared encoding strategy based on an Adaptive Gated Fusion Module (AGFM) is proposed in the encoder to fuse RGB-D multimodal data. Two decoding branches, namely StartpointNet and EndpointNet, are presented to detect antipodal points. To better focus on objects at different scales in multi-object scenes, a global multi-view cumulative attention mechanism, called Global Accumulative Attention Mechanism (GAAM), is also designed in this paper for StartpointNet. The proposed method is comprehensively validated and compared using a public dataset and real robot platform. On the GraspNet-1Billion dataset, the proposed method achieves 30.7%, 26.4%, and 12.7% accuracy at a speed of 88.4 FPS for seen, unseen, and novel objects, respectively. On the AUBO robot platform, the detection and grasp success rates are 100.0% and 95.0% on single-object scenes and 97.0% and 90.3% on multi-object scenes, respectively. It is demonstrated that the proposed method exhibits state-of-the-art performance with well-balanced accuracy and efficiency. [ABSTRACT FROM AUTHOR]

An industrial control system (ICS) can be described as an integration of heterogeneous processes, i.e., a discrete event-driven process at the automatic control layer and a continuous time-driven process at the physical layer. To accurately describe the behaviour of an ICS, a model must capture the characteristics of both the discrete and continuous processes and their interactions. We present a method to discover a data-interpreted Petri net (DIPN) model of an ICS from the observed input/output signals of the controller. A DIPN model combines a Petri net and differential equations which are typically used for modelling discrete event-driven processes and continuous time driven processes. Hence, the main contribution of our paper is to discover guards on event transitions which serve as the link between the discrete automatic control layer and the continuous physical layer processes of an ICS. Supporting this, we rely on existing system identification methods to discover models of discrete and continuous processes, i.e., Petri nets and differential equations. Model discovery is useful for wide range of applications such as reverse engineering, performance optimisation, and anomaly detection. This paper is motivated by the problem of discovering a model of an industrial control system for anomaly detection. Unlike black-box model discovery methods such as neural networks, the goal of our work for practical application is to discover a human readable model which it can provide actionable reports of anomaly detection. To assess the accuracy of the discovered DIPN model, it was used as a binary classifier to detect anomalies in a publicly available dataset of a water treatment plant. • Anomalous behaviour of Industrial Control Systems can lead to industrial accidents. • Monitoring Industrial Control Systems is essential for their safe operation. • System identification is a useful tool to build monitoring systems. • The effectiveness of an anomaly detection system depends on the actionable insights. [ABSTRACT FROM AUTHOR]

This paper proposes an intelligent slope stability prediction method based on the improved pelican optimization algorithm (IPOA) and the optimization random forest (RF) algorithm to reduce disasters and accidents caused by slope instability. First, exploratory data analysis (EDA) is performed using correlation diagrams, heat maps under different states, box plots, histograms, and quantile–quantile (Q-Q) diagrams of variables, followed by establishing a high-quality data set for slope engineering cases and an index system for slope stability prediction. Second, 10 benchmark functions reveal that the IPOA algorithm outperforms other algorithms. Accordingly, this paper develops a slope stability prediction model based on the IPOARF algorithm. Afterward, a set of intelligent slope stability prediction systems is created using MATLAB tools and applied to Lala Copper Mine in Sichuan Province. Finally, this paper compares the accuracy of various models and subjects the proposed model to additional testing. The results reveal that the prediction model based on improved IPOA and RF algorithms is reliable and effective, with an accuracy of up to 90.4%, which can serve as a solid technical basis for slope instability disaster prediction in geotechnical engineering. [ABSTRACT FROM AUTHOR]

Several methods of preference modeling, ranking, voting and multi-criteria decision-making include pairwise comparisons. It is usually simpler to compare two objects at a time, furthermore, some relations (e.g., the outcome of sports matches) are naturally known for pairs. This paper investigates and compares pairwise comparison models and the stochastic Bradley–Terry model. It is proved that they provide the same priority vectors for consistent (complete or incomplete) comparisons. For incomplete comparisons, all filling in levels are considered. Recent results identified the optimal subsets and sequences of multiplicative/additive/reciprocal pairwise comparisons for small sizes of items (up to n = 6). Simulations of this paper show that the same subsets and sequences are optimal in the case of the Bradley–Terry and the Thurstone models as well. This somehow surprising coincidence suggests the existence of a more general result. Further models of information and preference theory are subject to future investigation to identify optimal subsets of input data. • Multiplicative/additive/reciprocal pairwise comparisons vs. Bradley–Terry model. • Their equivalence is shown in case of consistency. • All filling in levels are investigated. • The same subsets of comparisons are shown to be optimal even in inconsistent cases. • Results raise new research direction: Are such coincidences valid in further models? [ABSTRACT FROM AUTHOR]

This paper proposes an intelligent slope stability prediction method based on the improved pelican optimization algorithm (IPOA) and the optimization random forest (RF) algorithm to reduce disasters and accidents caused by slope instability. First, exploratory data analysis (EDA) is performed using correlation diagrams, heat maps under different states, box plots, histograms, and quantile–quantile (Q-Q) diagrams of variables, followed by establishing a high-quality data set for slope engineering cases and an index system for slope stability prediction. Second, 10 benchmark functions reveal that the IPOA algorithm outperforms other algorithms. Accordingly, this paper develops a slope stability prediction model based on the IPOARF algorithm. Afterward, a set of intelligent slope stability prediction systems is created using MATLAB tools and applied to Lala Copper Mine in Sichuan Province. Finally, this paper compares the accuracy of various models and subjects the proposed model to additional testing. The results reveal that the prediction model based on improved IPOA and RF algorithms is reliable and effective, with an accuracy of up to 90.4%, which can serve as a solid technical basis for slope instability disaster prediction in geotechnical engineering. [ABSTRACT FROM AUTHOR]

• Machine learning approaches to resolve identity issues. • Implementing TensorFlow to investigate policing dataset. • Predictive models using ML techniques to identify fraudulent or genuine IDs. This paper focuses on applications of various machine learning techniques on an anonymized policing dataset used in EU SPIRIT Horizon 2020 project to identify fraudulent identities and help Law Enforcement Agencies (LEAs) in their investigation in finding potential criminals and identity resolution. Lack of qualitative data and appropriate methodology to carry out research on criminal fraudulent identities is a common reason for fewer research in this area. Additionally, it is a very sensitive data to work with and minor inaccuracy in prediction of result causes massive impact in the society as genuine people could be questioned whereas criminals could be sent free. Both of these issues are addressed in this paper by application of 39 million records from policing dataset and working towards higher accuracy while building the model. Various machine learning approaches are applied to train the dataset to make predictions and the research focus on being able to predict the 5 suspected fraudulent identities out of 39 million records in the policing dataset. One of the applied machine learning techniques include TensorFlow along with Keras model which has seldomly been applied by researchers in detection of criminal data. To compare the results and test accuracy of TensorFlow model, other machine learning techniques such as Support Vector Machine, Naïve Bayes and K-nearest Neighbours are also applied to have a comparative study on the obtained outcomes from each model. The goal of this research is to find fraudulent IDs amongst all the anonymized IDs in the criminal dataset using TensorFlow and three other machine learning models and select the most optimal model out of them. Since the model is comparing two names so string-matching techniques such as Levenshtein edit distance, Hamming Distance, Jaro-Winkler and Soundex were applied to select an effective approach first before building the model and analysing the results. TensorFlow model demonstrated highest accuracy with relatively least execution time and the only model to successfully predict all the 5 suspects from the policing dataset. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurodegenerative disorder that produces both motor and non-motor complications, degrading the quality of life of PD patients. Over the past two decades, the use of wearable devices in combination with machine learning algorithms has provided promising methods for more objective and continuous monitoring of PD. Recent advances in artificial intelligence have provided new methods and algorithms for data analysis, such as deep learning (DL). The aim of this article is to provide a comprehensive review of current applications where DL algorithms are employed for the assessment of motor and non-motor manifestations (NMM) using data collected via wearable sensors. This paper provides the reader with a summary of the current applications of DL and wearable devices for the diagnosis, prognosis, and monitoring of PD, in the hope of improving the adoption, applicability, and impact of both technologies as support tools. Following PRISMA (Systematic Reviews and Meta-Analyses) guidelines, sixty-nine studies were selected and analyzed. For each study, information on sample size, sensor configuration, DL approaches, validation methods and results according to the specific symptom under study were extracted and summarized. Furthermore, quality assessment was conducted according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) method. The majority of studies (74%) were published within the last three years, demonstrating the increasing focus on wearable technology and DL approaches for PD assessment. However, most papers focused on monitoring (59%) and computer-assisted diagnosis (37%), while few papers attempted to predict treatment response. Motor symptoms (86%) were treated much more frequently than NMM (14%). Inertial sensors were the most commonly used technology, followed by force sensors and microphones. Finally, convolutional neural networks (52%) were preferred to other DL approaches, while extracted features (38%) and raw data (37%) were similarly used as input for DL models. The results of this review highlight several challenges related to the use of wearable technology and DL methods in the assessment of PD, despite the advantages this technology could bring in the development and implementation of automated systems for PD assessment. • Deep learning and wearable technology are used in diagnosis and monitoring. • Growing interest in the use of deep learning and wearables in Parkinson's disease. • The adoption of deep learning in Parkinson's disease is currently under development. • Technical and methodological challenges difficult the technology adoption. [ABSTRACT FROM AUTHOR]

There are lots of research papers for ASC, and in recent years it is rapidly increasing. DCASE also provides different types of competition for the submission of several papers to solve the various tasks of ASC and it is the opportunity for the research scholars either to participate in those competitions or to provide the enhanced model for ASC. This paper provides details about the various recent approaches along with the block diagram used for pre-processing required before model development for ASC. It also includes a description of different recent techniques used for the classification of different sounds for ASC tasks. The comparative analysis for different recent available techniques both for pre-processing and classification has been done and summarized in this paper. It also describes the contributions towards the survey on ASC by comparing this paper with some existing survey papers based on several parameters like functionality described separately, results from description with quantifiable value, a dataset with proper quantifiable analysis, and pictorial representation of model discussed, etc. Finally, considering the benefits for eminent research scholars, this paper has also focused on the details for future directions for both pre-processing and classification for ASC. [Display omitted] • A systematic review on pre-processing and classification techniques for acoustic scenes. • Comparative analysis of pre-processing and classification techniques. • Discussion on different processing techniques for classification. • Identifies the future directions for further research in the area. [ABSTRACT FROM AUTHOR]

Several methods of preference modeling, ranking, voting and multi-criteria decision-making include pairwise comparisons. It is usually simpler to compare two objects at a time, furthermore, some relations (e.g., the outcome of sports matches) are naturally known for pairs. This paper investigates and compares pairwise comparison models and the stochastic Bradley–Terry model. It is proved that they provide the same priority vectors for consistent (complete or incomplete) comparisons. For incomplete comparisons, all filling in levels are considered. Recent results identified the optimal subsets and sequences of multiplicative/additive/reciprocal pairwise comparisons for small sizes of items (up to n = 6). Simulations of this paper show that the same subsets and sequences are optimal in the case of the Bradley–Terry and the Thurstone models as well. This somehow surprising coincidence suggests the existence of a more general result. Further models of information and preference theory are subject to future investigation to identify optimal subsets of input data. • Multiplicative/additive/reciprocal pairwise comparisons vs. Bradley–Terry model. • Their equivalence is shown in case of consistency. • All filling in levels are investigated. • The same subsets of comparisons are shown to be optimal even in inconsistent cases. • Results raise new research direction: Are such coincidences valid in further models? [ABSTRACT FROM AUTHOR]

Mahalanobis-Taguchi system (MTS) was proposed by Genichi Taguchi for the study of multidimensional systems and has been effectively applied in many fields. The traditional MTS method focuses on the dimensionality reduction of multidimensional systems and the measurement of abnormal degree of observations. In order to further improve the effectiveness of the MTS method, many studies related to the MTS method have been conducted, including the construction of Mahalanobis space, threshold determination, selection of useful variables, and so on. However, only four studies have been conducted to analyze the potential causes of abnormal observations diagnosed by the MTS method. Meanwhile, these studies ignore the counter-correlations between variables, which will make it impossible to find the potential causes of some abnormal observations and therefore unable to effectively improve these abnormal observations. This paper aims to improve the traditional MTS method and then propose an effective method to analyze the potential causes of abnormal observations diagnosed by the improved MTS method. First, this paper proposes to divide the traditional MTS method into two phases. In phase one, the scaled Mahalanobis distance function is still used to measure the abnormal degree of observation, while in phase two the weighted Mahalanobis distance function should be used to make the diagnosis more reasonable and accurate. Second, a new decomposition method of weighted Mahalanobis distance is proposed to identify potential causes of abnormal observations based on Mason-Young-Tracy (MYT) decomposition method. The method focuses not only on whether individual variables are outside their reference ranges, but also on whether the linear relationships between variables are consistent with the reference group, which makes the analysis of abnormal causes more comprehensive and reliable. Finally, the blood viscosity diagnosis system in a hospital was improved using the improved MTS method. The results showed that the variables in the diagnosis system decreased by 37.5%, and the differentiation between the abnormal conditions and the health group increased by 102%. At the same time, the potential causes of an abnormal observation were identified based on the MYT decomposition method of weighted Mahalanobis distance. The above results verified the feasibility and effectiveness of the method in this paper. [ABSTRACT FROM AUTHOR]

With the number of market participants rising, the issue of contradiction between heavy supervision task and insufficient supervision resource have become increasingly urgent for regulatory authorities to consider. The credit risk rating of enterprises is therefore introduced to improve the efficiency of supervision. By analyzing the purposes of enterprise credit risk rating and the multiple demands for regulatory authorities, this paper offers a multi-classification ensemble model with hybrid decomposition strategy and two-stage multi-objective feature selection. First, an adaptive resampling technique is introduced into the hybrid decomposition strategy for multi-classification, so to appropriately allocate supervision resources in each credit risk class. Then, a two-stage multi-objective feature selection method is developed to combine the various demands of regulatory authorities for feature selection. In the first stage, results of multiple Filter feature selection methods are integrated as output to improve the performance of feature information; In the second stage, the feature information from the first stage is used as input to guide the Wrapper feature selection, which is based on the Improved Multi-objective Ant Colony Optimization. Finally, a real listed enterprise credit dataset of China is used to evaluate the performance of each module and the entire model. The empirical results show that the design of hybrid decomposition strategy and multi-objective feature selection can not only deal with the class-imbalanced problem during the decomposition process, but also take into account the balance of each demand well. More importantly, a desirable framework is set in this paper to simplify the process from imbalanced multi-classification to a balanced binary one. [ABSTRACT FROM AUTHOR]

The stock market is a dynamic, complex, and chaotic environment, which makes predictions for the stock market difficult. Many prediction methods are applied to the stock market, but most are supervised learning and cannot effectively parse the trading information present in the stock market. This paper proposes a prediction model that combines unsupervised learning with reinforcement learning to address this problem. Firstly, we capture the stock trend from historical stock data and construct the trading environment state of the market by the growing neural gas (GNG) algorithm in unsupervised learning. Secondly, the reward function is restructured to provide timely feedback on the trading information present in the stock trading market. Finally, a novel trading agent algorithm, Triple Q-learning, is designed to execute the corresponding trading behavior and make comprehensive predictions of the stock market based on the environment state constructed by GNG. Experimental results on several stock datasets demonstrate that the proposed model outperforms other comparative models in this paper. [ABSTRACT FROM AUTHOR]

This paper proposes a new Multiple-criteria decision-making (MCDM) method called MUltiple-TRIangles ScenarioS (MUTRISS) with two scenarios respecting different levels of access to complete information for material selection problems. MUTRISS calculates the areas occupied by alternatives in n-dimensional space, employing analytic geometry and converting each alternative into n-edges forms. The paper applies MUTRISS to three material selection case studies, with Ti-6Al-4V, Material 4, and AISI 4140 Steel- UNS G41400 emerging as the best materials for the three examples with the highest overall scores of 0.036, 4.540 and 0.427 respectively. The results are compared with various MCDM methods through four statistical measures, including relative closeness ratio, robustness analysis, compromise ranking coefficient, and similarity degree. The measures focus on different aspects of MCDM methods in solving problems and their results. The paper concludes that MUTRISS offers a more robust and reliable approach for material selection problems compared to other MCDM methods, with the first scenario of MUTRISS being more reliable than the second scenario. The paper also emphasizes the importance of validating results in material selection problems due to the potential irreversible consequences of selecting the wrong material. [ABSTRACT FROM AUTHOR]

Due to increasing air pollution, which is a consequence of the environmental effects of production in various industries, green supply chain management (GSCM) has attracted the attention of both scholars and practitioners. Green supplier selection is an important problem in GSCM and seeks to satisfy a firm's environmental goals as well as its economic targets. In this paper, for the first time, a green supplier selection problem considering both green and non-green evaluation criteria in a closed-loop supply chain is studied, and a cap-and-trade mechanism as a way of controlling the air pollution caused by manufacturers is proposed. To solve this particular problem, we propose a multi-objective robust optimization (RO) model. This specific model is an effective approach to handle uncertainty. A numerical example using randomly generated data, accompanied by subsequent discussion of the proposed approach, is deployed to validate the model. The results prove that the developed model for green supplier selection is able to effectively enhance the decision-making process of the experts. By illustrating the trade-off in robustness between the model and proposed solutions, as well as the effect of the deviation penalty on the closeness of results to the achieved solution, we show how firms can make optimal decisions when assigning the parameters. Furthermore, analyses show that decreasing the allowance amount (cap) and increasing the allowance prices in the cap-and-trade system escalate the firms' costs, but lower the amount of carbon released. Finally, we show that the cap-and-trade mechanism results in a better solution in terms of the total utility of the supply chain compared to the penalty-based system for a specific range of carbon allowance. • This paper generalizes the green supplier selection and order allocation problem. • A mathematical model for the problem is developed. • A robust optimization approach to handle the model uncertainty is developed. • The impact of changes in model parameters on the objective functions is analyzed. • The cap-and-trade mechanism is compared with a penalty-based mechanism. [ABSTRACT FROM AUTHOR]

• An adaptive threshold-based noise determination method is developed. • A noise score is designed to evaluate the noise level of each instance. • The iterative filtering process combined with a bagging filter is applied. • Thorough analysis of the experimental results is provided. The quality of training data plays a decisive role in the establishment of intelligent models. Since raw data obtained from the real world are usually entwined with noise due to variety of causes, noise filtering has become an important aspect of machine learning techniques. In contrast with the extensive research conducted on noise elimination for classification purposes, papers addressing this problem for regression tasks are rather scarce. In this paper, we propose a novel noise filter to clean noisy instances with real-valued label noise. Aiming at the deficiency of the existing noise determination criterion, a new adaptive threshold-based method is first proposed. It allows a noisy instance to be adaptively defined according to the fitting difficulty levels of different datasets, and areas with different densities. Embedded with this criterion, an effective noise filtering procedure is also designed. An ensemble filtering scheme and an iterative filtering process are combined to detect as many potential noisy samples as possible from the original training set. According to the acquire noise detection information, a noise score for evaluating the noise level is specifically developed. The potential noisy samples whose scores exceed a reasonable threshold are further filtered, which can compensate for the possible errors incurred during the previous procedure, and contribute to more reliable filtering results. The validity of the proposed method is studied in exhaustive experiments. We discuss reasonable hyperparameters, and compare the developed method with several state-of-the-art noise filters. The outcomes show that the prediction accuracy of the utilized regressor can greatly benefit from preprocessing the given raw dataset by using our method. Simultaneously, the method is able to acquire a good balance between the elimination of noisy samples and the retention of clean samples, and consistently achieves a better noise filtering performance. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) technologies are increasingly applied to traffic flow prediction (TFP) to enhance prediction accuracy. This study utilizes bibliometric methods and network analysis measures to gain insights into the research status, development process, opportunities, and challenges of AI-based TFP research based on the literature data retrieved from the Web of Science core collection. The study first conducts basic statistical analysis of all papers. Subsequently, cooperation network analysis is conducted to identify the most productive countries/territories, institutions, and authors, the cooperative relationships, and the formed research communities. Co-citation network analysis is then employed to identify publications that have made outstanding contributions to the AI-based TFP field. Finally, the main path analysis of the paper citation network is used to analyze the knowledge diffusion process, while the keyword co-occurrence analysis is conducted to reveal the evolution characteristics of the research topics. Based on the bibliometric analysis results, we gain insights into the opportunities and challenges in this field from the perspectives of data, models, and applications, and provide pertinent suggestions for future research. Overall, this study can assist researchers in capturing the state-of-the-art and research directions in AI-based TFP. [ABSTRACT FROM AUTHOR]

Forecasting the forthcoming intersection movement-based traffic volume enables adaptive traffic control systems to dynamically respond to the fluctuation of traffic demands. In this paper, a deep-learning based Signal-control Refined Dynamic Traffic Graph (ScR-DTG) Model is proposed for advancing the network-level movement-based traffic volume prediction task. The proposed model attempts to further improve the-state-of-art and practice algorithms in traffic prediction for arterial network adaptive signal control utilizing tradition traffic flow theory boosted deep-learning methodology. For precisely inferencing the movement-based demand at cycle-to-cycle level, the proposed model incorporates spatial graph convolution inferencing layer and temporal inferencing layer to explore both the intricate spatial temporal dependencies, respectively. A signal control refining module is contrived to deduce the controlled movement saturation flow and introduce the essential control inferences, which is of great significance but frequently neglected in the previous researches. Additionally, according to the real-time movement specified travel time, this paper creatively constructs an adjacent graph with dynamic order for more accurately capturing the ever-changing spatial relevancies. Field experiments with multiple signal schemes were conducted in the downtown area of Zhangzhou (China). The promising results demonstrated the state-of-the-art accuracy than other high-performance volume prediction algorithms. Implementing the proposed model enables to obtain accurate movement-based volume predictions, which would assist the traffic management agencies in adjusting signal timing adaptively and further improve the efficiency of signal intersection. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a growing interest in neural network-based medical image classification methods, which have demonstrated remarkable performance in this field. Typically, convolutional neural network (CNN) architectures have been commonly employed to extract local features. However, the transformer, a newly emerged architecture, has gained popularity due to its ability to explore the relevance of remote elements in an image through a self-attention mechanism. Despite this, it is crucial to establish not only local connectivity but also remote relationships between lesion features and capture the overall image structure to improve image classification accuracy. Therefore, to tackle the aforementioned issues, this paper proposes a network based on multilayer perceptrons (MLPs) that can learn the local features of medical images on the one hand and capture the overall feature information in both spatial and channel dimensions on the other hand, thus utilizing image features effectively. This paper has been extensively validated on COVID19-CT dataset and ISIC 2018 dataset, and the results show that the method in this paper is more competitive and has higher performance in medical image classification compared with existing methods. This shows that the use of MLP to capture image features and establish connections between lesions is expected to provide novel ideas for medical image classification tasks in the future. • SCNet learns the comprehensive and important information. • S-MLP divides feature maps into regions for MLP to enhance overall features. • C-MLP groups channels to reduce overfitting and improve generalization. [ABSTRACT FROM AUTHOR]

The development of 5G brings convenience to people, but it also brings threats. It is particularly important to analyze attack–defense confrontation from a macro perspective. Network security of graph is an important research problem in current network environment. A Stackelberg game model based on 5G network graph is established to analyze the attack–defense confrontation in this paper. In order to solve the Nash equilibrium, a compact particle swarm optimization based on t-Location-Scale distribution (tCPSO) is proposed. The tCPSO uses less memory space and has better optimization performance. The experiments prove that tCPSO has better optimization performance than other heuristic algorithms on CEC2013. The clustering experiments further show that tCPSO has better optimization ability than other heuristic algorithms. The optimal defense strategies under different attack–defense resources are analyzed in this paper. It is concluded that increasing the successful defense rate is more effective for the defender to obtain greater profit than reducing the successful attack rate. Using intelligent computing to solve Nash equilibrium is a new idea for researchers to analyze attack–defense confrontation. • The tCPSO proposed in this paper has strong optimization ability. • Intelligent computing can efficiently solve Nash equilibrium. • More defense resources and fewer attack resources are better for the defender. • Increasing the successful defense rate is more beneficial to the defender. [ABSTRACT FROM AUTHOR]

This paper proposes a robust algorithm using two convolutional neural networks (CNN) to find a lost gamma source in a room despite various unpredictable obstacles. This algorithm is an improved and complementary method to our previous research, which does not limit the use of the algorithm to a specific geometry, and the presence of obstacles does not reduce the performance and inability of the method. In our previous research, an algorithm including a CNN was used to estimate the location of the lost gamma source in known geometry. In this paper, by adding another CNN to the previous algorithm, the algorithm can be used in environments with unknown geometry. The environmental simulations and data generation are performed using the Geant4 simulation program. The method has been tested in a designed scenario to check its effectiveness. The results show that by using these two CNNs, an agent can intelligently find the gamma source place in a room with multiple obstacles without human intervention with 95 percent accuracy. [ABSTRACT FROM AUTHOR]

Population aging and a shortage of medical resources are driving the growth of home health care (HHC). Many HHC studies have focused on developing an optimal routing plan to reduce operation costs; however, few have addressed the attendant long-term sustainability concerns, such as HHC center locations and carbon emissions from transportation. This paper proposes a home health care location-routing problem with a mixed fleet of electric and conventional vehicles that considers battery swapping stations. It aims to simultaneously determine the locations of HHC centers, the scheduling of caregivers with respect to skill requirements, and a routing plan for a mixed fleet under specific time windows, load capacities, synchronized visits, and driving ranges. To address this problem, the paper proposes a novel competitive simulated annealing (CSA) algorithm in which a series of problem-specific effective local search operators expand the solution space of the CSA algorithm, with a competitive mechanism to adaptively adjust these operators to accelerate convergence speed and improve exploration ability. To enhance the exploitation ability, it employs a modified simulated annealing algorithm with a heating strategy and variable neighborhood descent. Comparison experiments are conducted to verify the superior performance of the CSA algorithm in comparison to existing algorithms and the Gurobi solver. Finally, sensitivity analyses are performed on key factors and provide some new managerial insights. [ABSTRACT FROM AUTHOR]

This paper investigates how to conduct bidirectional feedback mechanism by establishing trust chains in social network group decision making (SN-GDM), which is more applicable than the ordinary bidirectional feedback process, and further explores its application in the Metaverse virtual community. Firstly, a trust chain between decision makers (DMs) is constructed from the trust network, which can connect two individuals who do not have trust relationship and therefore assist the opinion interaction and consensus building. Then, this paper designs an opinion transmission model based on trust chain to realize the information transmission and bidirectional feedback process of DMs, and the characteristics of the proposed model are revealed through simulation analysis. Finally, the proposed trust chain driven bidirectional feedback mechanism is applied to an illustrative example of Metaverse virtual community decision-making problem to demonstrate the effectiveness and applicability of the model, and comparisons with other methods shows the advantage of our proposed approach. • A trust chain searching method in the trust network is proposed. • A opinion transmission model based on trust chain is constructed. • A bidirectional feedback mechanism is proposed. [ABSTRACT FROM AUTHOR]

Background —Nowadays, with the rise of Internet access and mobile devices around the globe, more people are using social networks for collaboration and receiving real-time information. Twitter, the microblogging site that is becoming a critical source of communication, has also grabbed the attention of spammers to distract users. So far, researchers have introduced various defense techniques to detect spams and combat spammers' activities. To overcome this problem, many novel techniques have been offered by researchers, which have greatly enhanced spam detection performance. Objective —The purpose of this paper is to identify, taxonomically classify, and compare current Twitter spam detection approaches in a systematic way. Method —This study presents a comprehensive Systematic Literature Review (SLR) method for spam detection on Twitter regarding 70 most relevant papers published between 2010 and October 2022. Literature review analysis reveals that most of the existing Twitter spam detection techniques are based on textual content and messages (tweets) that rely on Machine Learning (ML)-based algorithms. The major differences in these ML algorithms which use various classification and clustering algorithms are related to various feature selection methods. Hence, we propose a classification based on different feature selection analyses, namely content analysis, user analysis, tweet analysis, network analysis, and hybrid analysis. Results —Various parameters are identified to investigate the Twitter spam detection approaches, and each of the papers was examined to find the research methodology and present comparative studies on current approaches. Conclusion —This paper demonstrates that the existing Twitter spam detection approaches have encountered several open issues, including scalability, streaming data analysis, and processing. The most obvious unresolved issues are spam drift and non-English tweets. [ABSTRACT FROM AUTHOR]

In this paper, a novel self-learning design of an interval type-2 hierarchical fuzzy system (IT2 HFS) based on rule relevance is proposed. Different from the existing methods, this paper uses data stream instead of batch data to construct the IT2 HFS. As time goes on, HFS gradually fills its rule base through fuzzy partition algorithm, where the rule base of HFS is empty at the beginning. A new self-updating method for consequent parameters is proposed based on rule relevance. When HFS is used for online learning, the proposed method can ensure that the system has better performance. The designed self-learning IT2 HFS is applied to online regression prediction issue, and is tested on two different online regression datasets. Self-learning type-1 HFS is also compared with self-learning IT2 HFS in prediction accuracy and system complexity. The results illustrate that the self-learning IT2 HFS performs better in prediction accuracy with lower rules. [ABSTRACT FROM AUTHOR]

Reducing the number of lower-level function evaluations (LFEs) is crucial to designing a bilevel evolutionary algorithm (BLEA) for bilevel optimization. Direct neighbor solution transfer (DST) is regularly used in BLEA because it can improve the lower-level search efficiency and reduce the number of LFEs. But this method still faces the challenge of misleading searches to make the algorithm converge to the wrong optimum. This paper proposes a bilevel improved multi-operator differential evolution algorithm (BL-IMODE) for bilevel optimization, which uses the knowledge transfer and adaptive coordinate systems approach. Specifically, this paper proposes a lower-level search knowledge transfer (LLS-KT) and a lower-level (LL) optimal solution distribution information transfer (LLO-DIT) mechanism to implement knowledge transfer. In LLS-KT, transferring LL solutions to the LL optimizer is similar to DST, but the LLS-KT transfers multiple solutions and thus has less possibility of misleading searches than DST. Moreover, the LLO-DIT transfers the LL optimal solution distribution information to the LL optimizer for generating promising offspring solutions. Since this method does not directly transfer LL solutions, it avoids misleading searches. Additionally, the adaptive coordinate systems (ACS) approach is used in two-level optimizers to suit different fitness landscapes and further reduce the number of LFEs. In ACS, three differential evolution mutation operators are produced in two coordinate systems. An adaptive strategy is used to select the suitable differential evolution mutation operator to generate promising offspring solutions in the Eigen coordinate or original coordinate system. Experimental studies on three test suites benchmark problems for comparison with seven state-of-the-art algorithms are conducted. The results show BL-IMODE has a significant advantage over the comparative algorithms. Finally, BL-IMODE is applied to tackle the inverse optimal control problem. • We propose a bilevel improved multi-operator differential evolution algorithm. • We propose a knowledge transfer approach to avoid misleading search. • We propose an adaptive coordinate systems approach to improve search efficiency. • We outperform all existing approaches in most test instances. [ABSTRACT FROM AUTHOR]

Identifying users' accounts on different platforms is important for the management and marketing of e-commerce platforms. To address the problem of sparse consumer behavior data on e-commerce platforms, this paper designs Double Generative Adversarial Network (Double-GAN) to compensate the data. This method uses not only the data of the one platform , but also of heterogeneous e-commerce platforms for alternate iteration compensation. For the complexity of "user-behavior-commodity" data feature space of e-commerce bookstore platform. Considering Consider the advantages of model JUST in capturing structural and semantic information of multiple types of nodes. This paper proposes a new method UBC2vec to integrate user's interest in commodities and change the random walk strategy to represent the overall information of data feature space of heterogeneous e-commerce platform. Finally, for the high computational complexity of the user alignment algorithm, this paper constructs a "user-commodity" bipartite graph to delineate the roles of users and reduce the complexity. Experiments show that the model can effectively alleviate the data sparsity problem and reduce the computational complexity of the algorithm. Above the real data set, it can effectively match users' accounts in different bookstore platforms. [ABSTRACT FROM AUTHOR]

In this paper, we address the Integrated Planning and Scheduling Problem (IPSP) on parallel and identical machines. Planning and scheduling are essential for the efficient management of supply chains. Although both pursue the same general objective, they are usually performed independently mostly because they relate to different timescales. As a consequence, the generated plans and schedules are typically sub-optimal from a global standpoint. The approaches followed in this paper explicitly consider the interdependence between the planning and scheduling activities by solving them simultaneously in an integrated way. We explore different heuristics based on variable neighborhood search procedures with new and specifically designed neighborhood structures relying on the properties of the IPSP. The quality of these approaches is evaluated through extensive computational experiments performed on a large set of benchmark instances. The results show that the proposed methods achieve high-quality solutions, with a substantially low computation time, outperforming other state-of-the-art results reported in the literature. • New approach to solve planning and scheduling simultaneously in an integrated way. • Different metaheuristics with new and specially designed neighborhood structures. • Exhaustive computational study on a large set of benchmark instances. • Low computing time for high-quality solutions, outperforming literature results. [ABSTRACT FROM AUTHOR]

• The feature representation of the network was extracted from a randomly searched sequence of vertices. • In networks of scientific documents, representation learning needs to consider similarity and citation relationships. • This paper proposed a method to search and learn multiple paths connecting similar documents in a scientific document network. • From scientific papers and patent datasets, we found empirical evidence that our algorithm is suitable for representation learning. • This paper can contribute to preparing the basis for inducing innovation in science and technology from scientific documents. A network is a structure that can represent an organic relationship of observations. Network representation learning has the advantage of extracting latent features in a network. In recent years, various algorithms have been developed to embed network representation in a low-dimensional feature space. Conventional algorithms learn a sequence of vertices that are randomly searched from a network and convert a vertex into a vector. This study focused on the representation learning of document networks. Thus, this study proposes a scalable network representation learning algorithm that preserves the structure and content of the document network and reduces data sparsity. To do this, we used the shortest walks to extract a sequence of vertices that reflected semantic similarity from a network. The shortest walk is a method for finding several shortest paths that connect similar vertices. After this, the sequence of vertices was inputted into the language model, assuming that the sequence was a sentence. Scientific papers and patent datasets provided empirical evidence for the validity of our approach. The former, the bibliography network of scientific paper, consists of 17,716 nodes and 105,734 edges. The latter is a patent describing a technology for energy, representing a network of 24,894 nodes and 28,314 edges. The results showed that the proposed algorithm exhibited the lowest error of the tested methods in multi-class classification and link prediction tasks. The results of these tasks provided evidence that our algorithm is suitable for extracting feature representations of document networks. [ABSTRACT FROM AUTHOR]

Effective supply chain management is crucial for economic growth, and sustainability is becoming a key consideration for large companies. COVID-19 has presented significant challenges to supply chains, making PCR testing a vital product during the pandemic. It detects the presence of the virus if you are infected at the time and detects fragments of the virus even after you are no longer infected. This paper proposes a multi-objective mathematical linear model to optimize a sustainable, resilient, and responsive supply chain for PCR diagnostic tests. The model aims to minimize costs, negative societal impact caused by shortages, and environmental impact, using a scenario-based approach with stochastic programming. The model is validated by investigating a real-life case study in one of Iran's high-risk supply chain areas. The proposed model is solved using the revised multi-choice goal programming method. Lastly, sensitivity analyses based on effective parameters are conducted to analyze the behavior of the developed Mixed-Integer Linear Programming. According to the results, not only is the model capable of balancing three objective functions, but it is also capable of providing resilient and responsive networks. To enhance the design of the supply chain network, this paper has considered various COVID-19 variants and their infectious rates, in contrast to prior studies that did not consider the variations in demand and societal impact exhibited by different virus variants. [ABSTRACT FROM AUTHOR]

Backward-Forward Sweep is one of the most used procedures for the power flow calculation of large-scale active multiphase distribution networks. This paper introduces the decoupled network model which is suitable for the multi-threaded implementation of the Backward-Forward Sweep procedure. The main objectives of this paper are: (i) to introduce the decoupled new models of traditional and Electronically-coupled Distributed Energy Resources, (ii) to introduce the decoupled models of single-, two- and three-phase line sections, (iii) to give the detailed Unified Modeling Language diagrams of the software model and procedures, (iv) to give a detailed model and a procedure for the single-threaded power flow calculation, and (v) to give a detailed model and a procedure for the multi-threaded power flow calculation of the large-scale active multiphase distribution networks. The results show the advantage of the proposed decoupled single-threaded approach over the traditional coupled-based one – the speedup is up to 160%. Moreover, the speedup of the decoupled multi-threaded calculation of the power flow compared to the single-threaded one goes up to the 200%. This means that the decoupled multi-threaded implementation is up to 300% faster than the coupled one. These results prove that the Backward-Forward Sweep is particularly usable for the multi-threaded implementation. [ABSTRACT FROM AUTHOR]

Multimodal medical image fusion extracts useful information from different modal medical images and integrates them into one image for a comprehensive and objective lesion description. However, existing methods ignore the simultaneous retention of significant edge and energy information that reflect lesion characteristics in medical images; this affects the application value of medical image fusion in computer aided diagnosis. This paper proposes a novel medical image fusion scheme based on extended difference-of-Gaussians (XDoG) and edge-preserving. A simple yet effective energy-based scheme was developed to generate the fused energy layer, which helped preserve energy. Moreover, the averaging filter was used to generate the detail layers of source images. The fusion of detail layers was considered the combination of significant and non-significant edge information. A rule of the detail layer with a salient edge based on edge extraction operator XDoG was proposed to efficiently detect the salient structure of the significant edges, and a spatial frequency energy operator was developed to detect the gradient and energy of non-significant information. The fused result could be reconstructed by synthesizing the fused energy layer and details of significant and non-significant edges. Experiments demonstrated that the proposed approach outperforms some advanced fusion methods in terms of subjective and objective assessment. The code of this paper is available at https://github.com/JEI981214/FGF-and-XDoG-based. [ABSTRACT FROM AUTHOR]

The occurrence of dynamic events such as machine breakdown during workshop production can make the original scheduling scheme infeasible. Therefore, this paper establishes a mathematical model for a multi-objective dynamic flexible job shop scheduling problem with machine breakdown, and proposes a multi-objective migrating birds optimization algorithm based on game theory. Firstly, in order to solve the problem of difficult to determine the weight in weighted multi-objective optimization, this paper introduces game theory to balance the Pareto optimality and fairness between the two objectives of production efficiency and stability. When solving the solution of the game model, there may be no perfect Nash equilibrium solution, so a solution method that approximates the Nash equilibrium solution is designed. In the improved migrating algorithm, neighborhood operators based on path relinking and machine age are designed to improve the search ability. Based on the attributes of multi-objective problems, a multiple similarity measure method is designed to select and replace solutions. The experiment part proves the effectiveness of the game strategy in multi-objective optimality and fairness, and concludes that the algorithm has good performance by comparing with the advanced algorithms in recent years. • A multi-objective game model is designed to solve dynamic scheduling problems. • The approximate Nash equilibrium solution is designed to solve the game matrix. • The neighborhood operators of path relinking and machine age are designed. • A multiple similarity measurement method is designed for multi-objective problem. [ABSTRACT FROM AUTHOR]

The rise of carpooling has made it easier for intercity commuters to travel between work and home. In this paper, we study the carpooling problem of delivering intercity commuters to the high-speed railway station, considering the uncertain role of commuters with a car. We propose a driver-rider matching and route optimization method to solve this problem. Specifically, we first formulate the carpooling problem as a multi-objective mixed-integer nonlinear programming model. The model considers two conflicting objectives, that is, the maximization of the platform revenue and the minimization of the path costs. In addition, we prove that the problem investigated in this paper is NP-Complete. Second, we present an improved NSGA-II algorithm to obtain the optimal carpooling schemes. Finally, we conduct some numerical experiments to validate the effectiveness of the proposed method and explore the effects of the model parameters on the carpooling results. The results show that the proposed method works well regarding convergence and diversity. [ABSTRACT FROM AUTHOR]