Search

The transformer architecture with its attention mechanism is the state-of-the-art deep learning method for sequence learning tasks and has achieved superior results in many areas such as NLP. Utilizing the transformer architecture for the prediction of sequential time series such as financial time series has hardly been investigated in previous studies. In this research paper, the transformer architecture with time embeddings is used in foreign exchange (FX) trading, the world's largest financial market, and tests its suitability. A systematic comparison is made between transformer and benchmark models. It also examined which influence multivariate, cross-sectional input data have on the forecasting performance of the various models. The goal of the paper is to contribute to the empirical literature on FX forecasting by introducing a transformer with time embeddings to the forecasting community and assessing the accuracy of corresponding models by forecasting exchange rate movements. Empirical results indicate the suitability of transformer models for FX-Spot forecasting in general but also evidence the need for transformer models for multivariate, cross-sectional input data to outperform other state-of-the-art neural networks such as LSTM. [ABSTRACT FROM AUTHOR]

The users' click prediction holds significant commercial value in online purchase platforms. Currently, some session-based interest extraction models overlook the impact of temporal interval factors on the distribution pattern of behaviors within a session. To address the above issue, this paper designs a module named session-based time-aware gated recurrent units (ST-GRU) to integrate the temporal interval factors into session sequence. The ST-GRU module utilizes a memory decay function, enabling the simulation process to identify the users' memory changes within each session. Subsequently, to account for the interdependence between different sessions, this paper introduces bi-directional gated recurrent units (Bi-GRU) with an attention mechanism to learn interaction relations of user interests. Additionally, for high-dimensional potential features, this paper integrates above modules and proposes a method called time interval aware deep session interest network (TIAE-DSIN) model. Correspondingly, comparative experiments are carried out on three public datasets, and the obtained results indicate that the AUC of TIAE-DSIN model is superior to other session interest extraction models. [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]

Sine Cosine Algorithm(SCA) is a population-based optimization algorithm, to find the optimal solution. However, SCA has problems such as premature convergence, insufficient solution precision for high-dimensional functions, and slow convergence speed. To solve the problems above, this paper proposes a multi-strategy-based Adaptive Sine Cosine Algorithm (ASCA). Firstly, a more uniform initial population is generated by the Halton sequence so that the initial population covers the entire search space to maintain the diversity of the initial population. Secondly, the adaptive grading strategy is adopted to sort according to the fitness value, and the population dynamics are divided into 4 grades: excellent, good, medium and poor. For the purpose of improving the convergence accuracy of the algorithm and enhancing the ability to jump out of the local optimum, hybrid mutation and elite guidance methods are applied to different levels of populations for perturbing mutations. Finally, in order to improve the convergence speed of the algorithm, a dynamic opposition-based learning global search strategy is proposed. The ASCA is tested on a set of 20 functions in low- dimensional and high-dimensional, and the improved algorithm is compared with Particle Swarm Optimization (PSO), Backtracking Search Algorithm(BSA), Genetic Algorithm(GA)and other improved Sine Cosine Algorithms. The results show the improved convergence accuracy and speed of the ASCA. Moreover, the ASCA proposed in this paper is applied to engineering optimization design. The solution results show that the ASCA is better than other algorithms in superiority-seeking ability, and can effectively solve the optimization problems in engineering. [ABSTRACT FROM AUTHOR]

Selecting weighting factors for H-infinity controller requires tones of knowledge and experience without guaranteeing obtaining the best results. This paper proposes novel idea for H-infinity controller synthesis using metaheuristics (MHs). The optimisation problem for the H-infinity controller synthesis is posed to find the weighting factors to optimise the control performance subject to stability and control handling constraints. A number of established MHs are used to solve the problem while their performance are investigated. The results indicate that the Artificial Hummingbird Algorithm and Grey Wolf Optimizer is the most efficient algorithm for the optimisation problem of H-infinity flight control design. Based on this study, the performance of several MHs on solving the H-infinity flight control design are examined while the optimum weighting factors for H-infinity flight controller are obtained. This paper is said to be a based line of studying in easy and efficient way for H-infinity controller synthesis using MHs. [ABSTRACT FROM AUTHOR]

• This paper studies the impact of oil shocks on systemic risk of G7 stock markets. • We construct a risk spillover network among G7 stock markets by TVP-VAR. • The results indicate that the impact of oil supply shock is insignificant. • Demand shock contributes the most to systematic risk in the short term. • G7 stock markets play a role as receiver and all oil structural shocks as emitter. In this paper, we delve into the critical role of oil shocks in influencing the systematic risk of G7 stock markets—a concern of paramount importance given the interconnectedness of global economies and the pivotal role of energy markets. We employ Delta Conditional Value at Risk (ΔCoVaR) and Marginal Expected Shortfall (MES) to measure the systematic risk of G7 stock markets due to volatility in the oil market. By decomposing oil price change into oil supply shocks, aggregate demand shocks, and oil-specific demand shocks using a structural vector autoregression model, we offer a more granular perspective to investigate the time-varying effects of oil price fluctuations on the systematic risk of G7 stock markets. The results indicate that the impact of oil supply shock is insignificant compared with aggregate demand shock and speculative demand shock. Speculative demand shock contributes the most to systematic risk in the short term, but their impact declines as the number of periods increases. In the long term, the biggest impact on systematic risk is aggregate demand shock. Additionally, we construct a network among G7 stock markets and oil structural shocks based on time-varying spillover and the empirical results show that G7 stock markets play a role as receiver and all oil structural shocks as emitter. Besides, Japan is the country in G7 countries most affected by oil shocks. [ABSTRACT FROM AUTHOR]

In recommender system, the proportion of interacted items with users is extremely sparse compared to the total number of items. This data sparsity problem particularly affects collaborative filtering methods. Even in modern collaborative filtering recommendation models based on deep learning, effectively acquiring more neighbor information and exploring how to utilize this information efficiently remains a promising research area. This paper not only explores heuristic algorithms for neighbor selection but also extends the application of neighbor selection to the GAN framework and negative sampling. To capture user neighbors that contain more potential feature information, this paper proposes a neighbor strategy that integrates explicit and implicit user information. It aggregates reciprocal neighbors of users based on the fusion of their explicit and implicit information, aiming to capture user preference information through neighborhood information. Furthermore, by designing an MRNGAN model based on a twin-tower generator, this paper successfully embeds user neighborhood information as feature embedding into the generator of GAN. In addition, this paper also proposes a heuristic negative sampling mechanism in the recall phase. It uses explicit and implicit information to fuse the nearest neighbors of items with the farthest neighbors of users. Negative samples that contain user neighborhood information are embedded into the discriminator of MRNGAN. The deep relationships between nearest and farthest neighbors are explored through the adversarial training of GAN, and their impact on recommendation performance is validated. The experimental results on three real-world datasets show that the MRNGAN model significantly improves the accuracy of Top-N recommendation. [ABSTRACT FROM AUTHOR]

Hierarchical text classification (HTC) aims to classify a text into multiple categories organized in a hierarchical structure. The state-of-the-art HTC methods usually employ graph networks, where label graphs are constructed and label representation is learned to interact with text representations for classification. In general, label graphs are built on the intrinsic label hierarchy, label semantic similarity, or label co-occurrence. Such graphs have been proven to be effective, but they only exploit knowledge from training data or simple label descriptions, without considering the vast external knowledge in the open sources. Actually, external knowledge from open sources could bring in complementary information to enhance the label graph's representation power. Motivated by the above considerations, we explore the use of external knowledge for improving HTC in this paper. We categorize knowledge into micro-knowledge and macro-knowledge, which are defined as the fundamental concepts related to a single class label and the correlations among class labels, respectively. For tailor-made incorporation of the two types of knowledge into representation learning and classification, we propose Adaptive Micro- and Macro-Knowledge Incorporation for Hierarchical Text Classification (AMKI-HTC) model in this paper. The micro-knowledge incorporation helps capture class-relevant keywords in the text and hence produce discriminative representations, while the macro-knowledge incorporation improves the accuracy of label graphs. Finally, a confidence maximization fusion strategy is developed for adaptive aggregation of multi-view features. Extensive experiments on three benchmark HTC datasets demonstrate that AMKI-HTC consistently outperforms state-of-the-art models. • Conceptualize extensive external knowledge as micro-knowledge and macro-knowledge. • Aggregate micro- and macro-knowledge into original text features adaptively. • Construct text-knowledge graphs to emphasize discriminant information. • Simplify hierarchy-GCN as SH-GCN with improved performance. • Adaptively fuse features from multiple label graphs by confidence maximization. [ABSTRACT FROM AUTHOR]

As a novel and economical transportation way, ride-sharing has attracted more and more passengers and drivers to participate. How to match passengers with drivers efficiently has become a key issue. Specifically, drivers are usually heterogeneous with different costs, and they may behave strategically (e.g. reveal their private cost information untruthfully) in order to make more profits. Drivers' strategic behavior may lead to inefficient matching, which results in the loss of social welfare of ride-sharing platforms and drivers. In this paper, an incentive-compatible and efficient mechanism is proposed to solve this issue, which can match passengers with drivers and determine the payments to drivers in order to maximize social welfare while ensuring drivers reveal their cost information truthfully. Specifically, an order matching algorithm with branch and bound based route planning is designed to accelerate the matching process. Meanwhile, the payments to drivers are computed based on the second-pricing algorithm. In so doing, a second-pricing based ride-sharing mechanism (SPRM) is proposed, which satisfies incentive compatibility, individual rationality, budget balance and computational efficiency. Based on the real Manhattan taxi order data and vehicle fuel consumption data, extensive experiments are conducted to evaluate the proposed mechanism. The experimental results show that SPRM can guarantee drivers' profits and improve the ratio of drivers' participation and the ratio of served orders, and eventually achieve greater social welfare than four typical benchmark approaches, GPri, ND, mT-share and mdp. The research of this paper can provide useful insights for designing efficient ride-sharing system to maximize the social welfare of all participants in the real life. • An efficient mechanism to match orders with drivers is proposed. • A branch and bound based route planning method is used to accelerate the matching. • A second pricing based mechanism is proposed to compute the payments to drivers. • The proposed mechanism can outperform benchmark approaches in the social welfare. [ABSTRACT FROM AUTHOR]

Decision-making problem is a fundamental activity in human life every day. Regarding group decision-making, individuals have insufficient comprehension of the decision objects owing to the limited experience and knowledge and drawback the evaluation process. Therefore, the evaluation information is missing and the group cannot get the precise information for decision objects resulting in the generation of incomplete information systems. It is meaningful for individuals finding an approach to Leverage and tap into existing information. On the basis, the work presented in this paper focuses on group decision-making problems (GDM) with incomplete information. Under the framework of group decision-making, a GDM approach with an incomplete information system is presented combining the formal concept analysis and rough set theory. Firstly, we propose a concept called formal decision context and discuss the properties of the formal decision context, which could divide the incomplete information system into many cognitive units, and the definitions of cognitive units will be given. Then, the property and the relations of various cognitive units will be discussed. Additionally, the upper and lower approximation space under the formal decision context is founded considering the risk attitudes integrating fuzzy rough set and formal concept context. Considering the order relation of various cognitive units and decision objects, we introduce the dominance relation and the importance degree of each cognitive unit under the framework of formal decision context. Furthermore, a theoretical framework of the multi-criteria decision-making problem is presented and two models for the multi-criteria group decision-making problem are discussed combined with fuzzy rough set and formal decision context from two perspectives, including qualitative analysis and quantitative analysis. Finally, an illustrated example is applied to verify the validity and effectiveness of the proposed models. The contributions of this paper include two aspects. On the one hand, this paper provides a new perspective and paradigm considering MCGDM problems with the incomplete information system from the perspective of group consensus. On the other hand, this paper gives two approaches for group decision-making problems from sorting and set theory by the perspective of multi-granular rough set and group consensus. • A model of formal decision context with incomplete information to describe the cognitive situation. • An approach to MCDM problem combined rough set with formal decision context with incomplete information. • Two approaches to MCGDM problem from qualitative analysis and quantitative analysis. [ABSTRACT FROM AUTHOR]

Over the last twenty years, patient opinions of the received healthcare services have emerged as a crucial quality indicator and a valuable instrument for evaluating the service quality of health organizations. However, many surveyors still utilized uncertain information for conducting this evaluation process. Whereas, in the past few years, the issues of inconsistency, indeterminacy, and uncertainty in data have been growing and have become a matter of concern in dealing with decision-making issues. This paper proposes an improved RAFSI method based on a single-valued trapezoidal neutrosophic number (SVTraNN) as a multi-attribute framework for dealing with a healthcare service quality evaluation. The proposed framework consists of two features: a feature for determining numerical criteria weights involving the procedures of the Ordinal Priority Approach (OPA) and a feature for selecting the best polyclinic through contributing our new SVTraNN Harmonic and arithmetic mean to yield criterion functions in the RAFSI method. This paper then compares the results obtained by the proposed method with other SVTraNN decision-making methods. A comparative analysis and rank reversal testing of the improved method demonstrated that the multi-attribute framework proffers the option of capability and stability in overcoming inconsistency, indeterminacy, and uncertainty information efficiently during the healthcare service quality evaluation. [ABSTRACT FROM AUTHOR]

As one of fundamental problems in robotics, coverage path planning (CPP) requires the robot path to cover the entire workspace which has been employed in several essential applications such as cleaning robots, land mine detector, lawnmowers and automated harvesters. Unlike most of existing studies considering the CPP problem under a unrealistic assumption of infinity energy, this paper takes the battery limitation of robots into account. This poses a significant challenge for enabling an efficient coverage path while satisfying the limited energy constraint, even in a priori known environment. Handling this challenge, we propose a BWave Framework that guides the robot to move following an improved Boustrophedon-like motion and a special area prioritization and especially, to return a charging station effectively before an exhausted energy. To that end, a weighted map is applied for recognizing the special areas, namely trap regions, and governing the robot to enter these fields in priority. Moreover, a return matrix, which forms the shortest-path tree from the charging station, is pre-computed to not only validate the energy requirement, but also speed up the calculation process of return and advance paths during the robot's operation. We then evaluate BWave Framework extensively in various scenarios in both generated and real-life indoor maps datasets. The results show that compared to typical baseline methods, BWave Framework achieves the CPP solution at a significantly accelerated running time, namely 51.5 to 72.8 times lower for generated maps, and 44.8 to 255 times for real maps, while reducing the total path length by 2.4%–17.6% and by 2.9%–18.5%, respectively. Moreover, the proposed method also outperforms the baselines in terms of overlap rate, number of returns and accounts for a lower number of deadlocks. • This paper tackles coverage path planning with energy constraints. • It introduces BWave, a novel framework for complete coverage. • BWave has two phases: environment knowledge extracting and complete coverage. • BWave is evaluated in various scenarios and compared with state-of-the-art methods. • BWave performs well in environments with many trap areas. [ABSTRACT FROM AUTHOR]

• An efficient slime mould algorithm PPMSMA with 3 improved strategies is proposed. • A set of theoretical and experimental analysis methods are proposed and used. • The time complexity, spatial complexity and convergence of PPMSMA are proved. • Multiple experimental methods are used to test the performance of PPMSMA. • The application ability of PPMSMA is tested by solving engineering problems. Metaheuristic intelligent optimization algorithms are effective methods for solving high-dimensional nonlinear complex optimization problems. The slime mould algorithm is a novel intelligent optimization algorithm proposed in 2020. However, the basic slime mould algorithm still has some shortcomings, such as slow convergence rate, easy to fall into local extremum, and unbalanced exploration and development capability. To further improve and expand the optimization ability and application scope of the slime mould algorithm, and enhance its performance in solving large-scale complex optimization problems, this paper proposes a slime mould algorithm (PPMSMA) based on Gaussian perturbation and phased position update, positive variation, and multi-strategy greedy selection. Firstly, Gaussian perturbation and phased position update mechanism are introduced to avoid the difficulty of the algorithm to jump out of the local extrema and also to speed up the convergence of the algorithm. Then, a positive variation strategy based on the sine cosine mechanism is introduced to move the variation of the population towards a better direction. Finally, a multi-strategy greedy selection mechanism is introduced, which effectively improves the search ability of the algorithm. The analysis and research on the optimization ability and performance of metaheuristic algorithms mainly include two aspects: theoretical analysis and experimental testing. Theoretical analysis has always been a relatively weak link in the research of metaheuristic algorithms, and there is currently no clear and effective method formed. For experimental testing, although there are more methods, they often lack systematization and adequacy. In this paper, a more complete, fine-grained and systematic approach to theoretical and experimental analysis is proposed. In the theoretical analysis part, the time complexity and spatial complexity of the PPMSMA algorithm are analytically proved to be the same as the basic slime mould algorithm, and the probability measure method is used to prove that PPMSMA algorithm can converge to the global optimal solution. In the simulation experiment section, the PPMSMA algorithm is compared with multiple sets of 10 representative comparison algorithms on the CEC2017 complex test function set suite for optimization accuracy analysis, Friedman comprehensive ranking analysis, average optimization rate analysis of PPMSMA relative to other algorithms, convergence curve analysis, and Wilcoxon rank-sum test analysis. To further examine the scalability of the improved algorithm in solving large-scale optimization problems, PPMSMA is compared with the above 10 comparative algorithms under 1000 dimensional conditions in the large-scale global optimization test set CEC2010, and the solution stability of each algorithm is analyzed through violin plots. The results show that the PPMSMA algorithm has significantly improved convergence performance, optimization accuracy, and solution stability in both high-dimensional and large-scale complex problems, and has significant advantages compared to multiple sets of 10 representative comparative algorithms. Finally, PPMSMA and 10 other comparative algorithms are used to solve engineering design optimization problems with different complexities. The experimental results validate the universality, reliability, and superiority of PPMSMA in handling engineering design constraint optimization problems. [ABSTRACT FROM AUTHOR]

This paper constructs a supply chain model consisting of two manufacturers and one platform, where the platform provides sales service to enhance the demand. The platform has demand information and decides whether and with which manufacturer to share the information. In practice, if the platform shares the information, the manufacturer can use the shared information to guide pricing decisions and further use Consumer-to-Manufacturer (C2M) strategy to drive product production. C2M means that the manufacturer produces products based on the shared information, making products satisfy consumers' needs, thereby increasing the market demand. Therefore, this paper uses a theoretical model to answer a key question: considering the role of C2M, whether the platform prefers to share demand information with others, and if the platform shares, which strategy is most beneficial to each player? First, this paper obtains the optimal equilibrium solutions under three strategies, that is, no information sharing (strategy NN), information sharing with one manufacturer (strategy SN or strategy NS), and information sharing with two manufacturers (strategy SS). Second, this paper derives that the information effect is the highest for all players under strategy SS. Whether the platform shares information with one or two manufacturers, the market effect has positive influences on both players. The cost effect does not affect the platform but hurts the informed manufacturer. Third, the conditions of the platform sharing information are obtained. There is a sales service efficiency threshold, if the sales service is more efficient, the platform shares the information with one manufacturer; otherwise, strategy SS is optimal. Fourth, through comparative analysis, this paper points out that when the C2M costs are lower, both manufacturers prefer the platform to choose strategy SS. Interestingly, when the C2M costs are higher, both manufacturers want the competitor to have information, which is different from the conclusions of previous studies. In addition, strategy SS makes the platform, and two manufacturers achieve Pareto optimality under certain conditions. Finally, the results are verified by numerical experiments. [ABSTRACT FROM AUTHOR]

Rice classification and quality detection are therefore crucial for ensuring the safety and quality of rice for human consumption and reducing the financial losses associated with rice spoilage. Accurate and efficient rice classification and quality detection techniques can help farmers, traders, and regulators identify the most valuable and high-quality rice cultivars, enabling them to make better crop management, storage, and transportation decisions. A system to automatically classify different types of rice grains is a valuable and crucial area of research in modern agriculture. Various methodologies have been used in recent years to identify agricultural products, including color-based, texture-based, and statistical-based features. This paper introduces a deep learning-based classification algorithm using ResNet deep models to represent the structural content of different varieties of rice grains. ResNet is a proven deep-learning model with impressive performance in various computer vision tasks, including signal classification. ResNet is adept at learning rich representations of images and generalizing them to new data making it a reliable choice for rice classification by combining residual learning and a well-structured architecture. In this paper, different architectures of ResNet, such as ResNet34, ResNet50, and a transferred version of ResNet50 using a transfer learning technique, are designed for performance evaluation in rice classification and quality detection problems. The performance of the proposed algorithm is compared with the other deep learning models and dictionary learning-based algorithms. The results demonstrate that the proposed algorithm using ResNet50 deep models and transfer learning accurately identified six rice varieties with an accuracy rate of over 99.85 %. The algorithm also accurately detects rice quality for different percentages of combination with other rice varieties with an average accuracy of 98.13 %. [ABSTRACT FROM AUTHOR]

• Treat a problem of the imbalanced customer churn classification. • A new multi-strategy collaborative processing method IADASYN-FLCatBoost is proposed. • The traditional ADASYN algorithm is improved and an IADASYN algorithm is proposed. • The Focal Loss function is embedded into the CatBoost to form a new FLCatBoost. • Empirical analysis shows the proposed method performs better than similar methods. The rapid advancement of big data and artificial intelligence heralds a dual-edged era of opportunities and challenges for the banking sector. Indeed, enhancing a model's capability to accurately classify imbalanced datasets represents a critical challenge within the field of customer churn prediction (CCP). In this paper, to address the challenges presented by the problem of imbalanced customer classification, a new multi-strategy collaborative processing method named IADASYN-FLCatBoost is proposed from dual perspectives: data and algorithm. At the data level, the traditional Adaptive Synthetic (ADASYN) sampling is improved, that is, the LOF (Local Outlier Factor) algorithm is introduced to eliminate outliers, and the classification features are specially processed to synthesize new minority class samples, thus an improved ADASYN (IADASYN) algorithm is obtained. At the algorithm level, the Focal Loss is embedded into the CatBoost ensemble learning framework to form a new Focal Loss-CatBoost (FLCatBoost) to make a focal-aware, cost-sensitive version of imbalanced customer churn prediction. Moreover, the empirical analysis is conducted in conjunction with the credit card customer dataset obtained from the Kaggle platform. The results of the staged comparison experiments show that the proposed method IADASYN-FLCatBoost in this paper shows the best prediction performance. Comparing the proposed method with 5 other imbalanced classification algorithms and 20 classifiers composed of classical sampling methods and ensemble learning algorithms, it is verified that the classification effect of the proposed method performs best, and the values of Recall , F 1 score, G-mean and Area under Precision-Recall curve (AUPRC) have been significantly improved. In addition, further verification of the model also proves that the proposed method has certain generalizability and is still valid for other banks and customer churn datasets of other industries. [ABSTRACT FROM AUTHOR]

Authors are often influenced by historical experience and personal habits when selecting keywords in composing papers, and tend to choose specific keywords, resulting in a phenomenon of conformity bias. In order to improve the accuracy of literature recommendation services, it is crucial to effectively identify and eliminate the adverse effects of conformity bias. Based on the definition of a measurement for the degree of impact of conformity bias using conformity width, this paper designs an effective method for eliminating conformity bias based on one-class implicit access information. At the same time, this method further utilizes the author's own keyword preference information based on explicit weight of keywords and achieves the comprehensive fusion of various effective user access information through the design of a model. The experimental results validated the phenomenon of conformity bias in the composing process of scholars, and comprehensively analyzed and compared the characteristics and advantages of the algorithm proposed in this paper. The code is available at https://github.com/EdwardSig/CBEWC_ESWA. [ABSTRACT FROM AUTHOR]

Hate speech pertains to the expression of negative emotions by people. The spread of hate speech contributes to societal inequity by imposing adverse consequences on individuals' emotional and physical well-being, financial circumstances, and overall quality of life, thereby hindering their daily existence. Hence, the development of a hate detection and diffusion prediction system is of utmost importance. The literature study reveals two primary findings regarding the development of a hate speech model. Firstly, it is crucial to understand the potential impact of a hate speech message, specifically the extent to which it influences the users exposed to it. Secondly, numerous researchers have focused on studying information propagation, with a particular emphasis on analysing network topology and structure. This paper introduces psycho-sociological analysis as another approach to understanding hate speech spread on social networks. We develop a hate speech diffusion model considering many psycho-sociological dimensions of social media users. This paper aims to answer a few basic questions: (a) Who starts hateful tweets on social media? (b) Who are the users who share, respond to, or like such posts? (c) Can we build a better hate-speech diffusion model by understanding each user's psycho-sociological traits towards hateful information? To answer the above questions, we analyse user psycho-sociological traits by studying three different dimensions of user behaviour, i.e., inner personality, societal personality, and dark emotion using the Big5 personality model, Schwartz value model, and the Dark triad behaviour model. We develop a collection of classifiers to detect users' personality traits. In addition, we proposed a system to predict the spread of hate content on social networks. Several empirical analyses are presented in this paper in order to understand the correlation between human personality and online hateful behaviour. From our empirical analysis of hostile behaviour, several key observations are reported in this paper, a few of which include the following: (i) People with dark triad orientations are mostly the originators of online hate speech, (ii) Those who post sexist tweets are often Machiavellian, (iii) Narcissistic users are more likely to make racist tweets, and (iv) Those who post sexist and racist tweets on social networks are often psychopathic. Using these insights, we have mapped the user behaviour dimension into a vector space called behaviour embedding. This space is used for developing the hate-speech diffusion model. We show that the proposed models also perform better than the state-of-the-art with a significant F 1 -score margin. • Hate spreaders can be identified by DL model using physiological features. • Dark triad traits are linked to the hate user and hate post spreader. • Deep CNN network to detect hate users on social networks. • Diffusion system predicts who will spread the hate post on social media. [ABSTRACT FROM AUTHOR]

The Fetal Electrocardiogram (FECG) signal plays a crucial role in monitoring the health of the fetus, but there are numerous challenges in eliminating the maternal thorax signal and reducing noise interference. This paper proposes a novel objective function that combines a Least Mean Squares (LMS) adaptive filter with a heuristic algorithms to enhance the quality of the extracted FECG signal. To achieve better results, we introduce the Discrete Artificial Bee Colony (DABC) algorithm with a new initialization strategy, a random wavelet basic function strategy, and Gaussian distribution. These improvements enhance global search capabilities and ensure a faster convergence rate. The application of heuristic algorithms can reduce noise signals and provides clearer and more accurate results compared to the traditional LMS filter. Furthermore, the effectiveness of this innovative algorithm is compared with other widely used heuristic algorithms. The experiment results demonstrate that the novel algorithm significantly enhances performance by up to 8% compared to other conventional extraction methods in some indicators. • A new objective function is designed to combine heuristic algorithms and LMS filter to extract the FECG signal from AECG signal. • This paper propose a novel Discrete Artificial Bee Colony, which introduce a tailored initialization strategy to improve the algorithm's convergence speed, based on the specific characteristics of the FECG signal extraction problem. The novel algorithm can obtain clearer extracted signal than other existed heuristic algorithms. • We incorporate the strategies of random wavelet basic functions and Gaussian distribution in the DABC algorithm to enhance the global search ability and prevent the population from prematurely becoming trapped in a local optimum. [ABSTRACT FROM AUTHOR]

Estimating the full state of physical systems, including thermal and flow status, from sparse measurements of limited sensors is a critical technology for perception and control. Neural networks have been used in recent studies to reconstruct the global field in a supervised learning paradigm. However, these studies encounter two major challenges: the lack of interpretability of black-box models and performance bottleneck caused by network structure and parameter optimization. This paper proposes a hybrid method based on proper orthogonal decomposition (POD) and deep neural networks (DNNs) to further enhance the interpretability and accuracy of flow and heat field reconstruction. The key idea is to leverage the inherent data modes extracted by POD that capture essential features in physical fields, and formulate the reconstruction problem as finding an optimal linear combination of dominant POD modes. To reduce the error introduced by underfitting and model structure, this paper estimates the coefficients of POD modes by establishing and solving a linear optimization problem that minimizes the gap between the recovered field and the exact measurements, rather than employing regression models. However, the underdetermined issue cased by the sparse measurements restricts the optimization problem to obtain a proper solution. To alleviate this problem, this paper presents to utilize the powerful non-linear approximation ability of DNNs to produce a reference field as auxiliary observations, which combines exact measurements to jointly constrain the optimization problem solving. Finally, the global physical field is reconstructed by superposing dominant POD modes weighted with the solved coefficients. By combining with POD technology, the proposed method can also improve the performance of neural networks on reconstruction problems with large-scale and irregular domains. The experiments conducted on the fluid and thermal benchmarks demonstrate that the proposed method can significantly boost neural network reconstruction performance and outperform existing POD-based methods. • A hybrid method based on POD and deep neural networks is developed for flow and heat field reconstruction from sparse measurements. • The data modes extracted by POD are explicitly used to alleviate black-box problems of neural networks. • The field reconstruction problem is converted to a linear optimization jointly constrained by exact measurements and DNN predictions. • The underdetermined issues with sparse measurements can be addressed. [ABSTRACT FROM AUTHOR]

State-of-the-art dense stereo matching algorithms have achieved excellent performance, demonstrating a capability to attain precise matching in most areas. However, current such methods rarely achieve this when images are captured under poor conditions. To improve the accuracy of the algorithm in such cases, this paper introduces a post-optimization algorithm to rectify matching errors and enhance outcomes. The main research areas of this paper include three aspects. (1) Disparities are classified into reliable and unreliable results based on the analysis of geometric matching relationships, local features in the images, and components within the matching cost function; (2) Subsequent analysis of horizontal image features identifies local characteristic indices calculated through integration along the horizontal axis, which establish specific matching criteria, forming the foundation for a cost volume that encompasses these distinct matches; (3) A redefined matching cost function is applied to previously classified unreliable results to rectify matching errors. This energy function is based on the cost volume above. Experimental results validate the efficacy of the proposed post-optimization algorithm, reducing the average matching errors from 8.66% to 5.85%. [ABSTRACT FROM AUTHOR]

Today's Internet of Vehicles (IoV) faces many security risks in the data transmission process, and image data is more vulnerable to security threats in the transmission process due to its special characteristics such as large amounts of information and high visibility. Therefore, to guarantee the dependability of data transmission in the IoV environment, this paper designs a blind signature scheme for IoV based on two-dimensional sine cosine cross-chaotic mapping (2D-SCML) image encryption and lattice cipher (BSS-IoV). The innovation of this scheme is that it aims at blind signature of image information, blinds it before sending the information, and combines the lattice public key encryption algorithm to better ensure the safe and reliable transmission of information and reduce the risk of information disclosure. To further ensure the security of the scheme, an image encryption algorithm based on 2D-SCML and pixel splitting (2PS-IEA) is proposed, which is used to blind the information and thus reduce the risk of information leakage on the one hand, on the other hand, it is used in the signature process to ensure the security of the signed information. The 2D-SCML is derived from the cross-model structure proposed in this paper. Through simulation results and experimental analysis, the values of NPCR and UACI, respectively, 99.6094% and 33.4635%, are close to ideal values. And 50% of the cut image can also recover the rough information, which indicates that the signature scheme has the security against differential attacks, cut attacks and noise attacks. Moreover, the security analysis shows that the scheme has the anti-tamper, anti-repudiation and traceability. • Designed blind signature scheme for IoV using image encryption and lattice cipher. • Proposed a crossover model structure is proposed. • Designed a 2D-SCML mapping with superior performance based on this model. • Devised an image encryption algorithm based on 2D-SCML and pixel splitting. • The signature scheme and encryption scheme are analyzed experimentally. [ABSTRACT FROM AUTHOR]

This paper discusses the use of portfolio approaches based on bandit algorithms to optimize multicriteria decision-making in recommender systems (accuracy and diversity). While previous research has primarily focused on single-item recommendations, this study extends the research to consider the recommendation of several items per iteration. Two methods, Multiple-play Gorthaur and Budgeted-Gorthaur, are proposed to solve the algorithm selection problem and their performances on real-world datasets are compared. Both methods provide a generalization of the Gorthaur method, which enables it to operate with any Multi-Armed Bandit (MAB) and Contextual Multi-Armed Bandit (CMAB) algorithm as meta-algorithm in a multi-item recommendation scenario. For Multiple-play Gorthaur, an empirical evaluation shows that the use of Thompson Sampling for algorithm selection (Gorthaur-TS) yields better results than the original EXP3 method (Gorthaur-EXP3) and the exclusive use of the optimal algorithm in the portfolio in contextual recommendation problems. Additionally, the paper includes a theoretical regret analysis based on the TS sketch proof applied for this variant of the method. Concerning Budgeted-Gorthaur, experiments show that it allows more flexibility to achieve a suitable trade-off between criteria and a broader coverage of the Pareto set of solutions, overcoming a natural limit of "a-priori" methods. Finally, this paper provides a detailed review, including pseudocodes and theoretical bounds, for all the fundamental MAB and CMAB algorithms used in this study. • Bandit literature lacks formal algorithm review, hindering clarity and comparability. • There is no silver bullet: no algorithm can be the best performer in every instance. • Recommender systems need to balance accuracy, diversity, multi-item recommendations. • Optimal algorithm balances criteria, matching decision maker's preferred trade-off. • Dynamic selection ensures safe performance when optimal algorithm is unknown. [ABSTRACT FROM AUTHOR]

• Newbie study using standard ML techniques with HAR Application and Discussions. • Activities found in Literature with the corresponding reference. • Co-occurrences between activities and sensors with the corresponding reference. • Summary and comparison among the different datasets found in Literature. • Summary of the experimentation settings with performance scores found in Literature. Human Activity Recognition (HAR) is an essential area of research related to the ability of smartphones to retrieve information through embedded sensors and recognize the activity that humans are performing. Researchers have recognized people's activities by processing the data received from the sensors with Machine Learning Models. This work is intended to be a hands-on survey with practical's tables capable of guiding the reader through the sensors used in modern smartphones and highly cited developed machine learning models that perform human activity recognition. Several papers in the literature have been studied, paying attention to the preprocessing, feature extraction, feature selection, and classification techniques of the HAR system. In addition, several summary tables illustrating HAR approaches have been provided: most popular human activities in the literature with paper references, the most popular datasets available for download (Analyzing their characteristics, such as the number of subjects involved, the activities recorded, and the sensors with online-availability), co-occurrences between activities and sensors, and a summary table showing the performance obtained by researchers. =The paper's goal is to recommend, through the discussion phase and thanks to the tables, the current state of the art on this topic. [ABSTRACT FROM AUTHOR]

The proliferation of malware in recent years has posed a significant threat to the security of computers and mobile devices. Detecting malware, especially on the Android platform, has become a growing concern for researchers and the software industry. This paper proposes a new method for detecting Android malware based on unbalanced heterogeneous graph embedding. First of all, most malware datasets contain an imbalance of malicious and benign samples, since some types of malware are scarce and difficult to collect. Thus, as a result of this problem, the classification algorithm is unable to analyze the minority samples through sufficient data, resulting in poor downstream classifier performance, in light of the fact that adversarial generation networks possess the characteristic of completing data, an algorithm for generating graph structure data is presented, in which nodes are generated to simulate the distribution of minority nodes within a network topology. Then, considering that heterogeneous information networks have the characteristics of retaining rich node semantic features and mining implicit relationships, heterogeneous graphs are used to construct models for different types of entities (i.e. Apps, APIs, permissions, intents, etc.) and different meta-paths. Finally, a new method is introduced to alleviate the over-smoothing phenomenon of node information in the propagation of deep network. In the deep GCN, we first sample the leader nodes of each layer node, and then add a residual connection and an identity map in order to determine the characteristics of the high-order leader. In this paper, a self-attention-based semantic fusion method is also applied to adaptively fuse embedded representations of software nodes under different meta-paths. The test results demonstrate that the proposed IHODroid model effectively detects malicious software. In the DREBIN dataset, which consists of 123,453 Android applications and 5,560 malicious samples, the IHODroid model achieves an accuracy of 0.9360 and an F1 score of 0.9360, outperforming other state-of-the-art baseline methods. • A new generative adversarial network model has been proposed for balancing data. • Heterogeneous graphs are used for modeling malware detection. • A new method is introduced to alleviate the over-smoothing phenomenon. [ABSTRACT FROM AUTHOR]

Roundwood sorting is still a manual process in many Swiss sawmills, requiring employees to visually inspect and categorize thousands of logs per day. The heavy workload can be both physically and mentally taxing and can lead to increased rates of human error. State-of-the-art automation systems like X-ray log scanners are expensive and difficult to integrate into existing process lines. This paper proposes a novel recommendation system that leverages recent advances in image classification to automate roundwood classification by quality and species. The system integrates a camera to capture cross-sectional images of logs and record numerical data, such as length, taper, and diameter. The analysis of the resulting dataset highlights the challenges of data imbalance and noise, which makes classification difficult and, in some cases, impossible. However, by using selected datasets with reduced noise, state-of-the-art Convolutional Neural Networks (CNNs) can extract quality and species features. Quality models learn from a manually selected and simplified dataset, featuring samples that experts can clearly classify based on the image's information. Species models are trained on a label-noise-reduced dataset, reflecting real-world complexity. The accuracy on the selected dataset for three quality classes is 80%. The species determination is less challenging and reaches 91% accuracy on a synchronized dataset for the main species spruce and fir. Overall, this paper highlights the potential of Machine Learning in augmenting the roundwood sorting processes and presents a novel system that can improve the efficiency and accuracy of the process. [Display omitted] • Automation of roundwood sorting: Replaces manual sorting with image-based AI. • Integrated camera system in roundwood sorting to collect labeled dataset. • Species prediction: 91% accuracy in spruce–fir distinction. • Quality prediction on complexity reduced dataset: 80% accuracy between three main quality levels. • Efficient, adaptable & scalable system which is easy to integrate into existing process lines. [ABSTRACT FROM AUTHOR]

Complex networks have a large number of nodes and edges, which prevents the understanding of network structure and the discovery of valid information. This paper proposes a new community detection method for simplified networks. First, a similarity measure is defined, the path and attribute information can reflect the potential relationship between nodes that are not directly connected. Based on the defined similarity, an Importance Score(IS) is constructed to show the importance of each node, it reflects the density around each node. Then, the simplification processes can be realized on complex networks. On the simplified network, this paper proposes a novel community detection method, in which the community structure of the simplified network is detected. The experiments were conducted on real networks and compared with several widely used methods. The experimental results illustrate that the proposed method is more advantageous and can visually and effectively uncover the community structure. [ABSTRACT FROM AUTHOR]

Intelligent applications are highly susceptible to uncertainty and inconsistency due to the intense and intricate interactions among their autonomous components (or agents), making their verification theoretically and practically challenging. This paper presents the design and implementation of a new open-source and scalable software tool for modeling and verifying intelligent applications with commitment and trust protocols under both uncertainty and inconsistency settings, using reduction-based multi-valued model checking techniques. The proposed tool is equipped with original and novel algorithms that transform our logics of multi-valued commitment (mv-CTLC) and multi-value trust (mv-TCTL) that we recently introduced to their classical two-valued commitment (CTLC) and trust (TCTL) logic versions as well as to Computational Tree Logic (CTL). Moreover, the tool transforms the mv-CTL to CTL, and it is applicable for the classical model checking by transforming the classical logics of trust and commitment to CTL. To demonstrate the practicality and applicability of the proposed tool in real settings, we present and report experimental results over two blockchain-based applications in the healthcare domain. Finally, we provide discussions and comparisons between the proposed approaches regarding scalability and efficiency. Moreover, we provide packages of more than 11 experiments, including the ones we conduct in this paper and enhanced experiments from previous works. Our findings ensure that the proposed approaches and the software tool that implements them are highly efficient and scalable, giving accurate results under varying conditions. • Design and implementation of an open-source scalable tool for systems model checking. • System modeling with multi-valued logic capturing uncertainty and inconsistency. • Practical demonstration using blockchain-based applications in healthcare domain. • Extensive experiments showing scalability, efficiency and reliability of the tool. [ABSTRACT FROM AUTHOR]

Modern power systems integrated with renewable energies (REs) contain many uncertainties. The proposed method introduces a novel approach to address the challenges associated with wind power generation uncertainty in probabilistic load flow (PLF) studies. Unlike conventional methods that use wind speed as an input, the paper advocates for utilizing wind generator output power (WGOP) as an input to the point estimate method (PEM) in solving PLF. The uniqueness lies in recognizing the distinct behavior of wind power uncertainty, where not all random samples of wind speed contribute to actual wind power production. The paper suggests a Nataf-KernelDensity-Spline-based PEM, combining the Nataf transformation, Kernel density estimation (KDE), and cubic spline interpolation. This innovative integration effectively manages wind power correlation within the analytical framework. By incorporating spline interpolation and kernel density estimation into the traditional PEM, the proposed method significantly enhances accuracy. To validate the effectiveness of the proposed approach, the method is applied to IEEE-9 and IEEE-57 bus test systems, considering uncertainties related to load, wind power generation (WPG), solar power generation (SPG), and conventional generator (CoG) outages. Comparative analysis with Monte Carlo simulation (MCS) results demonstrates that the proposed method outperforms the conventional PEM in terms of accuracy. Overall, the paper contributes a pioneering solution that not only highlights the importance of using WGOP as an input in PLF but also introduces a sophisticated method that surpasses traditional approaches, improving accuracy in power system studies involving renewable energy integration. The accuracy of the proposed method is validated by comparing its results with those obtained through Monte Carlo simulation (MCS), where the proposed method yields more accurate results than the conventional PEM. [ABSTRACT FROM AUTHOR]

Deep learning has recently demonstrated considerable promise for a variety of computer vision tasks. However, in many practical applications, large-scale labeled datasets are not available, which limits the deployment of deep learning. To address this problem, semi-supervised learning has attracted a lot of attention in the computer vision community, especially in the field of medical image analysis. This paper analyzes existing deep semi-supervised medical image segmentation studies and categories them into five main categories (i.e., pseudo-labeling, consistency regularization, GAN-based methods, contrastive learning-based methods, and hybrid methods). Afterward, we empirically analyze several representative methods by conducting experiments on two common datasets. Besides, we also point out several promising directions for future research. In summary, this paper provides a comprehensive introduction to deep semi-supervised medical image segmentation, aiming to provide a reference and comparison of methods for researchers in this field. [ABSTRACT FROM AUTHOR]

As one of the most critical variables in the hot rolling process, the accuracy of rolling force prediction is directly associated with production stability and product quality. Purely data-driven approaches, however, are severely constrained by the quantity and quality of data, posing challenges for further enhancing the accuracy of rolling force prediction. In this paper, a theory fusion deep neural network (DNN) modelling approach was proposed and applied to the prediction of rolling force during hot plate rolling. In terms of model establishment, the novel NN structure was designed in consideration of the rolling mechanism, and senior variable inputs were added at shallow locations in the network to reduce the loss of critical information. In terms of model training, the method of using rolling theory to guide the initialization of the model was proposed to enable the model to learn the theoretical features more completely in the pre-training phase. Finally, a method to optimize the overall structure of the model using the sparrow search algorithm (SSA) was proposed to ensure the best prediction performance. The model was tested with the data in the developed platform, and the results indicated that the proposed method achieves the best accuracy and stability in this paper, and the response relationship between model inputs and output was consistent with existing theoretical knowledge. Thus, the model can be trusted and flexibly applied to the actual manufacturing processes. [ABSTRACT FROM AUTHOR]

The trend in underground mine development is trackless transportation, and the scheduling optimization of underground mine trackless transportation is a current research hotspot. This paper proposes a truck scheduling optimization method for underground mine trackless transportation based on an improved estimation of distribution algorithm to address the truck scheduling problem in the underground mine trackless transportation process. The transportation process of transport trucks in underground mines is analyzed. The dispatching model of transport trucks in underground mines is constructed based on the requirements of reducing transportation costs and increasing transportation efficiencies, taking into account the truck meeting situation in the ramp section and minimizing the total shift transportation distance and the total waiting time of transport trucks as the objective functions. The improved estimation of distribution algorithm is used to solve the truck scheduling model, resulting in the optimal ore blending and scheduling schemes. The comparative analysis employs a genetic algorithm, particle swarm optimization algorithm, and immune algorithm. The results demonstrate that, compared to other algorithms, the improved estimation of distribution algorithm proposed in this paper has superior performance in terms of convergence speed and the search for the optimal solution. The total number of transportation tasks associated with the optimal ore allocation scheme is at least 82, and the waiting time associated with the optimal scheduling scheme is reduced to 7.5 min. The operation time chart of transport trucks calculated by the optimal dispatching scheme can clearly depict the location of each transport truck at any time during a shift's working time, which has significant guiding significance for the actual truck transportation in the mine. [ABSTRACT FROM AUTHOR]

Conceptual clustering is one of the key approaches for automatic concept generation from input contexts. In this paper, we propose an extension of the dominating k-means method. The proposed method introduces a flexible distance metric that enables the approximation of both Euclidean and meet(or join)-based similarity calculations. To increase the approximation accuracy, the method combines the k-means method with a Quality Threshold component. The paper shows that the method can also be used for approximation of formal concept lattices. Based on the performed tests, the method provides an efficient alternative conceptual clustering approach. • Novel extension of the k-means-based conceptual clustering algorithm. • Novel parameterized distance metric to cover different aggregation approaches. • Tool for flexible concept set reduction in formal concept analysis. [ABSTRACT FROM AUTHOR]

Intrusion Detection System (IDS) can ensure the network security by identifying network intrusions according to the abnormal traffic data. However, the intrusion detection data has the problem of high dimensionality and changes with network and attack environments, which leads to the poor performance and poor portability of intrusion detection algorithms. Therefore, this paper proposes an intrusion detection algorithm based on joint symmetric uncertainty and hyperparameter optimized fusion neural network. Firstly, a feature selection method based on symmetric uncertainty and approximate Markov blanket is proposed, which fully considers the correlation and redundancy of features, and also the correlation between combined features and the class label, so as to reduce the data dimensionality. Secondly, the CNN-LSTM classifier fused with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is used to extract the spatial features and temporal features to improve the classification performance. Finally, the Particle Swarm Optimization (PSO) algorithm is improved and used to automatically optimize the hyperparameters of the classifier, so that the classifier can be applied to different intrusion detection datasets with better generalization ability and portability. Experiments have verified the effectiveness and superiority of the proposed algorithm on multiple evaluation indicators. • An effective algorithm for intrusion detection is proposed in this paper. • Feature selection is based on symmetric uncertainty and approximate Markov blanket. • A fusion neural network is constructed to extract the spatial and temporal features. • The PSO algorithm is improved to automatically optimize the hyperparameters. [ABSTRACT FROM AUTHOR]

With global climate change posing a major threat to human society, a growing number of countries have taken "carbon-neutral" as a national strategy and proposed a vision of carbon-free future. As an important supplement to traditional fossil energy, renewable energy is the main force to reduce the use of high-carbon energy and carbon dioxide emissions, which will become the trend of social development in the future. Finding the optimal renewable energy source is of particular significance for achieving the net zero emissions. However, the existing evaluation methods of renewable energy sources have obvious shortcomings. In terms of weight calculation methods, such as the randomness of the subjective method is strong and the index weights do not reflect the small changes of the evaluation matrix, which affect the reliability and accuracy of the evaluation result. The existing ranking methods can only achieve the complete ranking of the different objects, but cannot classify the renewable energy technical alternatives into different grades. Given this background, this paper proposes a novel evaluation method for renewable energy plans based on improved sparrow search algorithm and projection pursuit model. Firstly, this paper improves the traditional sparrow search algorithm from three aspects: population initialization, population update and population variation. Then, the projection pursuit model is constructed, and the improved sparrow search algorithm is applied to optimize the projection target to find the optimal projection direction, so as to determine the weight values of each evaluation index. Finally, the weighted rank-sum ratio method is used to select the best renewable energy technical plan, which can not only realize the complete ranking of different plans, but also classify the technical plans into different levels. Based on the actual renewable energy development data from a province in China, experiments were carried out to investigate the effectiveness of the proposed method. Experimental results show that the proposed method performs better than some existing evaluation methods of renewable energy technical plans. [ABSTRACT FROM AUTHOR]

High-dimensional feature selection is of particular interest to researchers. In some domains, such as microarray data, it is quite common for a group of highly correlated explanatory variables to be of equal importance for inclusion in the predictive model. This paper proposes a new hybrid feature selection approach that integrates feature screening based on Kendall's tau and Elastic Net regularized regression (K -EN). K -EN as an approach that embeds the Elastic Net, has the advantage of the grouping effect, which automatically includes all the highly correlated variables in the group. The K -EN approach offers insightful solutions to high-dimensional regression problems and improves Elastic Net performance since the screening phase is preceded by a step that further reduces the number of explanatory variables by removing those that disagree with the target based on Kendall's tau. The use of Kendall's tau further enhances Elastic Net performance, as it is robust enough to handle heavy-tailed distributions, non-parametric models, outliers, and non-normal data with greater ease. K -EN is therefore a time-saving approach. The proposed algorithm is evaluated on four simulation scenarios and four publicly available datasets, including riboflavin, eyedata, Longley, and Boston Housing, and achieves 0.2528, 0.0098, 0.1007, and 0.4121 respectively as the Mean Squared Error (MSE). K -EN's MSEs are the best compared to those achieved by the state-of-the-art approaches reviewed in this paper. In addition, K -EN selects up to 100% of relevant features when run on simulated data. [ABSTRACT FROM AUTHOR]

[Display omitted] In today's world, a large number of people suffer from motor impairment-related challenges. Rehabilitation is the main method used to overcome these difficulties. The goal of the paper is to develop a deep learning-based electroencephalogram (EEG) sensor-controlled assistive device for the rehabilitation of elbow and finger movements. We have introduced an innovative finger and elbow movement rehabilitation method using an EEG sensor. The EEG sensor's recorded EEG signals, attention values, and meditation values have been used for this purpose. This rehabilitation technique helps a person perform basic finger movement rehabilitation motions, such as finger extension and flexion. Also, basic elbow movement rehabilitation exercises, i.e., elbow extension and elbow flexion, can be performed by using this rehabilitation technique. In this research, an EEG sensor records the prefrontal lobe's EEG signals, attention value, and meditation value of a person while the person performs motor imagery. A deep learning-based CNN-TLSTM (Convolution Neural Network-tanh Long Short-Term Memory) model with attention mechanism has been designed for decoding the EEG sensor recorded data. The trained deep learning model decides the course of action of the rehabilitation device. The designed model achieves an accuracy of 99.6%. A working prototype model of the rehabilitation device has been developed, and the overall success rate of the model is found to be 98.66%. The novelty of the paper lies in i) designing an attention-based CNN-TLSTM model for motor imagery classification and ii) developing a low-cost EEG sensor-driven rehabilitation device for finger and elbow movement rehabilitation. [ABSTRACT FROM AUTHOR]

The focus of this paper is on achieving a win-win situation regarding the economic, environmental, and social impacts of the cold chain logistics terminal distribution system. This paper proposes three multi-objective models to investigate the above effects by incorporating soft time windows, heterogeneous fleets, and path flexibility, with defining the objectives of examining logistics costs, fuel consumption, carbon emissions, quality damage to perishable commodities, and customer satisfaction using six evaluation functions. To solve the proposed models, an efficient optimization framework is developed by combining domain operators with versatile multi-objective evolutionary algorithms (MOEA) to obtain Pareto solutions. Extensive experiments are conducted to test the validity of the concerned model and algorithms. The results demonstrate that: (1) the proposed algorithm is effective in solving the proposed model; (2) the proposed multi-path strategy can effectively improve the performance of cold-chain logistics systems compared to single-path strategies; (3) evaluation functions that assess customer satisfaction greatly affect the performance of cold-chain logistics systems; and (4) the trade-off relationship between the objectives should be investigated to define the model. The paper also provides valuable managerial insights for improving the efficiency and sustainability of cold-chain logistics operations. [ABSTRACT FROM AUTHOR]

Nature- and society-inspired metaheuristic algorithms have recently become the most promising technological model. To solve more complex optimization problems and complicated engineering applications, this paper proposes a new people duality psychological tendency and feedback mechanism-based Inherited Optimization Algorithm(IOA), which is inspired by people showing positive-negative duality cognitive tendency and adaptive feedback behavior when selecting information resources with different identity attributes. The IOA algorithm contains the symmetric two exploration phases. The exploitation phase adaptively regulates the dualistic psychological balance of people in inheriting the information resources with better existence value through a feedback regulation mechanism controlled by the profitability awareness to increase population diversity. This paper qualitatively and quantitatively evaluates the optimization performance of IOA on 84 benchmarks, including swarm convergence behavior, effectiveness, convergence, robustness, and significance. The scalability of the IOA is investigated using the CEC2017 suites. The algorithm performance in solving constrained optimization is verified on 8 engineering problems. All statistical results of the IOA are compared with the most promising 12 metaheuristics, which shows that the absolute computational efficiency of IOA on four types of functions is 95%, 96.67%, 80.95%, and 76.92%, respectively, the average rank (rank sum ratio) of IOA is 1.08 (1.19%) among the 13 algorithms, ranking first. The Wilcoxon signed rank test results on the CEC2017 suites show that IOA contains 1437 significance indicators out of 1440 comparisons, with the proportion of significant differences 99.79%, which suggests the proposed IOA maintains efficient search efficiency. [ABSTRACT FROM AUTHOR]

The emergence of online social networks (OSN) platforms removes communication barriers that are essential to human life, catalyzing social networking growth. However, this emergence has given rise to a negative impact when someone abuses the platform to commit cyberbullying activities. Hence, it is crucial to work on automated cyberbullying-related classification to mitigate the societal phenomena in OSN. The research on the automated classification model for cyberbullying was pioneered over the last decade with growing interest among researchers. It is helpful to track its growth over the decades to elucidate the state-of-arts techniques applied in this field. This paper presents a large amount of literature germane to cyberbullying classification from past to present to provide a comprehensive review. A total of 126 papers were reviewed. This paper emphasizes text-based cyberbullying and multi-modal cyberbullying. The review was presented around the machine learning workflow, encompassing four core sections: dataset analysis, pre-processing analysis, feature analysis, and technique analysis. Based on the critical analysis, limitations are addressed along with the future works that can be conducted to fill the gap in previous research. Furthermore, the review also examined the ethical implications associated with the implementation of these techniques. This review paper is expected to assist readers in fully comprehending the current trend, architecture, and techniques applied to the field. [ABSTRACT FROM AUTHOR]

In the contemporary world, data pervades every facet of human life, and the information contained in this data plays a pivotal role in shaping decision-making and advancing technology. Among the plethora of techniques available, classification methods are highly effective tools for extracting valuable insights from vast volumes of data. The R ule A ggregation C lassifi ER (RACER) is a novel rule-based classification algorithm known for its exceptional performance. A notable limitation of RACER lies in its inability to handle continuous features. In this paper, we address the aforementioned limitation by employing various supervised discretization methods, including CAIM, MDLP, Decision Tree (CART), and ChiMerge. The impact of these methods on RACER's accuracy and understandability is evaluated across nine datasets from the UCI repository. Additionally, the paper conducts a comparative analysis of RACER's accuracy against well-known classifiers such as Naive Bayes, Logistic Regression, SVM, LightGBM, and Decision Tree. The findings indicate that RACER achieves the highest average accuracy when we utilize MDLP as the discretization method, surpassing its initial average accuracy. Moreover, RACER demonstrates superior understandability by generating the lowest number of rules when employing ChiMerge and Decision Tree for discretizing numerical features. Furthermore, RACER outperforms the other five classifiers when employing MDLP. • The discretization unit enables the RACER algorithm to handle continuous data. • The discretization unit improves the classification accuracy of the RACER. • The discretization unit increases the understandability of the RACER rules. [ABSTRACT FROM AUTHOR]

Heterogeneous graphs, which are also called heterogeneous information networks, analyze the different types of nodes in an information network and the different types of links between them to accurately tell the difference between different semantics. In recent years, there have been several GNN-based models to process heterogeneous graph data and achieve good performance. The model faces the challenge of first considering how to deal with the challenges posed by embedding different types of nodes in a heterogeneous graph; secondly, analyzing the node attribute information, which requires satisfying all nodes with attributes, which is not easy to achieve due to the existence of individual nodes and their neighbors that do not carry attributes. Previous network structures have added attributes to nodes by handcrafted methods, thus neglecting the overall learnability of the model, which in turn leads to poor performance. This paper analyzes the reasons for this phenomenon and aims to design a learning-competent heterogeneous graph neural networks(HGNN) framework. The understanding in this study embeds different types of nodes into the same feature space for node embedding, using the topological embedding of heterogeneous graphs as a guide to complete the process of complementing non-attributed nodes through learnable ways in the model and the use of residual attention mechanisms to handle attributes between nodes. Therefore, this paper proposes a general framework for Attribute Completion of Heterogeneous Graph Neural Network Based on Residual Attention Mechanism (RA-HGNN) , and combines it with other GNN models to enable end-to-end execution of the entire model. Experimental verification was completed on real-world data sets to prove the feasibility of the model, and the experimental results showed state-of-the-art performance. [ABSTRACT FROM AUTHOR]

In the realm of ecological management and human activities within river basins, short-term runoff forecasting plays a pivotal role. Addressing this need, this paper introduces an innovative framework for short-term runoff forecasting: the Ensemble Attention Temporal Convolutional Network (EA-TCN). The cornerstone of this innovation lies in the effective amalgamation of Temporal Convolutional Network (TCN), lightweight attention mechanism, and ensemble learning strategy. This integration synergistically enhances the model's overall performance in terms of accuracy, efficiency, and robustness. TCN forms the foundation of this framework, where its efficient architecture, characterized by shared parameters and parallel computation, significantly boosts computational efficiency. Its employment of causal and dilated convolutions adeptly captures long-term dependencies within time series inputs. The incorporated lightweight attention mechanism further augments the TCN, enabling EA-TCN to precisely discern complex relationship in temporal data, particularly exhibiting remarkable temporal robustness across various forecasting horizons—a feat challenging for conventional forecasting approaches. Additionally, the integration of the Snapshot ensemble method within the framework allows for simulating the effect of training multiple models through one single training process, thus further elevating the model's accuracy and robustness. Rigorous ablation and comparative experiments conducted on the US Columbia River dataset substantiate our claims. The results not only validate the individual merits of each component within EA-TCN but also illuminate the significant advantages of their collective application. Our comprehensive assessment unequivocally demonstrates the framework's exceptional performance in short-term runoff forecasting, positioning it as a state-of-the-art solution in this field. We will further discuss its impact of vocation education in this industry. • This paper applied the modified TCN to short-term runoff forecasting. • EA-TCN adopts a lightweight plug-and-play attention module in the time dimension. • The Snapshot ensemble method is also applied to our proposed model. • EA-TCN can make accurate predictions for multiple different lead times. [ABSTRACT FROM AUTHOR]

This paper exercises a novel procedure with virtual e-nose (VEN) systems using a single compacted nanoparticle ZnO chemical sensor. The pellets are formed by a nano-powders synthesized via a simple sol–gel method. Furthermore, in this paper task we show the transient differences in the dynamic response curves for ZnO pellet when exposed to volatile organic compounds (VOCs) namely ethanol, methanol, isopropanol, acetone and toluene. VOCs are categorized using the transient response of a single sensor at four different operating temperatures, offering diverse features that came from the reaction mechanism of the target molecule. The relevant attributes of responses were run through Ascending Hierarchical Classification integrated with Principal Component Analysis. Three clusters classified for three specific features subsets were distinguished. A new mathematical iteration of this hybrid process was performed and leads to good HAC output stability. The result is delivered automatically with three-digit sorts in a specified order after thorough implementation. [ABSTRACT FROM AUTHOR]

When writing academic papers, referencing statements, claims and previous studies is always an important activity. However, it is considered challenging for scientists to find relevant and appropriate scientific articles which are closely related to their current works in order to reference them in their research. As a consequence of the rapid growth in scientific papers being published every year, researchers might easily get overwhelmed within a huge number of resources. One way to help them find the desired references more easily is to use context-aware citation recommendation. The citation recommender system can automatically provide a list of suitable papers as references based on specified inputs which reflect the researchers' interests. Among the outstanding achievements of deep learning and natural language processing in recent years, the utilization of deep neural learning architectures have supported to address the problem of citation recommendation. As the result, the neural citation recommendation area has received much attention from the academic community, with the aim of enhancing the precision and correctness of the results of existing citation recommendation systems. Following this research direction, in our paper we present a novel context-aware citation recommendation model, called RHN-DualLCR (Recurrent Highway Networks – Dual Local Citation Recommendation), which integrates Recurrent Highway Networks (RHN), an improved model of the original Bidirectional Long Short-Term Memory (BiLSTM) architecture, and uses a SciBERT-based (Science text of Bidirectional Encoder Representations from Transformers) embedding layer to build up the efficiency of the state-of-the-art local citation recommendation model, which enriches context representation with global information. Our research demonstrates its originality and relevance because we used one of the latest achievements of deep models (RHN model) and natural language processing (SciBERT) applied to the citation recommendation problem. We have conducted experiments on the RHN-DualLCR model on 3 widely known datasets for the citation recommendation problem: ACL-200 (Association for Computational Linguistics), ACL-600 and RefSeer, and also used 2 common evaluation standards Mean Reciprocal Rank (MRR) and the Recall@K (R@K for short) to evaluate the performance of our model. Experimental results show that our proposed model is 3% to 16% better than the original models or state-of-the-art models. [ABSTRACT FROM AUTHOR]

The current body of research on multi-attribute group decision-making (MAGDM) exhibits some limitations, namely the utilization of the single attribute hierarchy and the assumption of attribute independence. This paper presents a novel approach, referred to as the R-DLMAGDM (R-numbers Dual-Level Multi-Attribute Group Decision-Making) model with interaction factors, which integrates the advantages of R-numbers in risk evaluation. The proposed model aims to address the limitations related to attribute hierarchies and the assumption of attribute independence. The first step in the new model involves establishing the entropy model with R-numbers to determine the expert weights. Subsequently, the R-numbers generalized weighted arithmetic average (RNGWAA) operator and the R-numbers generalized weighted geometric average (RNGWGA) operator are introduced to combine the information provided by the experts. Next, the application of the enhanced correlation coefficient and standard deviation (CCSD) method is utilized to ascertain the relative weights of the dual-level attributes using the inverse order concept. Then, the fuzzy cognitive map (FCM) is employed to evaluate the interrelationships among components in order to derive the final attribute weights. Additionally, the paper discusses the implementation of the R-DLMAGDM model for the assessment of risk in a virtual supply chain in the metaverse. The evaluation process entails the prioritizing of five different alternatives based on four Level 1 criteria and seven Level 2 criteria. The model's flexibility and validity are showcased through the execution of comprehensive sensitivity analysis and three-dimensional comparative analysis. [ABSTRACT FROM AUTHOR]

Post-hoc explaining approaches for deep learning (DL) models has attracted much attention in safety–critical applications such as rotating machinery intelligent fault diagnosis (IFD). However, with the help of the explanation techniques, the models are still fragile to domain shifts caused by varying speeds and loads without help for improving their cross-domain performance. Since humans in the decision-making loop are essential for a reliable diagnostic system to determine the reliability of diagnosis, this paper proposes a causal explaining guided domain generalization (CXDG) method to realize trust worthy IFD with human in the decision loop. Specifically, an explaining model is trained with the conditional mutual information, which is a causal strength metric, and utilized to tell the causal features in the input data as the attributions of the diagnostic model. A translation process of the attributions is proposed to make the explaining process understandable. Furthermore, the aim of this paper is not only explaining but also beyond that the diagnostic model is guided to focus on the causal features to improve its generalization ability in unseen domains. The effectiveness of the method is validated on two experiment datasets. The results show that the proposed method can both explain the attributions of the diagnosis model and be beneficial to the generalization ability. [ABSTRACT FROM AUTHOR]