Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126856
Ning Ma , Angjun Tang , Zifeng Xiong , Fuxin Jiang
This paper focuses on the micro-service migration problem with affinity, stemming from the cloud computing industry. Because of periodically creating and deleting micro-services to satisfy users’ demands, the deployment of micro-services in the cloud needs to be regularly adjusted, which is referred to as a micro-service migration. An optimal migration schedule should minimize the number of activated physical machines as well as maximize total internal invoking traffic (affinity). A cooperative multi-agent reinforcement learning (MARL) is proposed, which is enhanced by integrating Hindsight Reward Shaping and by fine-tuning the state encoder using a pre-trained ResNet model. The proposed MARL is validated on both synthetic datasets and real cloud traces of ByteDance and Alibaba, compared with four baseline algorithms: Migration Ant Colony Optimization, Migration Neighborhood Search, Single-Agent Reinforcement Learning, and the optimization solver CPLEX. Finally, an evaluation mechanism called Matching Score is proposed to explain the superior performance of MARL.
{"title":"A deep multi-agent reinforcement learning approach for the micro-service migration problem with affinity in the cloud","authors":"Ning Ma , Angjun Tang , Zifeng Xiong , Fuxin Jiang","doi":"10.1016/j.eswa.2025.126856","DOIUrl":"10.1016/j.eswa.2025.126856","url":null,"abstract":"<div><div>This paper focuses on the micro-service migration problem with affinity, stemming from the cloud computing industry. Because of periodically creating and deleting micro-services to satisfy users’ demands, the deployment of micro-services in the cloud needs to be regularly adjusted, which is referred to as a micro-service migration. An optimal migration schedule should minimize the number of activated physical machines as well as maximize total internal invoking traffic (affinity). A cooperative multi-agent reinforcement learning (MARL) is proposed, which is enhanced by integrating Hindsight Reward Shaping and by fine-tuning the state encoder using a pre-trained ResNet model. The proposed MARL is validated on both synthetic datasets and real cloud traces of ByteDance and Alibaba, compared with four baseline algorithms: Migration Ant Colony Optimization, Migration Neighborhood Search, Single-Agent Reinforcement Learning, and the optimization solver CPLEX. Finally, an evaluation mechanism called Matching Score is proposed to explain the superior performance of MARL.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"273 ","pages":"Article 126856"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126881
Qing Zhu , Chenyu Han , Shan Liu , Yuze Li , Jianhua Che
With the advancement in artificial intelligence, robo-advisor systems have emerged as powerful tools for formulating financial product trading strategies and assisting investors in making rational investment decisions. Consequently, to reduce risk and provide investors greater returns in volatile markets, improving the performance of these systems has become a key research focus. This paper proposes an enhanced robo-advisor system that employs deep mathematical feature engineering to embed a hybrid mechanism for robust feature extraction. The system implements a novel integrated algorithm, where technical indicators are first decomposed using variational mode decomposition technology, followed by feature extraction through a deep convolutional neural network with an attention mechanism. The high-level features are then fed into a bidirectional gated recurrent unit network to predict returns on short-term time-scale financial products. The experimental results indicate that the proposed robo-advisor system achieves robust, remarkable return performance on several types of assets under different market conditions, and provides decision support for investors in managing asset risks and seeking cross-market investment opportunities.
{"title":"Artificial intelligence-driven financial innovation: A robo-advisor system for robust returns across diversified markets","authors":"Qing Zhu , Chenyu Han , Shan Liu , Yuze Li , Jianhua Che","doi":"10.1016/j.eswa.2025.126881","DOIUrl":"10.1016/j.eswa.2025.126881","url":null,"abstract":"<div><div>With the advancement in artificial intelligence, robo-advisor systems have emerged as powerful tools for formulating financial product trading strategies and assisting investors in making rational investment decisions. Consequently, to reduce risk and provide investors greater returns in volatile markets, improving the performance of these systems has become a key research focus. This paper proposes an enhanced robo-advisor system that employs deep mathematical feature engineering to embed a hybrid mechanism for robust feature extraction. The system implements a novel integrated algorithm, where technical indicators are first decomposed using variational mode decomposition technology, followed by feature extraction through a deep convolutional neural network with an attention mechanism. The high-level features are then fed into a bidirectional gated recurrent unit network to predict returns on short-term time-scale financial products. The experimental results indicate that the proposed robo-advisor system achieves robust, remarkable return performance on several types of assets under different market conditions, and provides decision support for investors in managing asset risks and seeking cross-market investment opportunities.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"274 ","pages":"Article 126881"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126880
Zipeng Zhang , Zhencai Zhu , Bin Meng , Zheng Yang , Mingke Wu , Xinyu Cheng , Binhong Li , Houguang Liu
Top caving is a crucial mining method for extracting thick coal seams, with the gangue content rate serving as a significant measure of effectiveness. However, the mixing of gangue with coal during the mining process results in economic waste. Therefore, accurate identification of gangue is essential to minimize this content. The detection of gangue encounters challenges due to inconsistent frequency representations arising from uncertain collapsing behavior, which consequently leads to low accuracy when utilizing vibration signals. To address this issue, this paper presents a deep-learning-based method for the efficient identification of collapsed coal and gangue vibration signals with high accuracy. The method comprises feature enhancement blocks, amplitude–frequency perception modules, and a classifier. The feature enhancement block prioritizes key signal sections, while the amplitude–frequency perception modules capture shock representations, and the classifier utilizes these features for decision-making. Additionally, a retention mechanism is incorporated to optimize model size and enhance inference speed. Comparative experiments and an ablation study show the method’s effectiveness, surpassing 25 baseline models with 93.17% accuracy and only 704.266 k parameters. Through the proposed method, this paper demonstrates a feasible solution for accurate and rapid identification of vibration signals, providing an exemplary direction for the future development of coal gangue identification.
{"title":"Intelligent coal gangue identification: A novel amplitude frequency sensitive neural network","authors":"Zipeng Zhang , Zhencai Zhu , Bin Meng , Zheng Yang , Mingke Wu , Xinyu Cheng , Binhong Li , Houguang Liu","doi":"10.1016/j.eswa.2025.126880","DOIUrl":"10.1016/j.eswa.2025.126880","url":null,"abstract":"<div><div>Top caving is a crucial mining method for extracting thick coal seams, with the gangue content rate serving as a significant measure of effectiveness. However, the mixing of gangue with coal during the mining process results in economic waste. Therefore, accurate identification of gangue is essential to minimize this content. The detection of gangue encounters challenges due to inconsistent frequency representations arising from uncertain collapsing behavior, which consequently leads to low accuracy when utilizing vibration signals. To address this issue, this paper presents a deep-learning-based method for the efficient identification of collapsed coal and gangue vibration signals with high accuracy. The method comprises feature enhancement blocks, amplitude–frequency perception modules, and a classifier. The feature enhancement block prioritizes key signal sections, while the amplitude–frequency perception modules capture shock representations, and the classifier utilizes these features for decision-making. Additionally, a retention mechanism is incorporated to optimize model size and enhance inference speed. Comparative experiments and an ablation study show the method’s effectiveness, surpassing 25 baseline models with 93.17% accuracy and only 704.266<!--> <!-->k parameters. Through the proposed method, this paper demonstrates a feasible solution for accurate and rapid identification of vibration signals, providing an exemplary direction for the future development of coal gangue identification.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"274 ","pages":"Article 126880"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126885
Tao Han, Xinyi Ding, Yili Fang
Truth inference of truth from crowdsourced data presents a formidable challenge that has been widely recognized in the field. Recently, there has been a surge in deep learning and Bayesian methods that rely on task features. However, these methods fail to function effectively in situations where task features are lacking or the relationship between task truth and task features is weak. Traditional data mining methods from crowdsourced triplet data either rely on strong model assumptions with poor data adaptability or use weak assumption models based on worker confusion matrices, neglecting the difficulty differences between tasks. To address this, we propose a novel DS-like model that leverages the strong adaptability of the weak model assumption in the DS model by using a task confusion matrix to describe the impact of task difficulty information. Furthermore, we overcome the data information bottleneck by capturing multimodal information about additional data. Our model exhibits weak coupling characteristics, enabling it to adapt to the features of different data. To tackle the complex issues arising from parameter reduction in our model, we introduce an innovative coordinate ascent algorithm, termed ”twice-EM.” Finally, we substantiate the effectiveness of our proposed approach through a comprehensive series of experiments, highlighting significant improvements in the accurate inference of truth, thereby attesting to the significance of our method.
{"title":"Multimodal information capture based truth inference network in crowdsourcing","authors":"Tao Han, Xinyi Ding, Yili Fang","doi":"10.1016/j.eswa.2025.126885","DOIUrl":"10.1016/j.eswa.2025.126885","url":null,"abstract":"<div><div>Truth inference of truth from crowdsourced data presents a formidable challenge that has been widely recognized in the field. Recently, there has been a surge in deep learning and Bayesian methods that rely on task features. However, these methods fail to function effectively in situations where task features are lacking or the relationship between task truth and task features is weak. Traditional data mining methods from crowdsourced triplet data either rely on strong model assumptions with poor data adaptability or use weak assumption models based on worker confusion matrices, neglecting the difficulty differences between tasks. To address this, we propose a novel DS-like model that leverages the strong adaptability of the weak model assumption in the DS model by using a task confusion matrix to describe the impact of task difficulty information. Furthermore, we overcome the data information bottleneck by capturing multimodal information about additional data. Our model exhibits weak coupling characteristics, enabling it to adapt to the features of different data. To tackle the complex issues arising from parameter reduction in our model, we introduce an innovative coordinate ascent algorithm, termed ”twice-EM.” Finally, we substantiate the effectiveness of our proposed approach through a comprehensive series of experiments, highlighting significant improvements in the accurate inference of truth, thereby attesting to the significance of our method.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"273 ","pages":"Article 126885"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126837
Wenbo Liu, Xiaoyun Qiao, Chunyu Zhao, Tao Deng, Fei Yan
The rapidly developing intelligent vehicles can provide appropriate driving strategies for assisted driving based on the driving scenarios. As pedestrians and vehicles are the primary participants in these scenarios, accurate detection and localization of both are essential for intelligent driving systems to make reliable decisions in dynamic environments. However, many existing detection algorithms for pedestrians and vehicles lack robustness in dynamic and complex traffic conditions, leading to missed detections and false alarms that pose significant safety risks. We categorize complex traffic scenarios into three typical challenges: long-distance, truncation, and occlusion, and also focus on improving the robustness of models in solving these problems. Inspired by human visual perception, we propose a plug-and-play enhancement stage for the preliminary processing of external information. Specifically, we design a Visual Attention Module (VAM) that enhances the model’s perceptual capabilities by mimicking optic chiasm. This module collects high-quality horizontal and vertical spatial features and efficiently interacts between horizontal and vertical spatial features. Additionally, we use a Feature Reconstruction Module (FRM) to improve the quality of features and enhance the model’s inference ability. To enable accurate performance evaluation of different models in complex traffic scenarios, we propose the VP-dataset, a dedicated dataset that incorporates challenging scenes for testing. Comprehensive experiments on the KITTI benchmark, Cityscapes dataset, and the proposed VP-dataset demonstrate that our model achieves state-of-the-art performance across various challenging scenarios.
{"title":"VP-YOLO: A human visual perception-inspired robust vehicle-pedestrian detection model for complex traffic scenarios","authors":"Wenbo Liu, Xiaoyun Qiao, Chunyu Zhao, Tao Deng, Fei Yan","doi":"10.1016/j.eswa.2025.126837","DOIUrl":"10.1016/j.eswa.2025.126837","url":null,"abstract":"<div><div>The rapidly developing intelligent vehicles can provide appropriate driving strategies for assisted driving based on the driving scenarios. As pedestrians and vehicles are the primary participants in these scenarios, accurate detection and localization of both are essential for intelligent driving systems to make reliable decisions in dynamic environments. However, many existing detection algorithms for pedestrians and vehicles lack robustness in dynamic and complex traffic conditions, leading to missed detections and false alarms that pose significant safety risks. We categorize complex traffic scenarios into three typical challenges: long-distance, truncation, and occlusion, and also focus on improving the robustness of models in solving these problems. Inspired by human visual perception, we propose a plug-and-play enhancement stage for the preliminary processing of external information. Specifically, we design a Visual Attention Module (VAM) that enhances the model’s perceptual capabilities by mimicking optic chiasm. This module collects high-quality horizontal and vertical spatial features and efficiently interacts between horizontal and vertical spatial features. Additionally, we use a Feature Reconstruction Module (FRM) to improve the quality of features and enhance the model’s inference ability. To enable accurate performance evaluation of different models in complex traffic scenarios, we propose the VP-dataset, a dedicated dataset that incorporates challenging scenes for testing. Comprehensive experiments on the KITTI benchmark, Cityscapes dataset, and the proposed VP-dataset demonstrate that our model achieves state-of-the-art performance across various challenging scenarios.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"274 ","pages":"Article 126837"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Conducting condition monitoring for the whole flight process is of great significance to enhance the security and reliability of unmanned aerial vehicles (UAV). Existing fault detection approaches only focus on one or several specific flight phases instead of the entire flight process. Precise flight regime recognition is the prerequisite to realize cross-stage failure detection and implement status monitoring for the entire flight process. Nevertheless, UAV flight data has several specific characteristics such as significant sequence temporality, multivariate spatial associations, and sample imbalance of different flight phases, which pose a great challenge to the data analysis-based flight regime recognition. In this study, an end-to-end intelligent recognition approach named deep feature fusion network (DFF-Net) is developed. In DFF-Net, a series of specialized designs have been adopted to meet the unique characteristics of UAV flight data. First, a multivariate convolutional channel attention module is designed to model the spatial connections of different flight parameters. Subsequently, a cross-scale convolutional Transformer detector is developed to excavate comprehensive temporal information. This detector is in a pyramidal architecture and can recognize flight regimes with different durations by fusing multi-level features. In this detector, cross-scale temporal embedding and convolutional multi-head self-attention (CMSA) are specifically designed and combined to model the interaction of multi-scale local features and long-term temporal information. To address the problem of long-tailed sample distribution of different flight regimes, a novel dynamic hybrid class-balanced loss function is proposed to guide the model learning by simultaneously considering the marginal distribution and effective samples of different classes. Finally, in the inference stage, a priority-based interval detection and merging operation is designed to correct the short-term marking errors induced by data fluctuations to further improve the identification performance. Experimental results on the simulation and real flight data demonstrate that our approach can realize precise identification of UAV flight regimes.
{"title":"DFF-Net: An intelligent recognition network with high precision for unbalanced flight regimes of unmanned aerial vehicles","authors":"Shengdong Wang, Zhenbao Liu, Zhen Jia, Xinshang Qin","doi":"10.1016/j.eswa.2025.126929","DOIUrl":"10.1016/j.eswa.2025.126929","url":null,"abstract":"<div><div>Conducting condition monitoring for the whole flight process is of great significance to enhance the security and reliability of unmanned aerial vehicles (UAV). Existing fault detection approaches only focus on one or several specific flight phases instead of the entire flight process. Precise flight regime recognition is the prerequisite to realize cross-stage failure detection and implement status monitoring for the entire flight process. Nevertheless, UAV flight data has several specific characteristics such as significant sequence temporality, multivariate spatial associations, and sample imbalance of different flight phases, which pose a great challenge to the data analysis-based flight regime recognition. In this study, an end-to-end intelligent recognition approach named deep feature fusion network (DFF-Net) is developed. In DFF-Net, a series of specialized designs have been adopted to meet the unique characteristics of UAV flight data. First, a multivariate convolutional channel attention module is designed to model the spatial connections of different flight parameters. Subsequently, a cross-scale convolutional Transformer detector is developed to excavate comprehensive temporal information. This detector is in a pyramidal architecture and can recognize flight regimes with different durations by fusing multi-level features. In this detector, cross-scale temporal embedding and convolutional multi-head self-attention (CMSA) are specifically designed and combined to model the interaction of multi-scale local features and long-term temporal information. To address the problem of long-tailed sample distribution of different flight regimes, a novel dynamic hybrid class-balanced loss function is proposed to guide the model learning by simultaneously considering the marginal distribution and effective samples of different classes. Finally, in the inference stage, a priority-based interval detection and merging operation is designed to correct the short-term marking errors induced by data fluctuations to further improve the identification performance. Experimental results on the simulation and real flight data demonstrate that our approach can realize precise identification of UAV flight regimes.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"274 ","pages":"Article 126929"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126865
Zijie Lin, Siyuan Zhang, Zhichao Xia, Linbo Xie
Distributed fiber optic sensing has garnered significant attention in the field of perimeter security. However, existing research seldom addresses the unique challenges posed by long-distance detection, which include two critical issues for data-driven approaches: susceptibility to noise in complex environments and the rapid identification of multiple events within massive datasets. To address these challenges, this study proposes a spatiotemporal image-based method for external breakage recognition using long-distance distributed fiber optic sensing. For data preprocessing, Adaptive Signal Enhancement Denoising (ASED) is proposed to effectively reduce noise in spatiotemporal images converted from raw data. For the recognition model, Lightweight Spatiotemporal Perception Enhanced YOLO (LSPE-YOLO) is proposed, leveraging a one-stage network structure to facilitate fast multi-event recognition in spatiotemporal images. The proposed model integrates a space-to-depth strategy within its backbone network to enhance spatiotemporal awareness with fewer parameters. Additionally, Coordinate Attention (CA) is incorporated into the neck network, which better captures the long-range dependencies of spatiotemporal images. A realistic dataset was constructed by utilizing a 40km communication fiber-optic cable. Experiments show that the method proposed reaches 0.93 on mAP50. The number of parameters and Giga Floating Point of Operations (GFLOPs) are 2.8M and 7.6, respectively. There are obvious advantages in practical engineering applications.
{"title":"Spatiotemporal image-based method for external breakage event recognition in long-distance distributed fiber optic sensing","authors":"Zijie Lin, Siyuan Zhang, Zhichao Xia, Linbo Xie","doi":"10.1016/j.eswa.2025.126865","DOIUrl":"10.1016/j.eswa.2025.126865","url":null,"abstract":"<div><div>Distributed fiber optic sensing has garnered significant attention in the field of perimeter security. However, existing research seldom addresses the unique challenges posed by long-distance detection, which include two critical issues for data-driven approaches: susceptibility to noise in complex environments and the rapid identification of multiple events within massive datasets. To address these challenges, this study proposes a spatiotemporal image-based method for external breakage recognition using long-distance distributed fiber optic sensing. For data preprocessing, Adaptive Signal Enhancement Denoising (ASED) is proposed to effectively reduce noise in spatiotemporal images converted from raw data. For the recognition model, Lightweight Spatiotemporal Perception Enhanced YOLO (LSPE-YOLO) is proposed, leveraging a one-stage network structure to facilitate fast multi-event recognition in spatiotemporal images. The proposed model integrates a space-to-depth strategy within its backbone network to enhance spatiotemporal awareness with fewer parameters. Additionally, Coordinate Attention (CA) is incorporated into the neck network, which better captures the long-range dependencies of spatiotemporal images. A realistic dataset was constructed by utilizing a 40km communication fiber-optic cable. Experiments show that the method proposed reaches 0.93 on mAP50. The number of parameters and Giga Floating Point of Operations (GFLOPs) are 2.8M and 7.6, respectively. There are obvious advantages in practical engineering applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"273 ","pages":"Article 126865"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126869
Shlomi Efrati , Yoram Reich
This paper introduces a novel System Flow Centrality (SFC) index for evaluating node importance in network graphs, with a specific focus on system architecture analysis. Unlike traditional centrality measures such as betweenness centrality (BC), the SFC index considers all system paths and cycles, providing a more comprehensive assessment of a node’s influence within the network. We present both a basic SFC algorithm and an enhanced version that incorporates system element classification, allowing for more nuanced analysis of component properties. The proposed index is validated through application to various network topologies, including common IEEE bus system configurations and a real-world medical motor driver architecture. Comparative analysis with established centrality measures demonstrates the SFC index’s superior performance in identifying critical nodes, particularly in complex and asymmetric network structures. The SFC index shows promise as a valuable tool for multidisciplinary project teams, offering potential benefits in risk assessment, resource allocation, quality management optimization, and decision-making processes across diverse applications. This research contributes to the growing body of knowledge on network analysis and system architecture evaluation, providing a more accurate and system-oriented approach to quantifying node importance in complex networks.
{"title":"System flow centrality index for evaluating the influence of a given system element in a network graph","authors":"Shlomi Efrati , Yoram Reich","doi":"10.1016/j.eswa.2025.126869","DOIUrl":"10.1016/j.eswa.2025.126869","url":null,"abstract":"<div><div>This paper introduces a novel System Flow Centrality (SFC) index for evaluating node importance in network graphs, with a specific focus on system architecture analysis. Unlike traditional centrality measures such as betweenness centrality (BC), the SFC index considers all system paths and cycles, providing a more comprehensive assessment of a node’s influence within the network. We present both a basic SFC algorithm and an enhanced version that incorporates system element classification, allowing for more nuanced analysis of component properties. The proposed index is validated through application to various network topologies, including common IEEE bus system configurations and a real-world medical motor driver architecture. Comparative analysis with established centrality measures demonstrates the SFC index’s superior performance in identifying critical nodes, particularly in complex and asymmetric network structures. The SFC index shows promise as a valuable tool for multidisciplinary project teams, offering potential benefits in risk assessment, resource allocation, quality management optimization, and decision-making processes across diverse applications. This research contributes to the growing body of knowledge on network analysis and system architecture evaluation, providing a more accurate and system-oriented approach to quantifying node importance in complex networks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"274 ","pages":"Article 126869"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-20DOI: 10.1016/j.eswa.2025.126777
Waqas Ahmed, Ghulam Mustafa
The existing concepts of complex fuzzy sets (CFS), complex intuitionistic fuzzy sets (CIFS), complex Pythagorean fuzzy sets (CPFS), complex q-rung orthopair fuzzy sets, and complex linear Diophantine fuzzy sets (CLDFS) have numerous applications in diverse fields. However, these concepts have certain limitations, which make it difficult for decision-makers to deal with complicated real-life problems. To ease these restrictions, we introduce the concept of complex Pythagorean parameterized fuzzy sets (CPPFS) with the addition of reference parameters. The parameterizations of the CPPFS are efficient in modeling incomplete data in decision-making problems, providing valuable information to classify a physical system. Score functions and accuracy functions are defined over CPPFS. Several aggregation operators such as complex Pythagorean parameterized fuzzy weighted averaging (CPPFWA) operator, complex Pythagorean parameterized fuzzy weighted Geometric (CPPFWG) operator, complex Pythagorean parameterized fuzzy ordered weighted averaging (CPPFOWA) operator, complex Pythagorean parameterized fuzzy ordered weighted geometric (CPPFOWG) operator, complex Pythagorean parameterized fuzzy hybrid averaging (CPPFHA) operator, and complex Pythagorean parameterized fuzzy hybrid geometric (CPPFHG) operator are constructed with the properties such as idempotency, monotonicity, and boundedness. Real-life applications of the proposed concept are illustrated through the selection of sustainable housing designs and renewable energy systems. Moreover, the proposed methods are applied to the problem of supply chain management, digital crime and digital terrorism problem, and the selection of research grant projects. Comparative and sensitive analyses are performed to demonstrate the superiority, feasibility, and easiness of the proposed methods to the existing methods. The proposed methods provide accurate and effective results in decision-making problems.
{"title":"Complex Pythagorean parameterized fuzzy sets and their applications to countering digital crime and digital terrorism and supply chain management problem","authors":"Waqas Ahmed, Ghulam Mustafa","doi":"10.1016/j.eswa.2025.126777","DOIUrl":"10.1016/j.eswa.2025.126777","url":null,"abstract":"<div><div>The existing concepts of complex fuzzy sets (CFS), complex intuitionistic fuzzy sets (CIFS), complex Pythagorean fuzzy sets (CPFS), complex q-rung orthopair fuzzy sets, and complex linear Diophantine fuzzy sets (CLDFS) have numerous applications in diverse fields. However, these concepts have certain limitations, which make it difficult for decision-makers to deal with complicated real-life problems. To ease these restrictions, we introduce the concept of complex Pythagorean parameterized fuzzy sets (CPPFS) with the addition of reference parameters. The parameterizations of the CPPFS are efficient in modeling incomplete data in decision-making problems, providing valuable information to classify a physical system. Score functions and accuracy functions are defined over CPPFS. Several aggregation operators such as complex Pythagorean parameterized fuzzy weighted averaging (CPPFWA) operator, complex Pythagorean parameterized fuzzy weighted Geometric (CPPFWG) operator, complex Pythagorean parameterized fuzzy ordered weighted averaging (CPPFOWA) operator, complex Pythagorean parameterized fuzzy ordered weighted geometric (CPPFOWG) operator, complex Pythagorean parameterized fuzzy hybrid averaging (CPPFHA) operator, and complex Pythagorean parameterized fuzzy hybrid geometric (CPPFHG) operator are constructed with the properties such as idempotency, monotonicity, and boundedness. Real-life applications of the proposed concept are illustrated through the selection of sustainable housing designs and renewable energy systems. Moreover, the proposed methods are applied to the problem of supply chain management, digital crime and digital terrorism problem, and the selection of research grant projects. Comparative and sensitive analyses are performed to demonstrate the superiority, feasibility, and easiness of the proposed methods to the existing methods. The proposed methods provide accurate and effective results in decision-making problems.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"273 ","pages":"Article 126777"},"PeriodicalIF":7.5,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-19DOI: 10.1016/j.eswa.2025.126864
Maohuan Wang, Yu Meng, Lei Sun, Tao Zhang
It is challenging to predict the time series data with strong volatility. Aiming to deal with this issue, we propose an innovative hybrid forecasting framework called Temporal-Frequency Reconstruction (TFR) in this study. In this framework, the averaging operation is incorporated in seasonal-trend decomposition using Loess (STL), and uniform grouped singular spectrum analysis is developed. A novel decomposition algorithm is constructed by combining these two methods, referred to as aSTL-UGSSA. Firstly, the time series data is decomposed by aSTL-UGSSA to extract latent structure information. Then, these decomposition terms are predicted by gated recurrent unit (GRU) models. To improve the prediction accuracy, a novel marine predator framework embedding Adam algorithm (MPAdam) is proposed to optimize the parameters of GRU models. Further, we analyze the factors contributing to the strong performance of TFR. TFR can not only capture the trend and seasonal signals but also effectively extract information from the remainder component. MPAdam overcomes the problem of initialization sensitivity and converges rapidly. In the short-term and long-term forecasting tasks for single-seasonal and multi-seasonal data, TFR has outperformed the state-of-the-art time series forecasting models by a significant margin.
{"title":"Decomposition combining averaging seasonal-trend with singular spectrum analysis and a marine predator algorithm embedding Adam for time series forecasting with strong volatility","authors":"Maohuan Wang, Yu Meng, Lei Sun, Tao Zhang","doi":"10.1016/j.eswa.2025.126864","DOIUrl":"10.1016/j.eswa.2025.126864","url":null,"abstract":"<div><div>It is challenging to predict the time series data with strong volatility. Aiming to deal with this issue, we propose an innovative hybrid forecasting framework called Temporal-Frequency Reconstruction (TFR) in this study. In this framework, the averaging operation is incorporated in seasonal-trend decomposition using Loess (STL), and uniform grouped singular spectrum analysis is developed. A novel decomposition algorithm is constructed by combining these two methods, referred to as aSTL-UGSSA. Firstly, the time series data is decomposed by aSTL-UGSSA to extract latent structure information. Then, these decomposition terms are predicted by gated recurrent unit (GRU) models. To improve the prediction accuracy, a novel marine predator framework embedding Adam algorithm (MPAdam) is proposed to optimize the parameters of GRU models. Further, we analyze the factors contributing to the strong performance of TFR. TFR can not only capture the trend and seasonal signals but also effectively extract information from the remainder component. MPAdam overcomes the problem of initialization sensitivity and converges rapidly. In the short-term and long-term forecasting tasks for single-seasonal and multi-seasonal data, TFR has outperformed the state-of-the-art time series forecasting models by a significant margin.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"274 ","pages":"Article 126864"},"PeriodicalIF":7.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号