Search

In this paper, we address the problem of generating and enhancing Passive Gamma Emission Tomography (PGET) data from a deep learning perspective. The PGET instrument has been developed for the verification of spent nuclear fuel and relies on image reconstruction and analysis algorithms to detect missing or substituted fuel pins. Such techniques are sensitive to the quality of the input data: noisy or incomplete sinograms yield to poor reconstructions and, consequently, to low-confidence results. The development and validation of these algorithms is based on complex Monte Carlo simulations that are time-consuming and computationally-demanding. We propose the use of Convolutional Neural Networks (CNNs) for enhancing PGET data. Our technique learns the mapping between incomplete or noisy sinograms and their corresponding full representation. It effectively exploits the high degree of redundancy of the measurements, i.e. the contribution of a single pin can be observed from many different directions, to learn the underlying model of the data and to make informed predictions. The two main applications of our approach are: (1) accelerating Monte Carlo simulations and (2) pre-processing real measurements to enhance them before running the standard image reconstruction and analysis techniques. The experimental evaluation was performed with both, simulated and real measurements. Results show how effectively CNNs can learn and exploit the structure of the data. For the two use cases evaluated, denoising sinograms and inpainting incomplete ones, our technique achieved state-of-the-art performance with execution times in the order of milliseconds. • PGET sinogram data enhancement. • Monte Carlo Simulations acceleration with Deep Learning. • Sinogram denoising. [ABSTRACT FROM AUTHOR]

• A new homogenized cross-section parameterization package was developed and tested on a VVER-1200 fuel assembly model as a case study. • The package includes hyperparameter optimization, dataset splitting, and automatic model selection. • Several classical fitting methods and machine learning regression algorithms were implemented. • The evaluation was focused on a low number of sample points resulting from the utilization of Monte Carlo codes. This paper deals with group constant parameterization, a necessary step to utilize the results of assembly-level neutronics calculations at the full-core level. The focus is on low sample size problems when the commonly used linear interpolation approach is inadequate, a typical situation of using Monte Carlo codes for group constant generation. This work presents a newly developed code package for automated group constant parameterization. It implements several machine learning regression models − including a novel polynomial regression algorithm − performs hyperparameter optimization and selects the best model based on a detailed evaluation. The applicability of the new code package is demonstrated in a case study for a VVER-1200 fuel assembly covering both normal operation and transient conditions. In this example, the novel polynomial regression model provides a 73 pcm average error in k inf that leads to reactivity coefficients well within the desired precision. [ABSTRACT FROM AUTHOR]

Transient test reactors with the ability to test fissile specimens under extreme conditions have been crucial tools in the development of nuclear technologies. Less than 10 unique facility designs have ever been constructed, most of which remain operational today and still use the original nuclear fuel constructed for them more than 40 years ago. Historic fuel systems for transient test reactors vary in significant ways which have marked influences on reactor capabilities. Eventually, new fuel will be needed to support the longevity of transient test reactor missions. This paper reviews precedent transient reactor fuel systems in the context of their unique requirements. A few key conclusions are illustrated by comparing and contrasting these transient test reactors. Fuel composites which are mostly graphite can enable transient reactors with very high neutron fluence capability (>2E16 n/cm2) and are amenable to longer "shaped" transients but cannot achieve pulses <10 ms in duration. Reducing the graphite-to-uranium ratio can yield a very narrow pulse capability but delivers less fluence and requires cores with considerably more fissile material. Designs based on uranium dioxide (UO 2) make use of readily available materials to create compact cores with narrow pulse width capabilities but with moderate neutron fluence capabilities (∼2E15 n/cm2). Uranium zirconium hydride (U-ZrHx) is a well-established fuel system for pulsing reactors which has been intermittently manufactured throughout the decades. U-ZrHx offers similar capabilities to UO 2 designs in terms of nuclear kinetics, but with about half the fluence capability (∼1E15 n/cm2). An evolution of the UO 2 system, termed "ternary ceramic" fuel, shows that dispersing UO 2 in zirconium oxide and calcium oxide can increase fluence capability greatly (∼7E15 n/cm2), but is not presently a commonly available fuel form. A unique composite of UO 2 and beryllium oxide (UO 2 -BeO) can be used to create a core with similar kinetics and compact core geometry as U-ZrHx designs, but with significantly higher fluence capability (∼6E15 n/cm2). Like ternary ceramic fuel, newly fabricated UO 2 -BeO would require reestablishing its historic manufacturing process which would be further complicated by the health hazards associated with beryllium. Like most engineering problems, there is no perfect solution, but this paper outlines the advantages and disadvantages of candidate fuel options to help guide detailed evaluations. [ABSTRACT FROM AUTHOR]

• The jet theory is applied for predicting the gas column's breakup location. • A jet model in a pipe under a swirling flow field is developed. • The liquid-phase dominated cases are experimentally validated. Maintaining the stability of the gas column/liquid film in a swirling flow field in thorium molten salt reactor (TMSR) and pressurized water reactor (PWR). The linear stability analysis in jet theory can be used for this problem. This method focuses on the maximum growth rate of the perturbation at the gas–liquid interface and determines the stability of the gas column based on it. This approach is usually applied in the cases under non-swirling flow field. In this paper, we extend this method to the study of stability problem under a swirling flow field. We classify the stability problem within different reactors into two categories. The detailed calculation method of the maximum growth rate is given separately for the two cases. Based on the calculated maximum growth rate, we experimentally verified the stability method. Considering the differences between non-swirling flow field and swirling flow field, we improve the original method and give a new prediction correlation. The prediction errors of new correlation are within ±20 %. [ABSTRACT FROM AUTHOR]

• 3D integrated model of PHENIX reactor primary system including cold and hot pool was established. • Overall flow paths in reactor vessel during PHENIX Dissymmetric Test were identified. • 3D asymmetric thermal stratification phenomena in cold pool, hot pool and local area of IHX inlet were captured. • 3D temperature distribution of internals during PHENIX Dissymmetric Test were obtained. Temperature distribution of internals under different transient events is important for the design and safety analysis of pool-type sodium-cooled fast reactor (SFR). It is influenced by overall flow and thermal stratification phenomena in the multi-scale sodium pool. Due to the difficulty to perform experiment, three-dimensional (3D) numerical method is usually adopted for obtaining the temperature distribution and analyzing complex phenomena in pool-type SFRs. It needs to be further validated using the published benchmark, such as PHENIX Dissymmetric Test. The simplified model in system code and 3D model of local area in current study cannot capture the complex coupling effect of cold and hot pool during dissymmetric test. In this paper, an integrated 3D model of PHENIX reactor primary system both including cold and hot pools is established. The steady and transient simulation with 1800 s of PHENIX Dissymmetric Test process are carried out. The key parameters of simulation are compared with the available experimental and predicted data, which achieves good agreement. Overall flow and asymmetric temperature distribution phenomena in cold pool, hot pool and local area of IHX inlet are simulated. There is a temperature difference between different sides of IHX inlet during a period after scram, with the maximum value of 80 ℃ approximately at 90 s. This validated numerical method can be further used for the analysis of thermal hydraulic characteristics in other pool-type SFR. The obtained temperature distribution of internals can provide the reference for the stress assess of structures in the engineering design. [ABSTRACT FROM AUTHOR]

This paper presents a novel method for estimating the safety gap between deformed fuel channels. The irradiation causes deformation of the fuel channel, which narrows the control rod channel, directly affecting the safety of the reactor. Investigating the critical safety gap between fuel channels can be utilized for safety assessments in design. Specifically, we first define the safety gap and three typical dropping cases. Next, we analyze the forces on the control rod, including flow resistance and channel resistance. Then, we establish a nonlinear dynamic model and simulate three dropping cases. Finally, we explore the influence of the friction coefficient and the fuel rod bundle. We find that the critical safety gap for the NHR200-II reactor is -5.0 ∼ -3.1 mm (standard case) and -4.2 ∼ -2.5 mm (arbitrary case), respectively. Our study provides a novel solution to accurately evaluate the effect of deformed boxed channels on the control rod's dropping. [ABSTRACT FROM AUTHOR]

[Display omitted] • This paper demonstrates the Kartini Reactor's educational utility. • A case study was conducted by investigating reactor criticality. • The study achieved reactor criticality by inserting 5 fuel elements, totaling 2524.57 g. • The critical mass determination was refined by plotting the inverse of counts against the total mass of U-235. • This approach utilized both polynomial and linear trend lines to analyze the data. Research reactors serve critical roles across multiple domains—from physics to medicine—while distinctly not being used for electrical power generation. The Kartini Research Reactor located in Indonesia exemplifies the integration of research reactors in education and scientific research, particularly highlighting its educational applications through the Internet Reactor Laboratory (IRL). Established in 1978 and operational since 1979, the Training Research and Isotope Production by General Atomic (TRIGA) Mark II reactor is instrumental in advancing nuclear science with facilities like the Lazy Suzan/Rotate Rack and Beam Port. The IRL significantly enhances its educational process, enabling remote access to reactor physics experiments, thus facilitating global university participation in nuclear engineering education. This capability allows for the real-time visualization of reactor operations and detailed presentation of operational data and experiment results, enriching the learning experience. This paper demonstrates the Kartini Reactor's educational utility through a case study investigating reactor criticality and determining the critical fuel mass under safe operational parameters. Employing telecommunication hardware and software, the study achieved reactor criticality by inserting 5 fuel elements, totaling 2524.57 g. The critical mass determination was further refined by plotting the inverse of counts against the total mass of U-235. This approach utilized both polynomial and linear trend lines to analyze the data. While the polynomial analysis provided upper and lower thresholds for critical mass, the linear regression offered a precise critical mass value of 2428.62 g, showcasing a deviation of only 4% from the experimental findings. [ABSTRACT FROM AUTHOR]

The application of virtual reality (VR) technology in rehabilitation is a research area that has been attracting remarkable attention recently, especially as an intervention with learning and developmental disorders such as dyslexia and autism. Multi-modal VR-based rehabilitative systems can provide a rich experience to patients by responding to various types of bio-signals. This paper proposes a framework for incorporating voice input in rehabilitative games. The proposed framework equips collaborative learning environments with voice based interaction which allows for a more dynamic flow of therapy sessions between physically impaired patients and specialists in a rehabilitative VR environment. The proposed framework's pipeline begins with a speech recognition module to parse utterances into sentences. Next, comes the feature extraction module to identify the intent of the user and entities as well. Finally, we modulate the 3D environment in Unity. The framework was designed in a way that guarantees smooth integration with any game or 3D environment. Several technologies were tested in terms of accuracy and speed to increase the overall performance of the pipeline. To the best of our knowledge, this research is the first to do the following: 1) build a dataset of instructions, inspired by a product already used in the healthcare market, 2) based on which we could realize a multi-modal system, with voice as one of the modalities, for the context of VR-based rehabilitation. We evaluate every stage in the system pipeline, and we show that we can achieve considerable results on each of these stages including the speech recognition module, with a 5.64% word error rate, and on intent classification where the BiLSTM model outperforms BERT in the Named Entity Recognition by 11% in terms of the F1-score. We envisage the proposed system to lend itself well to emerging healthcare frameworks in the Metaverse. [ABSTRACT FROM AUTHOR]

Efficient generalisation in supply chain inventory management is challenging due to a potential mismatch between the model optimised and objective reality. It is hard to know how the real world is configured and, thus, hard to train an agent optimally for it. We address this problem by combining offline training and online adaptation. Agents were trained offline using data from all possible environmental configurations, termed contexts. During an online adaptation phase, agents search for the context maximising rewards. Agents adapted online rapidly and achieved performance close to knowing the context a-priori. In particular, they acted optimally without inferring the correct context, but by finding a suitable one for reward maximisation. By enabling agents to leverage off-line training and online adaptation, we improve their efficiency and effectiveness in unknown environments. The methodology has broader potential applications and contributes to making RL algorithms useful in practical scenarios. We have released the code for this paper under https://github.com/abatsis/supply_chain_few_shot_RL. • Agents are usually trained in simulations, but tested in the real world. • We use online adaptation to close the gap between simulation and the real world. • This problem is prevalent in real-world application of AI. • We test our methods in supply chain optimisation. [ABSTRACT FROM AUTHOR]

Monitoring highways and obtaining traffic data are relevant for planning and programming new investments. This data often comes from automatic counting stations or roadside traffic surveys that can also obtain socioeconomic and trip origin and destination information. This paper presents novel contributions to address the Bi-objective Support Unit Location Problem to Assist Roadside Traffic Survey with Multi-Stages (BSULP). The objective of this research is to propose an approach to optimize two conflicting objectives simultaneously: minimizing travel costs from support units to survey stations and minimizing the number of selected support units. To achieve this, we propose three modified versions of the NSGA-II algorithm, with tailored strategies for constraints handling of the BSULP. These strategies involve a significantly reduced structure for the chromosomes, and initial population, crossover and mutation algorithms that maintain the feasibility of the solutions. For a benchmark of instances, we implemented an exact ϵ -Constraint method, and the results were compared with different versions of modified NSGA-II using Hypervolume (HV) and Generational Distance (GD) metrics. The best results were obtained with the M3NSGA-II version, which on average represented more than 94% (HV) and less than 17% (runtime) of the exact method. In addition, it was possible to obtain solutions for large instances which was not possible with the exact method. • Modified NSGA proposal with relevant results in reduced computational time. • Chromosome encoding with significant size reduction and increased efficiency. • A new strategy for population reduction after the first generation. • Average of 94% for the Hypervolume with less than 17% of the exact method runtime. • Greater gains on medium and large instances. [ABSTRACT FROM AUTHOR]

• Propose a hybrid IVIF framework to evaluate the EMW disposal modes. • Develop an innovative IVIF-GBWM to derive the global criteria weights. • Fuse IVIF regret theory and MABAC to evaluate alternatives. This article attempts to develop a hybrid heterogeneous framework to evaluate the disposal modes for emergency medical waste (EMW) by fusing GBWM (group best-worst method), RT (regret theory), and MABAC (multi-attributive border approximation area comparison). This hybrid framework tries to address three key challenges: (i) determining criteria weights, (ii) computing the regret-rejoice evaluation matrix, and (iii) identifying the optimal alternative. To address the first challenge, this paper innovates an innovative interval-valued intuitionistic fuzzy (IVIF) GBWM, which considers multiplicatively consistent IVIF preference relation, to efficiently determine global criteria weights (GCWs). For the second challenge, RT is incorporated to compute the regret-rejoice evaluation matrix using experts' heterogeneous evaluations which consist of intervals, triangular fuzzy numbers, hesitant fuzzy linguistic term sets and IVIF values. Regarding the third challenge, MABAC is applied to sort alternatives based on the obtained regret-rejoice evaluation matrix. Afterwards, the validity of the hybrid framework is verified by an illustrative example, and its advantages are demonstrated with some worthy sensitivity and comparative analyses. Some innovations of the proposed framework are highlighted below: (i) The IVIF GBWM streamlines calculation load, since it derives GCWs by solving the group weight assignment model only once; (ii) The introduction of RT into MABAC assists decision-makers in mitigating regret psychology, enhancing the quality of decision outcomes; (iii) The proposed framework's practicality is enhanced by leveraging heterogeneous evaluations which capture the inherent complexities of actual decision-making problems. [ABSTRACT FROM AUTHOR]

Surrogate-assisted meta-heuristic algorithms (SAMAs) have been increasingly popular in recent years for solving challenging optimization problems. However, the majority of recent studies concentrate on low-dimensional problems. In this paper, a scale-free network based multi-surrogate-assisted stochastic fractal search (SF-MSASFS) algorithm is proposed. Specifically, based on the stochastic fractal search (SFS) algorithm, multiple surrogate models, namely RBF and Kriging models, are used to enhance the robustness of the algorithm. The scale-free network is used to build the topology structure of the SFS algorithm, and the offspring particles are generated by means of the connection relationship between the parent particles. In addition, to further enhance adaptability, an adaptive mechanism is implemented, tailoring three distinct update mechanisms based on their corresponding reward values. Finally, the performance of the proposed algorithm is demonstrated by comparing the proposed algorithm with a number of state-of-the-art SAMAs on several well-known benchmark functions, in particular in solving high-dimensional expensive problems (HEOPs). The results underscore the SF-MSASFS algorithm's commendable optimization performance. (The MATLAB code can be found at the authors github: https://github.com/xiaodi-Cheng/SF-MSASFS) [ABSTRACT FROM AUTHOR]

This paper proposes an intelligent risk management system in stock markets based on indications of social media platforms. Based on a brief survey, we found that the literature focuses on identifying, assessing and optimizing risks in stock markets using classical data sources as well as utilizing mathematical, statistical and machine learning techniques. So, we suggest a trendy data source that is social media and employing natural language processing as an advanced technique to identify and estimate risks in stock markets. This NLP model can help the investors of stock markets to be aware of the potential risks, its types and magnitudes which can help them to take the best decisions. In addition , we describe this model and some important expressions for risk analysis, risk recognition and risk estimation are driven. Besides, a practical experiment is provided to identify and evaluate the potential risks in NASDAQ stock market. Moreover, several performance measures are used to validate the efficiency of the proposed model such as the mean accuracy for the processes of risk analysis, risk identification and risk assessment is 73.33 %. [ABSTRACT FROM AUTHOR]

Game theory is a powerful tool in modeling actual decision-making problems. In many cases, it is difficult for players to give a crisp value of payoff. To conquer this issue, various extensions of fuzzy sets have been introduced to represent the payoffs. Although type-2 intuitionistic fuzzy (T2IF) set (T2IFS) can solve the game problem effectively, sometimes players prefer to give the primary (secondary) membership and non-membership degrees with some approximate ranges rather than crisp values. T2IFS cannot express such uncertain payoffs. Thus, this paper initiates a new concept called type-2 interval-valued intuitionistic fuzzy (T2IVIF) set (T2IVIFS) which has stronger ability than T2IFS and interval-valued intuitionistic fuzzy set (IVIFS) in representing uncertain information. Hamacher operations of T2IVIFSs are given. Hamming and Euclidean distances between T2IVIFSs are defined respectively. Some Hamacher aggregation operators for T2IVIFSs are developed and some desirable properties are analyzed. Afterwards, an effective method is proposed for solving T2IVIF matrix game, which can make game results more accurate and reliable. An example of new energy vehicle industry development is provided to validate the proposed T2IVIF matrix game. Comparative analyses reveal that the matrix game in T2IVIF environment has better flexibility and reliability than that in T2IF and IVIF environments. [ABSTRACT FROM AUTHOR]

Accurately forecasting demand is a potential competitive advantage, especially when dealing with perishable products. The multi-billion dollar horticultural industry is highly affected by perishability, but has received limited attention in forecasting research. In this paper, we analyze the applicability of general compared to dataset-specific predictors, as well as the influence of external information and online model update schemes. We employ a heterogeneous set of horticultural data, three classical, and twelve machine learning-based forecasting approaches. Our results show a superiority of multivariate machine learning methods, in particular the ensemble learner XGBoost. These advantages highlight the importance of external factors, with the feature set containing statistical, calendrical, and weather-related features leading to the most robust performance. We further observe that a general model is unable to capture the heterogeneity of the data and is outperformed by dataset-specific predictors. Moreover, frequent model updates have a negligible impact on forecasting quality, allowing long-term forecasting without significant performance degradation. • A comprehensive study on time series forecasting for horticultural sales. • Machine learning outperforms classical forecasting in horticultural sales prediction. • Statistical and calendar features are beneficial for horticultural sales prediction. • Detailed analysis of the impact of model refitting schemes on forecasting quality. • Company-specific forecasting models are superior to cross-company predictors. [ABSTRACT FROM AUTHOR]

Workflow scheduling poses a significant challenge in cloud computing environments, offering the potential to optimize execution time and reduce economic costs. In this paper, we present BFWS, a bidirectional workflow scheduling approach with a feedback mechanism, designed to address the deadline-constrained cost-aware workflow scheduling problem. BFWS is built upon a bidirectional scheduling framework that facilitates resource allocation from both the forward and the backward directions of the workflow. This framework incorporates a dynamic sub-deadline prediction method, leveraging prior knowledge and real-time scheduling progress to enhance the accuracy of task sub-deadline predictions. Additionally, a cost-aware resource selection operator is integrated into the framework, enabling the selection of appropriate virtual machines based on considerations of cost and time constraints. To further enhance decision-making and optimize performance, we introduce a feedback mechanism that enables BFWS to adapt and improve over time. Through extensive experiments using real-world workflows, the superior performance of BFWS is validated compared to the state-of-the-art algorithms. Moreover, the effectiveness of the bidirectional scheduling approach and the feedback mechanism is demonstrated individually through rigorous validation experiments. These findings highlight the potential of BFWS in achieving efficient and effective workflow scheduling in cloud computing environments. • Introducing bidirectional scheduling for task flexibility. • Implementing a feedback mechanism for continuous improvement. • Testing on diverse real-world workflows, demonstrating competitiveness. [ABSTRACT FROM AUTHOR]

During the last decade, RRT* algorithm has been widely concerned by researchers because of its asymptotic optimality. However, the slow convergence rate of the RRT* algorithm leads to poor quality of the optimal paths at small number of iterations. Meanwhile, searching the initial path slowly limits its application scenarios. To overcome these problems, a directionally biased variable step APF-RRT* (DBVS-APF-RRT*) algorithm is proposed in this paper. Firstly, a novel directionally biased variable step sampling strategy is used in RRT* algorithm to quickly generate the initial path. Then, global random sampling and key region sampling strategies are added to improve global search ability and optimal path quality. At the same time, an artificial potential field (APF) method is introduced to improve the ability of obstacle avoidance. In addition, we propose a pruning strategy based on triangular inequality with direct connection of goal points to reduce the number of redundant nodes and shorten the path length. Finally, DBVS-APF-RRT* algorithm is compared with RRT*, Bias-RRT*, Informed-RRT* and Bias-P-RRT* algorithms to verify its superiority of optimal path quality, stability of the algorithm and its rapidity of finding the initial path. • A DBVS sampling strategy is proposed to find the initial path with ultra-high speed. • Global random sampling and key region sampling are added to improve path quality. • APF algorithm is combined to improve obstacle avoidance ability and adaptability. • A pruning strategy is proposed to reduce redundant nodes and shorten path length. [ABSTRACT FROM AUTHOR]

Graph Neural Networks (GNNs) have been extensively employed in the field of recommendation systems, offering users personalized recommendations and yielding remarkable outcomes. Recently, GNNs incorporating contrastive learning have demonstrated promising performance in handling the sparse data problem of recommendation systems. However, existing contrastive learning methods still have limitations in resisting noise interference, especially for multi-behavior recommendation. To mitigate the aforementioned issues, this paper proposes a GNN-based multi-behavior recommendation model called MB-SVD that utilizes Singular Value Decomposition (SVD) graphs to enhance model performance. In particular, MB-SVD considers user preferences across different behaviors, improving recommendation effectiveness. First, MB-SVD integrates the representation of users and items under different behaviors with learnable weight scores, which efficiently considers the influence of different behaviors. Then, MB-SVD generates augmented graph representation with global collaborative relations. Next, we simplify the contrastive learning framework by directly contrasting original representation with the enhanced representation using the InfoNCE loss. Through extensive experimentation, the remarkable performance of our proposed MB-SVD approach in multi-behavior recommendation endeavors across diverse real-world datasets is exhibited. • Proposing a novel contrastive learning paradigm for multi-behavior recommendation. • Solving the data sparsity and noise problem simultaneously. • Adopting SVD method for graph augmentation to enhance model performance. • Experiments on real-world datasets show the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

With the exponential growth in the number of academic researchers, it is crucial for editors of scientific journals to identify the highest-quality papers. While several measures exist to evaluate a paper's impact post-publication, the challenge of determining the potential impact of a manuscript during the review process remains an understudied issue. In this paper, we propose a reviewer-reputation ranking algorithm to identify high-quality papers based on paper citations, where a reviewer's reputation is computed from the correlation between their past ratings and the current number of citations received by the papers they have evaluated. During the review process, reviewers with high reputation scores are given more weight to determine the quality of papers. We test the algorithm on an artificial network with 200 reviewers and 600 papers, as well as on the American Physical Society (APS) data set, including in the analysis 308,243 papers and 274,154 mutual citations. We compare our approach with two existing methods, demonstrating that our algorithm significantly outperforms the others in identifying manuscripts with the highest quality. Our findings can help improve the impact of scientific journals, thereby contributing to academic and scientific progress. • We propose an algorithm to identify the papers with the highest quality from a large number of submissions. • We compare our new algorithm with other existing methods of aggregating user ratings in various online services. • We test our algorithm both with an artificial network and with the empirical data of the APS data set. • We show that our algorithm outperforms the other methods in identifying the papers with the highest quality. [ABSTRACT FROM AUTHOR]

This paper focuses on a NP-Hard vehicle routing problem with profits, and presents a hybrid heuristic solution approach for the Capacitated Team Orienteering Problem (CTOP), which is a variant of the well-known team orienteering problem. In the CTOP, given a set of homogeneous fleet and a set of clients to each is associated a deterministic profit and volume demand, one maximizes the collected profits for serving customers by operating a set of routes while respecting vehicles' limited time and volume capacities. Our proposed method to solve the CTOP is a Hybrid Adaptive Large Neighborhood Search (HALNS) heuristic. Several removal and insertions operators with different node selection strategies and local search procedures are developed to generate solutions in the first step. In the second step, solutions' routes are passed to a set packing problem which is solved using an exact branch-and-cut procedure in order to obtain the best solution. Compared to all the state-of-the-art methods, extensive computational experiments show that our method outperforms in terms of solution quality and/or computational times when tested on the small and large-scale benchmark CTOP instances respectively proposed by Archetti et al. (2009) and Tarantilis et al. (2023). Furthermore, our hybrid method improves 10 of the best known solutions for large-scale benchmark instances. • We propose an efficient hybrid heuristic for the Capacitated Team Orienteering Problem. • Our heuristic method is based on an adaptive large neighborhood search. • The proposed heuristic identifies most of the best-known solutions. • We improve 10 of best known solutions for large-scale benchmark instances. [ABSTRACT FROM AUTHOR]

Correctly predicting up trends, sideways trends and down trends for stock returns is vitally important in financial market. Group penalized trinomial logit dynamic models can not only provide three-class label information and three-class probability estimations, but also enhance three-class prediction performance by shrinking group coefficients to bypass multi-collinearity and over-fitting. In this paper we propose G-LASSO/G-SCAD/G-MCP penalized trinomial logit dynamic models with 24 technical indicators to predict up trends, sideways trends and down trends for stock returns, develop group coordinate descent algorithm (GCD) to complete group selection and group estimation simultaneously, establish the relative optimal Bayes classifier to identify class labels, introduce three-class confusion matrix and hypervolume under the ROC manifold (HUM) to assess the three-class prediction performance to 15 methods. Experiment results show that G-LASSO/G-SCAD/G-MCP penalized trinomial logit dynamic models predict better than LASSO/SCAD/MCP penalized trinomial logit dynamic models, 6 deep learning models and 3 machine learning models in terms of Accuracy and HUM. In particular, the highest prediction Accuracy (the average Accuracy) from G-LASSO penalized method outperforms 3-Layer Long Short-Term Memory (LSTM) and Random Forest (RF) for 4.76% and 10.29% (8.16% and 11.78%), respectively. Moreover, compared with LASSO/SCAD/MCP penalized methods, G-LASSO/G-SCAD/G-MCP penalized methods enhance 5.88% Accuracy and only require 27.29% Predicted Time. The proposed G-LASSO/G-SCAD/G-MCP penalized trinomial logit dynamic models can not only be extended as more general three-class prediction method by replacing 24 technical indicators by some factors influencing three-class response variable, but also be directly extended as more efficient multi-category prediction method by replacing three-class response variable by multi-category response variable. • Propose the new group penalized methods to predict stock return movement direction. • Develop a new GCD algorithm for G-LASSO/G-SCAD/G-MCP penalized trinomial logit model. • Obtain the new rapidly convergent G-LASSO/G-SCAD/G-MCP estimator. • Introduce a few measures to assess three-class prediction performance to 15 methods. • G-LASSO/G-SCAD/G-MCP penalized methods predict better than the other 12 methods. [ABSTRACT FROM AUTHOR]

• The paper explores AI decision-making to enhance transparency of CIN diagnosis using colposcopy images. • The study presents interpretable insights for clinical validation using different XAI methods. • Saliency method showed best result, using gradients to reveal likely malignancy traits. • Expert Clinic Validation of results conducted, along with statistical analyses. Although artificial intelligence techniques have performed well in analysing medical images, it is essential to consider the degree of understanding or interpretation in evaluations. This is especially important when diagnostic support is involved, as the trustworthiness of machine learning predictions needs to be clarified and evaluated. For deep learning algorithms to be translated into clinical practice, they must be made less opaque. To examine the classification of cervical dysplasia-diagnosed patients, we will explore explainable artificial intelligence (XAI) approaches, by implementing seven different interpretation techniques (Saliency, XRAI, Integrated Gradients, Smooth Gradients, Smooth Integrated Gradients, Grad-CAM, Smoothgrad-CAM). These XAI techniques shall be explored in order to assess the performance of four Convolutional Neural Network models (AlexNet, VGG16, MobileNet, and InceptionNet). Our results show that saliency qualities most closely match expert annotations, and there is a moderate to strong association between a model's sensitivity and the agreement between humans and computers. We also discovered a relevant relationship between expert insights and computational learning. This highlights the potential role of human expertise in influencing effective computer learning. [ABSTRACT FROM AUTHOR]

With rising data security concerns, privacy preserving machine learning (ML) methods have become a key research topic. Federated learning (FL) is one such approach which has gained a lot of attention recently as it offers greater data security in ML tasks. Substantial research has already been done on different aggregation methods, personalized FL algorithms etc. However, insufficient work has been done to identify the effects different model update strategies (concurrent FL, incremental FL, etc.) have on federated model performance. This paper presents results of extensive FL simulations run on multiple datasets with different conditions in order to determine the efficiency of 4 different FL model update strategies: concurrent, semi-concurrent, incremental, and cyclic-incremental. We have found that incremental updating methods offer more reliable FL models in cases where data is distributed both evenly and unevenly between edge nodes, especially when the number of data samples across all edge nodes is small. • Federated learning model performance is influenced by multiple environmental factors. • Different update strategies react differently to dataset size and participant number. • Update strategies can be categorized into incremental and concurrent. • Strategy selection can help inter-institutional collaboration achieve better results. • Incremental modes are more robust to lack of data. [ABSTRACT FROM AUTHOR]

Current sonar image recognition methods excel in closed-set and balanced scenarios, but real underwater data often follow an open-set and long-tailed distribution, leading to misclassifications, especially among tail classes. Although open-set long-tail recognition (OLTR) tasks have received attention in natural images in recent years, there has been a lack of systematic research in sonar images. To address this gap, we present the first comprehensive study and analysis of open-set long-tail recognition in sonar images (Sonar-OLTR). In this paper, we establish a Sonar-OLTR benchmark by introducing the Nankai Sonar Image Dataset (NKSID), a new collection of 2617 real-world forward-looking sonar images. We investigate the challenges posed by long-tail distributions in existing open-set recognition (OSR) evaluation metrics for sonar images and propose two improved evaluation metrics. Using this benchmark, we conduct a thorough examination of state-of-the-art OSR, long-tail recognition, OLTR, and out-of-distribution detection algorithms. Additionally, we propose a straightforward yet effective integrated Sonar-OLTR approach as a new baseline. This method introduces a Push the right Logit Up and the wrong logit Down (PLUD) loss to increase feature space margins between known and unknown classes, as well as head and tail classes within known classes. Extensive experimental evaluation based on the benchmark demonstrates the performance and speed advantages of PLUD, providing insights for future Sonar-OLTR research. The code and dataset are publicly available at https://github.com/Jorwnpay/Sonar-OLTR. • Enhancing underwater robot usability by tackling open-set & long-tail challenges. • Building the first benchmark: new dataset, improved metrics, and experimental plan. • Our method improves model's ability via feature synthesis and specialized loss function. • Our method outperforms state-of-the-art on three different sonar image datasets. [ABSTRACT FROM AUTHOR]

• Two axiomatic notions for information measures are introduced. • Two novel methods for information measures are established. • A convergent group consensus reaching process is developed. • An empirical application is provided to show the advantages. For practical group decision-making (GDM) problems, DMs play varying degrees of importance. Thus, determining the weight of decision makers (DMs) is one of the key issues in GDM. Additionally, it is known that information measures methods have been a growing focus in recent years. Therefore, under the probabilistic linguistic fuzzy information environment, a group consensus reaching approach with the help of information measures is designed. First, two axiomatic notions regarding to entropy and similarity measures for probabilistic linguistic term sets (PLTSs) are introduced. Then, in line accordance with logarithmic function, two novel methods of entropy and similarity measures with PLTSs are established, which is followed by the determination of the weight vector of DMs by using probabilistic linguistic fuzzy entropy. Subsequently, based on probabilistic linguistic fuzzy entropy and similarity measures, we develop a group consensus reaching process (CRP), which is convergent and able to enhance the group consensus level. Moreover, the proposed group CRP can calculate the weight vector with the initial probabilistic linguistic evaluation information of DMs. Finally, for displaying the applicability and merits of the developed group CRP, the numerical example, sensitivity analysis and comparative analysis are provided. It's worth noting that our proposed measure fully utilizes the elements of the original probabilistic linguistic preference relationships (PLPRs), which can reduce the systematic error of the entire decision model, thereby making the results more reflective of the original decision information from DMs. The novelties of this paper are as follows: (1) The proposed novel way can estimate the degree of importance of DMs by the mean fuzzy entropy of PLPRs; (2) We construct two formulas about fuzzy entropy and similarity measures for PLTSs and proof these formulas, which are both reasonable and effective. [ABSTRACT FROM AUTHOR]

In the realm of video surveillance systems, pedestrian detection (PD) is a crucial task that enables the identification and tracking of individuals, crowd monitoring, and people counting. However, accurate PD is a challenging task due to variations in the appearance and pose of pedestrians. With the advent of deep learning (DL) techniques, particularly convolutional neural networks (CNNs), computer vision (CV) methods for object classification and detection have been revolutionized. Effective PD depends on supervised learning, which requires large labeled datasets. This paper, we present pedestrian detection (PD) using a Robust Multi-modal Pedestrian Detection using a Deep Convolutional Neural Network with an Ensemble Learning (RMPD-DCNN-EL) model. This model effects computer vision and ensemble learning to accomplish precise pedestrian detection. The SimAM EfficientNet model with a stochastic gradient descent (SGD) optimizer is used for feature extraction, while ensemble classification is performed using three DL models are Nested Long Short-Term Memory (NLSTM), deep belief networks (DBNs), and extreme learning machine (ELM). To evaluate the effectiveness of tettapproach, we use the INRIA dataset, and the experimental results prove the greater performance of RMPD-DCNN-EL over other DL methods. The proposed method enables robust pedestrian detection despite modifications in arrival and pose, making it an operative solution for video surveillance systems in smart transport environments. Experimental results show that the detection accuracy is 99.30% of the proposed algorithm is considerably higher than that of the traditional convolutional neural network algorithm. [ABSTRACT FROM AUTHOR]

The volume of e-commerce continues to increase year after year. Buying goods on the internet is easy and practical, and took a huge boost during the lockdowns of the Covid crisis. However, this is also an open window for fraudsters and the corresponding financial loss costs billions of dollars. In this paper, we study e-commerce credit card fraud detection, in collaboration with our industrial partner, Worldline. Transactional companies are more and more dependent on machine learning models such as deep learning anomaly detection models, as part of real-world fraud detection systems (FDS). We focus on continual learning to find the best model with respect to two objectives: to maximize the accuracy and to minimize the catastrophic forgetting phenomenon. For the latter, we proposed an evaluation procedure to quantify the forgetting in data streams with delayed feedback: the plasticity/stability visualization matrix. We also investigated six strategies and 13 methods on a real-size case study including five months of e-commerce credit card transactions. Finally, we discuss how the trade-off between plasticity and stability is set, in practice, in the case of FDS. • Fraud detection models must be updated continually to handle new fraud strategies. • They must balance plasticity (learn new patterns) and stability (remember old ones). • We show how to quantify both and discuss the trade-off for fraud detection. • We provide an extensive comparison of six strategies and 13 different models. • We present a real case study based on more than 50 million e-commerce transactions. [ABSTRACT FROM AUTHOR]

A digital hologram (DH) is an ultra-high-value video content that includes three-dimensional information in two-dimensional data. Therefore, for the distribution of this content, the intellectual property rights must be protected. This paper proposes robust hologram watermarking based on deep neural networks using guided attack modules and attack rate control techniques. The proposed method robustly embeds the watermark into the original hologram to cope with various attacks while keeping the invisibility that the watermarked hologram is similar to the original hologram. Previous work considered PSNR during training. However, hologram exists in the complex domain. Thus SNR for complex numbers should be considered to confirm the reconstruction results. In addition, we propose an enhanced network with increased depth to improve performance compared with previous work. Experiments show that the proposed method outperforms the previous work regarding robustness and invisibility against various attacks, such as Crop Out, Salt & Pepper Noise, and Rotation. Therefore, this study is expected to be widely used in various fields, such as digital image authentication, copyright protection, and data security. [ABSTRACT FROM AUTHOR]

Wi-Fi fingerprint, a mainstream technology of Indoor Location Base Service (ILBS), estimates location through a radiomap that places received signal strength (RSS) as AP and location. However, the semi-regularity of the radiomap due to the diversity of the service area limits the fingerprint locally. To solve this problem, in this paper, we propose a Region Clustering based Fingerprint Model that combines a Region Clustering algorithm and a Region Fingerprint network that enables an integrated Wi-Fi fingerprint. The proposed model consists of RCA, which extracts regions from the global radiomap and selects regions, and RFN, which estimates locations regardless of the size of regions. The proposed RCA divides the service area into optimal regions in the offline phase using clustering and standardizes the radio map by matching each area to the same size. Also, it selects a standardized radio map in the online phase and delivers it to the positioning network. In addition, the proposed RFN estimates the location through reference pointwise Bi-LSTM. Through this, the proposed RCF model is capable of flexible fingerprinting in any size of the service area and can provide stable positioning in terms of performance. [ABSTRACT FROM AUTHOR]

Class imbalance problems pose significant challenges in the field of data mining. The skewed distribution of classes in imbalanced datasets often leads conventional classification methods to neglect the importance of minority classes, favoring the majority ones. In this paper, we propose an imbalanced complemented subspace representation model with adaptive weight learning to address imbalanced classification challenges. This approach incorporates a novel regularization technique and an adaptive weighting mechanism. The regularization technique integrates a complemented subspace term based on space theory into the efficient collaborative representation-based classification (CRC) framework, enhancing the overall accuracy of existing CRC-based methods. Furthermore, it takes into account both intra-class and inter-class density information to assign greater weights to minority classes. This highlights the contribution of minority classes and mitigates bias towards majority classes. Additionally, it is demonstrated that the proposed model can be efficiently solved with a closed-form solution. Extensive experiments conducted on diverse imbalanced datasets showcase the superiority of our method over most state-of-the-art imbalanced classification algorithms. • A complemented subspace regularization term is introduced into CRC. • An adaptive weight learning strategy is present. • The closed-form solution is provided to ensure the efficiency of our model. • Experimental results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

The goal of pansharpening methods is to complement the spectral and spatial information contained in Multi-spectral (MS) and panchromatic (PAN) images to obtain the desired High-resolution multispectral (HRMS) image. The existing majority of pansharpening methods either extract feature information separately from the MS image and PAN image, or extract feature information after concatenating the MS image and PAN image. However, the entire extraction process lacks the utilization of complementary information and tends to generate redundant information, thereby leading to the loss of certain important information during the extraction process, which in turn affects the overall performance. In order to better utilize the complementary information between the MS image and PAN image and enhance the interpretability of the network, we propose the Deep Unfolding Convolutional-Dictionary Network (DUCD) for pansharpening in this paper. This network fully integrates complementary information between the MS image and PAN image to generate the final fused image. The entire network structure consists of two parts: The encoder and the decoder. In the encoder part of the network, we clarify the common and unique feature information between MS and PAN images by constructing an observation model. Simultaneously, we use the approximate gradient algorithm to continuously optimize the model and iteratively unfold it into a deep network structure. In the decoder part of the network, we concatenate the obtained common and specific information from MS and PAN images and pass them through convolutional and activation layers. Subsequently, they are input into the introduced Frequency Domain-based Transformer (FDT) module and an information-lossless inversible neural network(INN). This provides a more efficient method for establishing long-range dependency relationships between feature extraction and feature fusion. To demonstrate the effectiveness of our proposed method, we conduct extensive experiments on three benchmark datasets QB, GF2 and WV3. Experimental results show that our method outperforms the current SOTA Pansharpening methods in terms of performance. • Convolutional-Dictionary Network, Pansharpening. • Prior knowledge, Proximal gradient algorithm, strong interpretability. • Inversible neural network, Attention mechanism. [ABSTRACT FROM AUTHOR]

To enhance RUL prediction accuracy and uncertainty quantification, numerous methods have been developed, including model-based, data-driven, and hybrid approaches. However, model-based approaches struggle with complex relationships and uncertainties. Data-driven methods might overlook prior knowledge and struggle with limited data. Hybrid models for RUL prediction face two key challenges: inadequate use of physical information and difficulty in accurately quantifying uncertainty. Aiming at the problems of non-linearity, small sample sizes, and the absence of uncertainty quantification in RUL prediction, this paper introduces a hybrid method aimed at achieving RUL prediction and uncertainty quantification in few-slot scenarios. In this study, a hybrid approach that combines model-based approach and data-driven approach is proposed to achieve accurate RUL prediction. The uncertainty is measured based on a Bayesian framework. Specifically, the proposed method combines the degradation trend model using a double-exponential degradation model (DEDM), and the degradation fluctuations is predicted by a Gated Recurrent Unit (GRU) network to achieve point estimation of the RUL. Subsequently, an ensemble learning method is adopted to integrate the different modules using a Bayesian neural network (BNN) for uncertainty quantification. The applicability and effectiveness of the proposed method is investigated through case studies conducted on the three lithium battery datasets. The comparative analyses are also conducted with commonly used EMD-based approaches. Experimental results demonstrate that the proposed method has good performance in both data leakage and non-leakage scenarios and is more effective than individual methods to achieve accurate RUL prediction under small sample datasets. Finally, this study dedicates to integrate physical models and data-driven models to address the challenge of data drift in future research. [ABSTRACT FROM AUTHOR]

This paper tackles a flexible job shop scheduling problem with extra resource constraints (FJSP-ERC) which arises in the practical context of aircraft manufacturing. The challenge is to schedule operations on identical computer numerical control (CNC) machining centers, considering the simultaneous availability of machines and tools. We describe the FJSP-ERC as a mixed integer linear programming (MILP) model and then propose an efficient meta-heuristic algorithm ABC II to solve the scheduling problem. This is a novel structured artificial bee colony algorithm incorporated with problem-specific local improvement strategies organized by Adaptive Large Neighborhood Search (ALNS). After applying the initialization techniques to the solution, the main structure of the algorithm is designed in two stages. In the first stage, all machining operations of a part are taken as a whole in order to find some near-optimal job order. The solutions obtained in the first stage will then serve as a warm-up for the second stage, where the operations are treated as independent individuals. After preliminary parameter tuning, comprehensive computational experiments were conducted to verify the effectiveness of the proposed solution approach by comparing with the solutions obtained by five different algorithms and CPLEX. The results show that the proposed ABC II significantly outperforms other methods in terms of efficiency and effectiveness. • A dual-resource constrained flexible job-shop scheduling problem is studied. • An efficient meta-heuristic algorithm is proposed to solve the problem. • The algorithm incorporates a problem-specific local improvement strategy. • Extensive computational experiments have been conducted to verify the algorithm. [ABSTRACT FROM AUTHOR]

The online bin packing problem is a well-known optimization challenge that finds application in a wide range of real-world scenarios. In the paper, we propose a novel algorithm called FuzzyPatternPack(FPP), which leverages fuzzy inference and pattern-based predictions of the distribution of item sizes in online bin packing. In comparison to traditional heuristics like BestFit(BF) and FirstFit(FF), as well as the more recent PatternPack(PaP) and ProfilePacking(PrP) algorithm based on online predictions, FPP demonstrates competitive and superior performance in solving various benchmark problems. Particularly, it excels in addressing problems with evolving distributions, making it a promising solution for real-world applications where the item sizes may change over time. This research unveils the promising potential of employing fuzzy logic to effectively address uncertainty in scheduling and planning problems. • Proposed algorithm utilizes pattern extraction and handles uncertainty effectively. • Employment of a fuzzy classification system adds flexibility in modeling ambiguity. • Superior performance and robustness were seen under evolving input distributions. [ABSTRACT FROM AUTHOR]

Anomaly detection in time series data is crucial for many fields such as healthcare, meteorology, and industrial fault detection. However, traditional unsupervised time series anomaly detection methods suffer from biased anomaly measurement under contaminated training data. Most of existing methods employ hard strategies for contamination calibration by assigning pseudo-label to training data. These hard strategies rely on threshold selection and result in suboptimal performance. To address this problem, in this paper, we propose a novel unsupervised anomaly detection framework for contaminated time series (NegCo), which builds an effective soft contamination calibration strategy by exploiting the observed negative correlation between semantic representation and anomaly detection inherent within the autoencoder framework. We innovatively redefine anomaly detection in data contamination scenarios as an optimization problem rooted in this negative correlation. To model this negative correlation, we introduce a dual construct: morphological similarity captures semantic distinctions relevant to normality, while reconstruction consistency quantifies deviations indicative of anomalies. Firstly, the morphological similarity is effectively measured based on the representative normal samples generated from the center of the learned Gaussian distribution. Then, an anomaly measurement calibration loss function is designed based on negative correlation between morphological similarity and reconstruction consistency, to calibrate the biased anomaly measurement caused by contaminated samples. Extensive experiments on various time series datasets show that the proposed NegCo outperforms state-of-the-art baselines, achieving an improvement of 6.2% to 26.8% in A rea U nder the R eceiver O perating C haracteristics (AUROC) scores, particularly in scenarios with heavily contaminated training data. • Unsupervised time series anomaly detection under data contamination. • Calibrating the biased anomaly measurement by exploiting the negative correlation. • Normal samples from a learned Gaussian distribution to model negative correlation. • Single forward propagation enables anomaly detection using the trained autoencoder. [ABSTRACT FROM AUTHOR]

Knowledge graph (KG) modeling constructs a connected network of hazard/fault events by drawing on historical reports, helping extract risk factors and propagation features in railway signaling safety. For the huge graph structure of the knowledge system, efficiently and accurately transforming the event information with text for risk level prediction is the crucial topic of this paper. To establish a quantitative risk assessment method based on KG modeling, we innovatively introduce text clustering technology to intelligently divide the entity short text data set in the KG, assign standardized entity names to the cluster partitions, and then complete the calculation and analysis according to the characteristic parameter formula, greatly reducing the labor and time consumption of data annotation and approximate text repetitive processing. Significantly, a two-stage clustering ensemble algorithm (TSCEA) integrating base clusterer optimization and hierarchical clustering prediction is proposed, whose innovative approach lies in describing sample similarity by the co-association matrix, while considering the contribution discrepancy of samples for decision-making. Specifically, Stage One selects and optimizes various base clusterers with different method kernels, while Stage Two emphasizes the contribution discrepancy of the cluster core and the cluster halo to make the final clustering decision, with the ensemble strategy serving as the bridge between these two. The KG established on field investigation is used to complete the experiment and analysis of the novel algorithm. Another clustering ensemble algorithm (based on a direct weighting strategy) and each base clusterer are applied to verify clustering performance, while the evaluation depends on external indicators. The results indicate that the proposed clustering ensemble algorithm outperforms others in various indicators, significantly improving clustering accuracy and robustness. [ABSTRACT FROM AUTHOR]

• Informed fundamental diagram knowledge into a newly proposed data-driven model. • Applied and evaluated the proposed PI-SGTGCN model through real-world dataset. • Investigated the physical interpretation of the dynamic graph adjacency matrix. Accurate and fine-grained traffic state prediction has always been an important research field. For long-term traffic flow prediction, the high-dimensional and coupled traffic feature evolution patterns are deeply recessive, posing challenges in effectively characterizing and modeling them. This paper proposed a novel spatial–temporal graph convolution network model with traffic Fundamental Diagram (FD) information informed. The model decouples the high-dimensional spatiotemporal relationships in the transportation network and fully leverages the physical evolution laws of traffic states. First, the Graph Convolutional Network (GCN) with a spatial attention mechanism was proposed to capture spatial relations of the road network. The mechanism can better represent the spatial dynamics of the graph adjacency matrix in GCN. Second, this study injected prior physical knowledge into the graph adjacency matrix. This process was achieved by embedding characteristics of FDs from historical traffic data on the diagonal of the matrix, by which the propagation pattern of traffic states in road network could be considered. Third, to further catch the time dependence of the road network, the Gated Recurrent Unit (GRU) structure and the Transformer encoding structure were employed to locally and globally reform traffic state time sequences. Finally, experiments on a revised traffic dataset demonstrated that the proposed method consistently outperforms other baselines regarding Mean Absolute Error and Root Mean Square Error across all cases. Moreover, it achieved the optimal Mean Absolute Percentage Error in the 30- and 60-minute prediction tasks. This study shows a novel solution to inform traffic physical laws into data-driven state prediction models, and the reliability of the proposed method in long-term prediction offers valuable support for improving traffic management and alleviating traffic congestion. [ABSTRACT FROM AUTHOR]

Multi-object tracking (MOT) detects multiple targets in an image and assigns a unique identifier to each target. However, challenges such as rapid motion, occlusion, and camera motion in the tracking scene may lead to identity switches (IDs) and missing trajectory problems, which degrade the performance of the tracker. To address these issues, this paper presents an MOT algorithm based on an interactive attention network and adaptive trajectory reconnection. First, an interactive attention network was created to learn the features for two different tasks of detection and tracking to alleviate feature conflicts in order to extract sufficient feature information. A new cost matrix was then designed to fuse the motion and feature information, thereby reducing the number of IDs. Meanwhile, the extreme gradient boosting reconnection module was used to achieve adaptive trajectory reconnection and reduce missing trajectories. The proposed algorithm achieved 61.5 % and 55.4 % HOTA using the standard MOT17 and MOT20 datasets, respectively. In comparison to FairMOT, our algorithm showcased notable enhancements of 3% and 1.6% on these datasets. Furthermore, when compared to state-of-the-art algorithms, the proposed algorithm demonstrated superior tracking performance. [ABSTRACT FROM AUTHOR]

Advanced Process Control (APC) has become an increasingly pressing issue for the semiconductor industry, particularly in the new era of sub-5 nm process technology. To minimize human input in analyzing equipment state and output quality, Virtual Metrology (VM), one such incredibly reliable and resource-saving APC tool built on artificial intelligence and machine learning techniques, was introduced as an aide to real metrology and is aimed at predicting semiconductor product quality based on equipment status/process variables and sampled actual metrology. In this paper, VM efforts for semiconductor manufacturing applications are, for the first time, systematically reviewed. Based on comprehensive mining of literature, a generic architecture for semiconductor VM is presented, and the general requirements are discussed. Moreover, the state-of-the-art VM works for prominent processes involved in semiconductor manufacturing are surveyed, and the unique contributions of those VM predictive works are summarized and compared. Nevertheless, VM is still in its infancy stage, and there are significant hurdles that prevent wider VM implementation and acceptance in semiconductor industry. In this end, a critical analysis is provided to reveal the research gaps and discuss the challenges, such that further research can be simulated in the future. It is hoped that this work could illuminate researchers to understand the needs and future directions towards developing VM technology for semiconductor processes. [ABSTRACT FROM AUTHOR]

Data quality estimation has become an important research axis in applications when defining useful information is required. Determining useful information is an essential task in the learning process. One important aspect thereby is to find optimal and sufficient information that has a good quality and which is complimentary to improve the performance of the decision-making system. In this paper, a survey of data quality is operated in the possibilistic framework. The main objective of this work is the development of a possibilistic approach that aims to extract useful information from imperfect knowledge. The new method consists of two main steps, the classification of feature quality and the determination of the optimal feature subset. The optimal feature subset is deduced according to the feature classification technique and the feature complementarity. To show the performance of the proposed approach, the new method has been evaluated, firstly, on a synthetic dataset, and then on different benchmark databases. Later, the new method is evaluated on two real databases to gain a better insight into the performance of this method. Experiments showed the effectiveness of the proposed method in extracting useful information using the optimal feature subset. Experimental results illustrate significant accuracy rates compared with different earlier methods, especially when the system complexity increases. • This work aims to develop a possibilistic approach for extracting useful data. • Our method involves classifying features based on their quality and defining the optimal subset • Our method is evaluated on synthetic dataset, benchmark databases and two real databases. [ABSTRACT FROM AUTHOR]

Feature selection has a prominent role in high-dimensional datasets to increase classification accuracy, decrease the learning algorithm computational time, and present the most informative features to decision-makers. This paper proposes a two-stage hybrid feature selection for high-dimensional medical datasets: Maximum Pattern Recognition - Multi-objective Discrete Evolution Strategy (MPR-MDES). MPR is a rapid filter ranker that significantly outperforms existing frequency-based rankers in recognizing non-linear patterns, effectively eliminating a majority of non-informative features. Then, the wrapper Multi-objective Discrete Evolution Strategy (MDES) uses the remaining features and obtains sets of solutions which are automatically presented to decision-makers. The experiments conducted on large medical datasets demonstrate that MPR-MDES achieves considerable improvements compared to state-of-the-art methods, in terms of both classification accuracy and dimensionality reduction. In this sense, the proposal successfully performs when presenting informative feature sets to decision-makers. The implementation is available on https://github.com/KhaosResearch/MPR-MDES. [Display omitted] • Maximum Pattern Recognition (MPR) is proposed as a frequency-based filter ranker. • Multi-objective Discrete Evolution Strategy (MDES) is proposed as a wrapper method. • The proposed MPR-MDES selects the best feature sets in the Pareto front. [ABSTRACT FROM AUTHOR]

Augmented reality (AR) and Artificial Intelligence (AI) are technologies pioneers in innovation and alteration in several domains. AR allows the creation of an entirely new and interactive experience for users. However, there are several drawbacks in developing AR applications, such as the marker identification process and the creation of content itself. These are very time-consuming procedures and require ad-hoc development. The advantages of using AI to solve AR limitations have recently been explored in literature. Motivated by these findings, in this paper it is proposed DeepReality, a software toolkit plug-in for Unity 3D. It is conceived for allowing developers to integrate any Deep Learning (DL) models into Unity, through AR Foundation and Barracuda inference engine. DeepReality is aimed at simplifying and streamlining the usage of DL models in conjunction with AR. As such, users skilled in Unity and DL can easily create mobile applications (iOS and Android) to: extract visual features of real-world objects (framed with the device camera) via DL; Show on-screen content on top of those real-world objects, via AR. DeepReality performs object semantic processing within the scene, and extended semantic effects for incongruent objects, overcoming the environmental tracking, which is feature-based. In order to test DeepReality usability, experiments have been performed on the execution time and memory usage data, demonstrating the feasibility and possibility of integrating and using DNNs models in mobile applications for AR. The complexity analysis confirms that DeepReality can be completely executed on mobile devices. DeepReality is also open-source and it is freely available in the Unity asset store. By fostering accessible AI-AR integration, DeepReality addresses key shortcomings in existing approaches, encapsulating contributions such as versatile DL integration, open-source accessibility, operational validation, and comprehensive metrics analysis. DeepReality empowers developers to transcend boundaries, enriching AR applications with AI's transformative potential. Our proposed framework fosters benchmarking, comparison, and a future harmonised by AR-AI synergy. [Display omitted] • DeepReality is an open-source toolkit, freely available in the Unity asset store. • DeepReality integrates Deep Learning models for streamlined mobile apps. • DeepReality leverages AR Foundation and Barracuda inference engine. • It demonstrates efficient execution and memory usage in mobile AR. • Complexity analysis confirms that it can be fully executed on mobile devices. [ABSTRACT FROM AUTHOR]

This paper puts forward an adaptive saturated threshold event-triggered control (STETC) scheme with global transient and steady-state performance assurance for nonlinear Markov jumping systems. Initially, the dead-zone model is characterized by an adaptive approximation model while integrating the property of the Nussbaum function. Then, an improved adaptive global preassigned performance control scheme is developed under the command-filtered backstepping control framework, where a second-order filter is employed to tackle the curse of dimensionality faced by the iterative derivation and a novel error compensation signal is constructed with consideration of the characteristics of dead-zone output and preassigned performance to eliminate the potential effects caused by filter errors. Drawing inspiration from the preceding ETC results, a STETC tactic fusing the dynamic parameter is proposed to economize the communication costs, and the control signal is encoded and decoded as 0 or 1 bits to decrease the bandwidth consumption simultaneously. The reported STETC method guarantees that overall signals in the closed-loop system keep bounded in probability while the tracking error rigorously evolves within the prescribed range without dependent on initial values. Ultimately, two illustrative examples are implemented to check the flexibility and practicality of the reported control solution. • Control design is flexible consuming less bandwidth resources in comparison to existing PPC and ETC. • Differential calculation of the virtual control signal avoid the curse of dimensionality. • Improved error compensated signal drastically eliminates the filter errors. • STETC method guarantees that overall signals keep bounded in probability. • The tracking error rigorously evolves within the prescribed range regardless of the initial value. [ABSTRACT FROM AUTHOR]

For online public opinion events, the misconduct of opinion leaders can easily lead to the spread of negative public opinion, which in turn can adversely affect real society. In order to minimize this adverse impact to the greatest extent, this paper uses social network analysis to explore the attributes of individuals, features of network structure, and social relationships between decision makers (DMs). It constructs the structural system of evaluation criteria and a multiple criteria decision model to comprehensively and reasonably identify opinion leaders. It additionally considers the importance of criteria and the interaction among them. The hierarchical structure is combined with the evaluation level to construct a precise structural system of criteria. To handle the interaction, the Choquet integral is applied as the preference model. Based on the disaggregation principle, a generalized hierarchical level dependent Choquet integral is developed to reproduce additional preference information provided by decision analysts (DAs) and aggregate evaluation values of DMs on multiple interacting criteria. Then, the relevant indices of this integral and the preference information are applied to robust ordinal regression to mine rich preference relations among DMs. Furthermore, the hierarchical level dependent Choquet integral-driven multiple criteria decision model is proposed to rank DMs and identify opinion leaders. Finally, a numerical example and two real datasets validate the effectiveness and advantages of the proposed decision model. • By mining social networks, we construct a structural system of evaluation criteria. • The interaction between criteria is considered in the decision-making process. • A generalized Choquet integral is defined from two dimensions. • Additional preference information provided by decision analysts is considered. • A decision model is constructed to identify opinion leaders. [ABSTRACT FROM AUTHOR]

Nowadays information technology advances allow the collecting and storage of large complex datasets in many areas. Modeling and forecasting interval-valued time series (ITS) has drawn much attention over the last two decades because interval-valued observations contain more information than point-valued observations over the same period and remove undesirable noises in high-frequency data. However, most work mainly focuses on modeling a linear univariate ITS or bivariate point process. This paper proposes nonparametric regression models for interval-valued time series with imposing constraints, e.g., monotonicity. This setting with a monotonic constraint is consistent with the existing literature, which focuses on incorporating valuable empirical information in modeling and forecasts. Two constraint estimators are developed and asymptotic properties are established. Monte Carlo simulation is conducted to show the finite sample performance. An empirical application to equity premium documents that the proposed model yields a better forecast performance than some popular models in the literature. • First applies the parsimonious nonparametric spirit to interval time series. • Provide an algorithm obtaining the constraint interval estimators with bagging. • Derive the consistency and limit distribution of the proposed estimators. • Outperforms existing methods in the interval predictive model for stock returns. [ABSTRACT FROM AUTHOR]

Imbalanced data severely hinder the classification performance of learning-based algorithms and attract a great deal of attention from researchers. The undersampling method of selecting the majority class from samples through the prototype is one of the most common techniques to address class imbalance. However, traditional undersampling-based methods inherently lead to information loss. Meanwhile, they tend to perform undersampling for the majority class using distance-based locality methods, resulting in completely ignoring the density of the minority class samples. To this end, this paper proposes a novel undersampling method that incorporates the density distribution information of the minority class. Specifically, the probability density distribution of the minority class samples is learned by kernel density estimation, and the majority class samples located in the high-density band of the minority class are removed through filtering. Based on this, sampling fitness is proposed to evaluate the desirable value of each majority class sample to select information-rich samples. The research was carried out in 25 publicly available datasets and compared with state-of-art methods. The results show that our approach offers clear superiority. • The method learns the distribution of the minority class with time complexity O (n l o g n). • The sampling fitness combined with the roulette operator reduces information loss. • The experiments confirmed the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Recently, researchers have been extensively exploring the immense potential of Q-Star. However, the available resources lack comprehensive information on this topic. Despite this, a Q-table, an uncomplicated lookup table containing actions and states, is often seen as a mere data structure for tracking. This overlooks the vast amount of knowledge that can be derived from it through visualization. The Q-learning algorithm utilizes this table to update values and determine the highest anticipated rewards for actions in each state. However, instead of relying solely on complex reward functions for algorithm development, leveraging the existing knowledge within the Q-table would be highly beneficial. Incorporating this valuable information into the algorithmic framework can minimize the need to develop intricate reward functions. This paper proposes an expected-mean gamma-incremental Q approach to tackle the challenges of convergence speed in an uninformed search reinforcement learning (RL) algorithm and the issue of path optimality in path planning problems. The gamma-incremental RL method revolves around adjusting the weight of the future value by considering the level of exploration. It enables the robot to receive preference feedback, either near-term reward or long-term reward, based on the frequency of the visited state. Meanwhile, the expected-mean technique uses the information of the robot's turning actions to update the Q-target. By consistently incorporating valuable insights from the Q-table, the algorithm can gradually enhance its understanding of the available information, resulting in more efficient decision-making. The experiment results indicate that the proposed algorithm accelerates the convergence rate, outperforming the baseline Q-learning by up to 2 times. It addresses the challenge of robot path planning by prioritizing promising solutions, resulting in near-optimal outcomes with higher total rewards and enhanced learning stability. [ABSTRACT FROM AUTHOR]

The Baltic Dry Index (BDI) is an essential index to measure international dry bulk shipping freight, which can reflect global economic changes to a certain extent. Accurate forecasting of BDI supports shipping market participants in grasping risks and making scientific decisions. Based on the Prophet model, this paper considers the impact of multi-dimensional significant events related to the shipping industry and conducts BDI forecasting research. Firstly, we simulate the most momentous events in the world in recent years, namely the 2008 Global Financial Crisis and the 2019 New Crown Epidemic, and utilize the Prophet model to decompose the BDI sequence into three parts: trend, seasonality, and momentous event shocks. Secondly, we extensively collect other multi-dimensional significant event uncertainty indexes to establish a "significant event database". The Maximal Information Coefficient and Boruta methods were employed to extract the uncertainty index particularly correlated with BDI as an exogenous variable for forecasting. Then, we employ the K-Shape method to cluster exogenous variables and explore the combined sense of clustering. Finally, we utilize the Prophet model to forecast BDI in stages. It discusses the influence of exogenous variables and their cluster combinations on the forecasting effect individually and sequentially. Empirical results show that considering the two momentous events of the Financial Crisis and COVID-19 can remarkably improve the accuracy of BDI forecasting. In addition, the study of exogenous variable significance found that during the Financial Crisis, economic policy uncertainty in Europe and the Americas greatly impacted BDI forecasting. During COVID-19, global and developed economic policy uncertainty was noteworthy in the BDI forecasting. The comparative experimental results show the Prophet model has an exemplary forecasting result and strong robustness. It also performs excellently in model generalization and interpretability. This paper proposes a reliable and advanced algorithm for shipping freight rate index forecasting, which has noteworthy reference value for shipping market participants to make investment decisions and risk avoidance. [ABSTRACT FROM AUTHOR]

Surface roughness is a critical parameter for quantifying the surface quality of a workpiece. Accurate surface roughness prediction can significantly influence the overall quality of the final components by reducing costs and enhancing productivity. Although various prediction methods have been explored in previous research, less attention has been given to explainable prediction methods for surface roughness. This paper proposes a surface roughness prediction model based on the Differential Evolution (DE) algorithm with ensemble learning. It aims to elucidate the intrinsic correlation between processing parameters and surface roughness values in Multi-Jet Polishing (MJP) using explainable analysis methods. The proposed Ensemble Regression with Differential Evolution (ERDE) algorithm comprises two main modules: data processing and analytics, and ensemble model prediction. These modules investigate the surface roughness of MJP from the data and model levels, respectively. To validate the effectiveness of ERDE, MJP experiments were conducted on three-dimensional printed components of 316L stainless steel. The experimental data indicated that ERDE outperforms other existing algorithms, reducing the mean absolute percentage error by approximately 42 %. [ABSTRACT FROM AUTHOR]

Intelligent Decision Support Systems (DSS) have gained considerable interest within the field of construction engineering through the utilization of Artificial Intelligence (AI) and Machine Learning (ML) methodologies. These systems possess the capacity to enhance decision-making processes and optimize the results of projects. Nevertheless, it is imperative to conduct a thorough and inclusive examination that incorporates and evaluates the various methodologies employed within this particular discipline, thereby bridging the existing void in research. The current state of research in the field of AI and ML in construction engineering is characterized by a dearth of comprehensive reviews that encompass the wide array of methodologies utilized. Although certain studies have delved into specific facets of this subject, there remains a novelty and research gap in terms of a holistic examination of the topic. The objective of this review is to conduct a comprehensive analysis of AI and ML methodologies in the field of construction engineering, with a specific emphasis on their practical applications, advantages, and constraints. The study also ascertains potential areas for future research and improvement in the domain of Intelligent DSS. This study employed a rigorous approach that involved an extensive review of scholarly literature and empirical investigations from 2001 to June 2023. The findings of the analysis indicate a noticeable increase in the number of research papers focusing on Intelligent DSS within the field of construction engineering during the last twenty years. The field has witnessed the emergence of key research areas, namely the utilization of Internet of Things (IoT), explainable AI, supply chain optimization, sustainable construction practices, and human–machine collaboration. The results of this study hold significant implications for the construction industry. The incorporation of AI and ML techniques within Intelligent DSS can effectively tackle various issues such as cost overruns, project delays, and safety concerns. [ABSTRACT FROM AUTHOR]