Engineering Applications of Artificial Intelligence最新文献_第6页

Neuro inspired deep learning based secure and energy efficient routing with autonomous intrusion prevention in wireless sensor networks 无线传感器网络中基于神经启发的深度学习的安全节能路由与自主入侵防御

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-18 DOI: 10.1016/j.engappai.2025.112783

A. Babu Karuppiah , Vijayalakshmi Nanjappan , R. RajaRaja , S. Vishnu Priyan

{"title":"Neuro inspired deep learning based secure and energy efficient routing with autonomous intrusion prevention in wireless sensor networks","authors":"A. Babu Karuppiah , Vijayalakshmi Nanjappan , R. RajaRaja , S. Vishnu Priyan","doi":"10.1016/j.engappai.2025.112783","DOIUrl":"10.1016/j.engappai.2025.112783","url":null,"abstract":"<div><div>Wireless Sensor Networks (WSNs) are crucial in mission-driven domains such as environmental monitoring, industrial control, and military surveillance. However, their open communication medium, constrained resources, and unattended deployment make them prone to routing-layer attacks. Existing security frameworks mostly rely on reactive intrusion detection systems or conventional deep learning models, which incur high computational overhead and fail to adapt effectively under dynamic network conditions. To overcome these limitations, this study proposes a Neuro-Inspired Deep Learning Framework based on Spiking Neural Networks (SNNs) for autonomous intrusion prevention and energy-aware routing. The proposed model leverages latency-based spike encoding of key behavioral metrics (e.g., residual energy, latency, routing frequency, and packet delivery ratio) and utilizes a Leaky Integrate-and-Fire neuron architecture for proactive vulnerability prediction. Implementation using the Network Simulator-3 (NS-3) simulation tool and validation on the Wireless Sensor Network Dataset (WSN-DS), the framework achieves 99.72 % prediction accuracy, 99.98 % precision, 99.33 % recall, and 99.12 % F1-score, outperforming existing studies in attack detection rate. The proposed Secure Energy-Aware Routing Metric (SEARM) protocol achieves an average energy consumption of 0.32 J and a packet delivery ratio of 99.1 % while maintaining performance across varying network sizes (30–150 nodes) and attack intensities (up to 50 %). Additionally, the model features a self-healing mechanism that reintegrates previously blocked nodes based on dynamic trust recovery. This research establishes a proactive, low-power, and intelligent security paradigm for WSNs and sets the foundation for future innovations in biologically inspired and scalable network protection strategies.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112783"},"PeriodicalIF":8.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Efficient template-separable hierarchical transformer tracking for edge computing 边缘计算的高效模板可分分层变压器跟踪

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-18 DOI: 10.1016/j.engappai.2025.112784

Yixin Xu , Wankou Yang

{"title":"Efficient template-separable hierarchical transformer tracking for edge computing","authors":"Yixin Xu , Wankou Yang","doi":"10.1016/j.engappai.2025.112784","DOIUrl":"10.1016/j.engappai.2025.112784","url":null,"abstract":"<div><div>In recent years, transformer-based visual tracking models have demonstrated substantial advancements in modeling capabilities. These approaches utilize the global feature representation of vision transformers to enhance information interaction during tracking. However, their high computational demands pose challenges for efficient deployment on resource-constrained platforms, such as mobile devices and robotic systems. To address this issue, we propose a novel model called OneStar, which refers to a template-branch separable vision transformer tracker designed to balance efficiency and accuracy. Unlike existing one-stream trackers that process the template at every frame, the proposed OneStar model performs template inference for feature extraction and information fusion only during the initialization stage, thereby reducing redundant computations in subsequent frames. Additionally, we devise a guided hierarchical architecture conducive to tracking and introduce a tracking token that effectively guides the weight ratios of multi-scale features. Furthermore, we offer a particularly lightweight model variant tailored for low-power edge computing devices. Extensive evaluations demonstrate that the proposed OneStar model surpasses state-of-the-art real-time trackers while achieving impressive speed. For example, the OneStar model achieves 70.0% Average Overlap (AO), a metric that measures tracking accuracy, on the Generic Object Tracking 10k (GOT-10k) dataset and operates four times faster than other high-performance trackers on edge computing devices.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112784"},"PeriodicalIF":8.0,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Choquet integral-based method for optimal selection of industrial wastewater management systems using linguistic interval-valued T-spherical fuzzy sets 基于Choquet积分的语言区间值t球模糊集工业废水管理系统优选方法

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112723

Amjid Khan, Jawad Ali

{"title":"Choquet integral-based method for optimal selection of industrial wastewater management systems using linguistic interval-valued T-spherical fuzzy sets","authors":"Amjid Khan, Jawad Ali","doi":"10.1016/j.engappai.2025.112723","DOIUrl":"10.1016/j.engappai.2025.112723","url":null,"abstract":"<div><div>Industrial wastewater management is a critical challenge due to the increasing environmental concerns and stringent regulatory requirements. Selecting an optimal wastewater treatment system involves multiple conflicting attributes, requiring robust decision-making approaches under uncertainty. This study employs the linguistic interval-valued T-spherical fuzzy (LIVt-SF) set theory to enhance the decision-making process for industrial wastewater management. To achieve this, novel aggregation operators, specifically the LIVt-SF Choquet integral averaging and LIVt-SF Choquet integral geometric operators, are introduced. These operators facilitate a more accurate representation of uncertainty by effectively capturing and modeling the interactions among decision attributes, rather than treating them as independent factors. This ensures a more realistic and informed evaluation in multiple attribute group decision-making (MAGDM) problems. Building on these operators, we propose a comprehensive MAGDM framework incorporating the Choquet integral method to model interdependencies among attributes. The effectiveness of the proposed approach is demonstrated through a real-world case study on industrial wastewater management system selection. Comparative analysis and sensitivity testing confirm the superiority and robustness of the model over existing methods, making it a valuable tool for sustainable and efficient decision-making.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112723"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual seismic image collaborative recognition algorithm based on deep learning 基于深度学习的双地震图像协同识别算法

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112800

Fanke Meng, Tong Jiang, SiXin Zhu, Li Wan

{"title":"Dual seismic image collaborative recognition algorithm based on deep learning","authors":"Fanke Meng, Tong Jiang, SiXin Zhu, Li Wan","doi":"10.1016/j.engappai.2025.112800","DOIUrl":"10.1016/j.engappai.2025.112800","url":null,"abstract":"<div><div>To address the inefficiencies and subjectivity of traditional manual interpretation in seismic data analysis, this paper introduces a deep learning-based dual image collaborative recognition (DICR) model. The model is based on an enhanced you only look once version 8 (YOLOv8) architecture with a dual-stream feature extraction network. A multi-task-optimized Cross Stage Partial Darknet-Path Aggregation Network(CSPDarknet-PANet) backbone processes seismic stacked velocity spectra and seismic trace set data in parallel. The multi-class detection head estimates the probability distribution of energy clusters in the velocity spectrum, while the geometric morphology analysis module analyzes the geometric morphology of seismic reflection events. A novel cross-modal correction mechanism implements a bidirectional feedback system using a velocity-time domain transformation matrix. Iterative parameter optimization continuously aligns detected energy clusters with corrected seismic reflection events. Real seismic datasets were employed for end-to-end evaluation experiments. Across 728 images affected by strong noise interference and waveform distortions, the DICR model achieves an average absolute localization error of 4.7 % (±1.3 %) for energy cluster centers. Furthermore, the structural similarity index measure (SSIM) for seismic reflection event reconstruction reaches 0.912, while processing efficiency is approximately 30 times higher than that of manual interpretation. By incorporating domain knowledge into the deep learning framework via a confidence fusion (a decision-level integration of velocity spectra and gather features using weighted fusion), this model develops an intelligent recognition system with physical interpretability. The error rate is maintained within a strict 5 % confidence interval, ensuring compliance with practical engineering accuracy requirements for seismic exploration.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112800"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A graph-based knowledge distillation framework for drug repurposing via multi-task learning 基于多任务学习的基于图的药物再利用知识蒸馏框架

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112752

Zahra Alaeddini , Parham Moradi , Bahram Sadeghi Bigham

{"title":"A graph-based knowledge distillation framework for drug repurposing via multi-task learning","authors":"Zahra Alaeddini , Parham Moradi , Bahram Sadeghi Bigham","doi":"10.1016/j.engappai.2025.112752","DOIUrl":"10.1016/j.engappai.2025.112752","url":null,"abstract":"<div><div>Biomedical Knowledge Graphs (BKGs) capture intricate interactions between biological entities, playing a crucial role in the repurposing of drugs. However, current BKG completion methods often face challenges in scalability, predictive performance, and computational efficiency. We propose a novel Graph-based Knowledge Distillation approach for Drug Repurposing via a Multi-Task Learning framework (GKDRMTL), to address these limitations. By leveraging a teacher–student knowledge distillation strategy, our model not only enhances predictive accuracy but also substantially reduces computational demands. Compared to the state-of-the-art baselines, the student model consistently demonstrates substantial efficiency gains, achieving ∼30–93 % faster training time per epoch, ∼75–99 % lower memory usage, ∼46–88 % faster inference time, while maintaining competitive accuracy. Evaluated on an extended HetioNet, a heterogeneous biomedical knowledge graph, GKDRMTL reached state-of-the-art results across multiple link prediction tasks, including drug–disease associations, drug-drug similarity, disease-disease similarity, and disease–gene associations. The teacher achieves near-perfect performance in Area under the Receiver Operating Characteristic Curve (ROC-AUC) of 0.9889, Area Under the Precision-Recall Curve (AUPR) of 0.9875, and Accuracy of 0.9876. While the student approximates teacher performance with ROC-AUC of 0.9739, AUPR of 0.9704, and Accuracy of 0.9673, despite its simplified architecture. These findings underscore the importance of integrating knowledge distillation with multi-task learning for efficient and high-performance biomedical link prediction. The code of the proposed method and data are available here: <span><span>https://github.com/Zahra-Alaeddini/GKDRMTL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112752"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive gradient-aware neural dynamics: Towards fast and accurate solutions for dynamic convex optimization 自适应梯度感知神经动力学：动态凸优化的快速和准确的解决方案

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112798

Chengze Jiang , Aiping Ye , Huiting He , Xiuchun Xiao , Cong Lin

{"title":"Adaptive gradient-aware neural dynamics: Towards fast and accurate solutions for dynamic convex optimization","authors":"Chengze Jiang , Aiping Ye , Huiting He , Xiuchun Xiao , Cong Lin","doi":"10.1016/j.engappai.2025.112798","DOIUrl":"10.1016/j.engappai.2025.112798","url":null,"abstract":"<div><div>Constrained Dynamic Convex Optimization (CDCO) represents a core challenge in many engineering applications, where the objective is to minimize a time-varying cost function subject to dynamically evolving constraints. While recent neural network-based methods have demonstrated potential in addressing CDCO, they still suffer from limitations in convergence and solution accuracy, which restrict their effectiveness in real-world deployments. To overcome these challenges, we propose an Adaptive Gradient-Aware Neural Dynamics (AGAND). As an artificial intelligence model derived from a branch of Hopfield networks, AGAND integrates a gradient-aware term with a time derivative term to enhance solution performance. Our AGAND uses gradient information and time-derivative data to achieve faster and more accurate solutions for CDCO. Besides, the convergence of the model is further boosted by introducing state-aware coefficient with gradient feedback mechanism. Theoretical analysis demonstrates the global convergence of the AGAND, along with a detailed complexity assessment. To further adapt AGAND for practical deployment, a discretization scheme is proposed to facilitate implementation on digital hardware. Comparative experiments with state-of-the-art methods illustrate the competitiveness of our AGAND in terms of convergence and accuracy, achieving Average Steady-state Residual Error (ASSRE) of <span><math><mrow><mn>3</mn><mo>.</mo><mn>10</mn><mo>×</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span> and Convergence Time (CT) of 0.04 s. Finally, a robot kinematics scheme and hyperspectral image target detection are formulated on the basis of our AGAND, demonstrating the feasibility and practical utility of the AGAND in real-world engineering problems.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112798"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A federated learning framework for arbitrary spatio-temporal graph neural networks 任意时空图神经网络的联邦学习框架

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112801

Heeyong Yoon , Kang-Wook Chon , Min-Soo Kim

{"title":"A federated learning framework for arbitrary spatio-temporal graph neural networks","authors":"Heeyong Yoon , Kang-Wook Chon , Min-Soo Kim","doi":"10.1016/j.engappai.2025.112801","DOIUrl":"10.1016/j.engappai.2025.112801","url":null,"abstract":"<div><div>The proliferation of mobile and Internet of Things (IoT) devices has resulted in a surge of time-series sensor data, posing significant challenges for centralized data collection and processing. This challenge has driven the adoption of edge computing, which offloads data processing to mid-level servers located at the edge of the Internet, thereby reducing computation and bandwidth demands. Federated learning has emerged as a promising method for training models in edge-computing environments. Recently, spatio-temporal graph neural networks (STGNNs) have shown impressive performance in time-series prediction, yet their application in edge computing is limited by the complexity of adapting them to distributed environments. To address this gap, we propose FedSTGNN (Federated Spatio-Temporal Graph Neural Network), a universal framework that converts existing centralized STGNN models into a federated learning version. We formulate the common STGNN training process using matrix operations, employ graph-based imputation methods to handle missing sensor values at edge servers, and facilitate the transition from centralized to federated STGNNs. Our comprehensive evaluations demonstrate that FedSTGNN not only preserves the prediction accuracy of the original STGNN models but is also significantly more network-efficient than the competing model. Furthermore, the framework proves its robustness in challenging real-world scenarios, including sparse graphs, long-term forecasting, and dynamic server participation. Our work presents a practical, robust, and universal solution for deploying STGNNs into various edge computing applications.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112801"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data-driven parameterization of fault detection algorithms in high voltage direct current systems using classification trees 基于分类树的高压直流系统故障检测算法的数据驱动参数化

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112776

Juan Ramón Camarillo-Peñaranda , Gustavo Cezimbra Borges Leal , Bruno Wanderley França , Kleber Melo e Silva

{"title":"Data-driven parameterization of fault detection algorithms in high voltage direct current systems using classification trees","authors":"Juan Ramón Camarillo-Peñaranda , Gustavo Cezimbra Borges Leal , Bruno Wanderley França , Kleber Melo e Silva","doi":"10.1016/j.engappai.2025.112776","DOIUrl":"10.1016/j.engappai.2025.112776","url":null,"abstract":"<div><div>Reliable fault detection in High Voltage Direct Current (HVDC) systems is critical, but its effectiveness depends on the optimal parameterization of protection algorithms. Traditionally, this parameter selection is a heuristic process, reliant on subjective, experience-based tuning that lacks objectivity and reproducibility. This paper addresses this gap by introducing a novel data-driven framework to automate the parameterization process, deliberately distinguishing its scope from the development of new detection algorithms. Within this framework, Classification and Regression Trees (CART) are applied to four prominent non-unit protection techniques: the Rate of Change of Current (ROCOC), the Rate of Change of Voltage (ROCOV), the reactor voltage-based method (L), and Mathematical Morphology (MM). The models are trained on extensive fault data from both Line-Commutated Converter (LCC) and Modular Multilevel Converter (MMC) systems, simulated in PSCAD/EMTDC (Power Systems Computer Aided Design/Electromagnetic Transients including DC). This process yields optimized, transparent decision trees that provide directly implementable if-else rules for protection relays. The efficacy of the CART-derived parameters was rigorously validated using a Finite State Machine (FSM) implementation against a comprehensive suite of unseen fault scenarios. The results confirm the framework’s effectiveness, identifying ROCOV as the superior algorithm for the LCC system and ROCOC for the MMC system. This outcome highlights the approach’s ability to produce technology-specific solutions. By replacing a subjective art with a systematic and objective science, the proposed framework offers a reproducible and interpretable pathway to enhancing the reliability and performance of protection schemes in modern HVDC grids.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112776"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel dual-channel model with adaptive multi-scale attention for time series forecasting 一种具有自适应多尺度关注的双通道时间序列预测模型

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112803

Shuqing Wang , Jinghao Lu , Ren Wang , Xiaofeng Zhang , Hua Wang , Yujuan Sun

{"title":"A novel dual-channel model with adaptive multi-scale attention for time series forecasting","authors":"Shuqing Wang , Jinghao Lu , Ren Wang , Xiaofeng Zhang , Hua Wang , Yujuan Sun","doi":"10.1016/j.engappai.2025.112803","DOIUrl":"10.1016/j.engappai.2025.112803","url":null,"abstract":"<div><div>Time series forecasting plays a crucial role in various domains, including finance, traffic management, energy, and healthcare. However, as application scenarios continue to expand, the complexity of time series data has significantly increased, posing substantial challenges in capturing trend fluctuations of multivariate features and the dynamic relationships among them. To address these issues, this paper proposes a novel architecture–DASformer (<strong>D</strong>ual-Channel model with <strong>A</strong>daptive multi-<strong>S</strong>cale attention) - which enhances time series analysis by leveraging a dual-channel multivariate extractor and an adaptive multi-scale attention mechanism. Specifically, the dual-channel multivariate extractor comprises two independent yet interactive streams, focusing on capturing information at different levels of the time series, thereby effectively decoupling complex dynamic relationships. Moreover, to alleviate the problem of feature forgetting and loss in the long-term trend stream, the model incorporates an adaptive multi-scale attention module. This module adopts multi-scale processing and a dynamic weighting mechanism to learn dependencies across different scales and effectively capture their dynamic variations. Experimental results show that DASformer consistently achieves state-of-the-art performance on nine widely used benchmark datasets, delivering superior prediction accuracy, particularly in long-term forecasting tasks. The source code is available at: <span><span>https://github.com/LDU-TSA/DASformer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112803"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Dual-Population Constrained Multi-Objective Evolutionary Algorithm with Success Incentive Mechanism and its application to uncertain multimodal transportation problems 具有成功激励机制的双种群约束多目标进化算法及其在不确定多式联运问题中的应用

IF 8 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-10-17 DOI: 10.1016/j.engappai.2025.112586

Zhe Yang , Libao Deng , Yuanzhu Di , Chunlei Li , Yifan Qin , Lili Zhang

{"title":"A Dual-Population Constrained Multi-Objective Evolutionary Algorithm with Success Incentive Mechanism and its application to uncertain multimodal transportation problems","authors":"Zhe Yang , Libao Deng , Yuanzhu Di , Chunlei Li , Yifan Qin , Lili Zhang","doi":"10.1016/j.engappai.2025.112586","DOIUrl":"10.1016/j.engappai.2025.112586","url":null,"abstract":"<div><div>The evolution of the transportation industry has heightened the focus on environmentally sustainable multimodal transport, particularly in addressing carbon emissions. In modern logistics, path planning under uncertainty has become a pivotal research area. This paper proposes a multi-objective, multi-constraint optimization model for multimodal transport that aims to concurrently minimize cost, carbon emissions, and time. The model accounts for numerous operational constraints, including timetables, as well as dual sources of uncertainty from demand and the transport environment. To solve this complex problem, this paper introduces a new algorithmic framework. The proposed algorithm, a Dual-Population Constrained Multi-Objective Evolutionary Algorithm with a Success Incentive Mechanism (DSCMOEA), integrates three key innovations: a universal priority-based encoding/decoding adapter, a specialized constraint-handling architecture, and an adaptive operator selection mechanism. The adapter is central to the framework, enabling continuous-domain evolutionary algorithms to solve the discrete transport problem without internal modification. This approach also provides the versatility to handle various uncertainty paradigms through a multi-scenario simulation context. Experimental analysis validates the superiority of the proposed algorithm against eight established competitors, demonstrating its effectiveness in solving complex multimodal transport problems under uncertainty.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"162 ","pages":"Article 112586"},"PeriodicalIF":8.0,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145333687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0