Expert Systems with Applications最新文献_第5页

Object search strategy for service robots with knowledge-based viewpoint selection and hierarchical action decisions 基于知识的视点选择和分层行动决策的服务机器人目标搜索策略

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-05 DOI: 10.1016/j.eswa.2026.131538

Yuhao Wang, Guohui Tian

Service robots are frequently tasked with searching for target objects relevant to specific operations. However, the dynamic nature of object locations poses significant challenges for precise localization and tracking. To address this, we propose a unified framework for efficient object search and navigation that integrates viewpoint selection, dynamic map construction, and adaptive hierarchical planning. Our method constructs a visual-topological map (VTMap) that fuses prior knowledge, object-room and object-object co-occurrence statistics, and spatial probability distributions modeled via Gaussian Mixture Models (GMM). The robot continuously generates and updates a room-level probability map, enabling systematic selection of optimal viewpoints. This process maximizes the likelihood of target detection while minimizing travel distance through a utility-based strategy. Multimodal sensory observations are represented as graph nodes, with navigation actions encoded as edges, supporting accurate localization and action planning. To complement global planning, we introduce a hierarchical search strategy that unifies long-term exploration objectives with adaptive local exploration informed by imitation learning. The agent dynamically adjusts its search direction by integrating prior experiences with real-time sensory cues. Local exploration is formulated as a partially observable Markov decision process (POMDP), guided by spatial memory and semantic targets. Furthermore, action cost modeling and an auxiliary inflection point prediction task refine the local exploration process, enabling the system to flexibly transition between global and local search strategies. Collectively, these components facilitate robust and efficient object-oriented navigation in complex and dynamic environments.

服务机器人的任务通常是搜索与特定操作相关的目标物体。然而，物体位置的动态性对精确定位和跟踪提出了重大挑战。为了解决这个问题，我们提出了一个统一的高效目标搜索和导航框架，该框架集成了视点选择、动态地图构建和自适应分层规划。我们的方法构建了一个视觉拓扑地图（VTMap），该地图融合了先验知识、对象空间和对象共现统计以及通过高斯混合模型（GMM）建模的空间概率分布。机器人不断生成和更新房间级别的概率图，从而系统地选择最佳视点。这个过程最大限度地提高了目标检测的可能性，同时通过基于效用的策略最小化了旅行距离。多模态感官观察被表示为图节点，导航动作被编码为边，支持精确的定位和行动计划。为了补充全局规划，我们引入了一种分层搜索策略，该策略将长期探索目标与模仿学习的适应性局部探索相结合。智能体通过整合先验经验和实时感知线索来动态调整其搜索方向。局部探索是由空间记忆和语义目标引导的部分可观察马尔可夫决策过程（POMDP）。此外，行动成本模型和辅助拐点预测任务改进了局部搜索过程，使系统能够灵活地在全局和局部搜索策略之间转换。总的来说，这些组件有助于在复杂和动态的环境中实现健壮和高效的面向对象导航。

{"title":"Object search strategy for service robots with knowledge-based viewpoint selection and hierarchical action decisions","authors":"Yuhao Wang, Guohui Tian","doi":"10.1016/j.eswa.2026.131538","DOIUrl":"10.1016/j.eswa.2026.131538","url":null,"abstract":"<div><div>Service robots are frequently tasked with searching for target objects relevant to specific operations. However, the dynamic nature of object locations poses significant challenges for precise localization and tracking. To address this, we propose a unified framework for efficient object search and navigation that integrates viewpoint selection, dynamic map construction, and adaptive hierarchical planning. Our method constructs a visual-topological map (VTMap) that fuses prior knowledge, object-room and object-object co-occurrence statistics, and spatial probability distributions modeled via Gaussian Mixture Models (GMM). The robot continuously generates and updates a room-level probability map, enabling systematic selection of optimal viewpoints. This process maximizes the likelihood of target detection while minimizing travel distance through a utility-based strategy. Multimodal sensory observations are represented as graph nodes, with navigation actions encoded as edges, supporting accurate localization and action planning. To complement global planning, we introduce a hierarchical search strategy that unifies long-term exploration objectives with adaptive local exploration informed by imitation learning. The agent dynamically adjusts its search direction by integrating prior experiences with real-time sensory cues. Local exploration is formulated as a partially observable Markov decision process (POMDP), guided by spatial memory and semantic targets. Furthermore, action cost modeling and an auxiliary inflection point prediction task refine the local exploration process, enabling the system to flexibly transition between global and local search strategies. Collectively, these components facilitate robust and efficient object-oriented navigation in complex and dynamic environments.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"313 ","pages":"Article 131538"},"PeriodicalIF":7.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154276","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}

引用次数: 0

Hybrid intelligence–driven global path planning for ships in complex maritime environments 复杂海洋环境下船舶混合智能驱动的全局路径规划

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-05 DOI: 10.1016/j.eswa.2026.131473

Jiao Liu , Kaige Zhu , Yuanqiang Zhang , Miao Gao , Pengjun Zheng

Global ship path planning in complex maritime environments is challenged by dynamic disturbances, vessel-specific constraints, and long-range trajectory dependencies. This study develops an integrated hybrid planning framework that combines deep generative modeling with rule-based optimization. Automatic identification system trajectory time series are first transformed into Gramian Angular Field images to enhance spatio-temporal feature extraction. Vessel type and length are encoded as one-hot vectors and introduced as conditional variables, enabling personalized path generation. These inputs are processed by a Multi-Head Attention–based Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (MHA-cWGAN-GP), in which multi-head attention is used to model long-range dependencies, and conditional Generative Adversarial Network (cGAN) training together with a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) objective is adopted to improve conditioning behavior and training robustness. The model generates initial navigation paths, which are further refined using an A* search procedure that incorporates wind and current disturbances, as well as constraints such as static obstacles, water depth, and Traffic Separation Scheme (TSS) regulations. The final path is smoothed to ensure feasibility and compliance. In case studies for the Ningbo–Zhoushan Port and Yangtze River Estuary, the hybrid planner reduces the number of search nodes from 45 to 57 to 29–35 while simultaneously enforcing TSS, water-depth, wind, and current constraints, with only about a 3–4% increase in path length relative to classical A* and Dijkstra algorithms. The results indicate that the proposed framework effectively integrates learning and optimization, offering a practical and intelligent solution for real-world maritime path planning.

在复杂的海洋环境中，全球船舶路径规划受到动态干扰、船舶特定约束和远程轨迹依赖的挑战。本研究开发了一个集成的混合规划框架，将深度生成建模与基于规则的优化相结合。首先将自动识别系统的轨迹时间序列转化为格莱曼角场图像，增强时空特征提取。船舶类型和长度被编码为单热向量，并作为条件变量引入，从而实现个性化路径生成。这些输入通过基于多头注意力的Wasserstein梯度惩罚条件生成对抗网络（mfa - cwgan - gp）进行处理，其中多头注意力用于建立远程依赖关系模型，并采用条件生成对抗网络（cGAN）训练与WGAN-GP目标相结合来提高条件反射行为和训练鲁棒性。该模型生成初始导航路径，并使用A*搜索程序进一步优化，该搜索程序包含风和电流干扰，以及静态障碍物、水深和交通分道制（TSS）法规等约束条件。最后的路径被平滑以确保可行性和合规性。以宁波-舟山港和长江口为例，混合规划器将搜索节点数从45 ~ 57个减少到29 ~ 35个，同时执行TSS、水深、风和电流约束，路径长度仅比经典a *和Dijkstra算法增加约3 ~ 4%。结果表明，该框架有效地将学习与优化相结合，为现实世界的海上路径规划提供了实用的智能解决方案。

{"title":"Hybrid intelligence–driven global path planning for ships in complex maritime environments","authors":"Jiao Liu , Kaige Zhu , Yuanqiang Zhang , Miao Gao , Pengjun Zheng","doi":"10.1016/j.eswa.2026.131473","DOIUrl":"10.1016/j.eswa.2026.131473","url":null,"abstract":"<div><div>Global ship path planning in complex maritime environments is challenged by dynamic disturbances, vessel-specific constraints, and long-range trajectory dependencies. This study develops an integrated hybrid planning framework that combines deep generative modeling with rule-based optimization. Automatic identification system trajectory time series are first transformed into Gramian Angular Field images to enhance spatio-temporal feature extraction. Vessel type and length are encoded as one-hot vectors and introduced as conditional variables, enabling personalized path generation. These inputs are processed by a Multi-Head Attention–based Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (MHA-cWGAN-GP), in which multi-head attention is used to model long-range dependencies, and conditional Generative Adversarial Network (cGAN) training together with a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) objective is adopted to improve conditioning behavior and training robustness. The model generates initial navigation paths, which are further refined using an A* search procedure that incorporates wind and current disturbances, as well as constraints such as static obstacles, water depth, and Traffic Separation Scheme (TSS) regulations. The final path is smoothed to ensure feasibility and compliance. In case studies for the Ningbo–Zhoushan Port and Yangtze River Estuary, the hybrid planner reduces the number of search nodes from 45 to 57 to 29–35 while simultaneously enforcing TSS, water-depth, wind, and current constraints, with only about a 3–4% increase in path length relative to classical A* and Dijkstra algorithms. The results indicate that the proposed framework effectively integrates learning and optimization, offering a practical and intelligent solution for real-world maritime path planning.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131473"},"PeriodicalIF":7.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122663","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}

引用次数: 0

MSIF-SSTR: A “Quick smuggler” smuggling speedboat trajectory recognition method based on multi-source information fusion MSIF-SSTR：基于多源信息融合的“快速走私者”走私快艇轨迹识别方法

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131525

Zhuhua Hu , Yifeng Sun , Yaochi Zhao , Wei Wu , Lingkai Kong , Keli Chen

Cooperating with maritime administrative departments to identify smuggling activities and enhance the control ability of nearshore vessels holds significant practical significance. However, existing research mostly relies on basic AIS data and simple features, making it difficult to deal with complex vessel behaviors. Especially when identifying covert and flexible smuggling activities, it is prone to misjudgment and has limited effectiveness. In real-world enforcement, distinguishing truly suspicious “Quick Smuggler” smuggling from benign high-speed transit requires modeling subtle, deep-level spatio-temporal cues that couple motion dynamics with external conditions (e.g., wind, wave, visibility) and context. Simple linear mappings and shallow temporal encoders often overfit speed bursts or local detours, causing elevated false alarms. By contrast, dilated-convolutional receptive fields in TCNs capture multi-scale temporal dependencies efficiently, while KAN layers provide adaptive nonlinear function bases to fit complex, locally varying trajectory patterns. This synergy is particularly suited to covert nighttime operations under shifting sea states, where genuine smuggling exhibits trajectory micro-structures and weather-conditioned behaviors that are hard to emulate by normal craft. To address these challenges, this study proposes a Multi-Source Information Fusion-based “Quick Smuggler” Smuggling Speedboat Trajectory Recognition method (MSIF-SSTR). First, we construct the HN_BF dataset, comprising real-world nighttime radar trajectories from the Qiongzhou Strait and corresponding meteorological data. Next, parallel TCN networks are employed to separately extract motion features, and meteorological features, enabling the model to better capture global temporal dependencies during feature extraction. Finally, the fused features are fed into an LSTM for classification, while a Kolmogorov-arnold networks (KAN) module replaces traditional fully connected layers to improve the representation of complex trajectory patterns. Experimental results demonstrate that MSIF-SSTR achieves F1-scores exceeding 94.2% on the HN_BF dataset, outperforming state-of-the-art methods with higher computational efficiency. Field applications confirm the model’s robustness.

与海事管理部门合作，查清走私活动，提高近岸船舶的管制能力，具有重要的现实意义。然而，现有的研究大多依赖于基本的AIS数据和简单的特征，难以处理复杂的船舶行为。特别是在识别隐蔽和灵活的走私活动时，容易出现误判，效果有限。在现实世界的执法中，区分真正可疑的“快速走私者”走私和良性的高速运输需要建模微妙的、深层次的时空线索，这些线索将运动动力学与外部条件（例如，风、波浪、能见度）和环境相结合。简单的线性映射和浅时间编码器经常过拟合速度突发或局部弯路，导致误报警升高。相比之下，tcnn中的扩展卷积接受场有效地捕获多尺度时间依赖性，而KAN层提供自适应非线性函数基来拟合复杂的局部变化轨迹模式。这种协同作用特别适合在变化的海况下进行夜间秘密行动，因为真正的走私显示出常规船只难以模仿的轨迹微观结构和受天气影响的行为。针对这些挑战，本研究提出了一种基于多源信息融合的“快速走私者”走私快艇轨迹识别方法（MSIF-SSTR）。首先，我们构建了HN_BF数据集，该数据集包含琼州海峡真实的夜间雷达轨迹和相应的气象数据。其次，采用并行TCN网络分别提取运动特征和气象特征，使模型在特征提取过程中更好地捕获全局时间依赖关系。最后，将融合的特征输入到LSTM中进行分类，而Kolmogorov-arnold网络（KAN）模块取代传统的全连接层，以改善复杂轨迹模式的表示。实验结果表明，MSIF-SSTR在HN_BF数据集上的f1得分超过94.2%，计算效率高于现有方法。现场应用验证了模型的鲁棒性。

{"title":"MSIF-SSTR: A “Quick smuggler” smuggling speedboat trajectory recognition method based on multi-source information fusion","authors":"Zhuhua Hu , Yifeng Sun , Yaochi Zhao , Wei Wu , Lingkai Kong , Keli Chen","doi":"10.1016/j.eswa.2026.131525","DOIUrl":"10.1016/j.eswa.2026.131525","url":null,"abstract":"<div><div>Cooperating with maritime administrative departments to identify smuggling activities and enhance the control ability of nearshore vessels holds significant practical significance. However, existing research mostly relies on basic AIS data and simple features, making it difficult to deal with complex vessel behaviors. Especially when identifying covert and flexible smuggling activities, it is prone to misjudgment and has limited effectiveness. In real-world enforcement, distinguishing truly suspicious “Quick Smuggler” smuggling from benign high-speed transit requires modeling subtle, deep-level spatio-temporal cues that couple motion dynamics with external conditions (e.g., wind, wave, visibility) and context. Simple linear mappings and shallow temporal encoders often overfit speed bursts or local detours, causing elevated false alarms. By contrast, dilated-convolutional receptive fields in TCNs capture multi-scale temporal dependencies efficiently, while KAN layers provide adaptive nonlinear function bases to fit complex, locally varying trajectory patterns. This synergy is particularly suited to covert nighttime operations under shifting sea states, where genuine smuggling exhibits trajectory micro-structures and weather-conditioned behaviors that are hard to emulate by normal craft. To address these challenges, this study proposes a Multi-Source Information Fusion-based “Quick Smuggler” Smuggling Speedboat Trajectory Recognition method (MSIF-SSTR). First, we construct the HN_BF dataset, comprising real-world nighttime radar trajectories from the Qiongzhou Strait and corresponding meteorological data. Next, parallel TCN networks are employed to separately extract motion features, and meteorological features, enabling the model to better capture global temporal dependencies during feature extraction. Finally, the fused features are fed into an LSTM for classification, while a Kolmogorov-arnold networks (KAN) module replaces traditional fully connected layers to improve the representation of complex trajectory patterns. Experimental results demonstrate that MSIF-SSTR achieves F1-scores exceeding 94.2% on the HN_BF dataset, outperforming state-of-the-art methods with higher computational efficiency. Field applications confirm the model’s robustness.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131525"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192599","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}

引用次数: 0

Multi-objective hybrid intelligent optimization for time-delay switched systems 时滞切换系统的多目标混合智能优化

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131384

Huan Li, Ying Jin, Chi Zhang, Jun Fu

The multi-objective dynamic optimization of time-delay switched systems (TDSS) presents considerable challenges, stemming from the complex interplay among time-delay-induced dynamic lag, discrete switching logic, and conflicting performance objectives. To address these difficulties, a multi-objective hybrid intelligent optimization method is proposed, aimed at generating a well-distributed and comprehensive Pareto solution set. First, an improved Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) is developed, which adopts uniformly distributed weight vectors to ensure comprehensive Pareto front coverage and integrates neighborhood-based collaboration to improve computational efficiency. The algorithm also incorporates a constraint-handling mechanism to maintain solution feasibility throughout the search process, thereby enabling effective global exploration within the feasible domain. Then, Hamiltonian-based costate analysis is employed to derive exact gradients of the scalarized objective function with respect to switching times and control parameters, providing a theoretical basis for precise local refinement of candidate solutions. Finally, numerical simulations on a nonlinear TDSS validate the effectiveness of the multi-objective hybrid intelligent optimization method, as it generates a more uniform Pareto front, delivers better objective performance than the MOEA/D and ϵ-constrained method.

时滞切换系统（TDSS）的多目标动态优化面临着很大的挑战，这主要是由于时滞引起的动态滞后、离散的切换逻辑和相互冲突的性能目标之间的复杂相互作用。针对这些困难，提出了一种多目标混合智能优化方法，旨在生成分布良好的综合Pareto解集。首先，提出了一种改进的基于分解的多目标进化算法（MOEA/D），该算法采用均匀分布的权向量保证了Pareto前的全面覆盖，并结合基于邻域的协作提高了计算效率。该算法还引入了约束处理机制，在整个搜索过程中保持解的可行性，从而在可行域内实现有效的全局探索。然后，利用基于哈密顿的协态分析，推导出标化后的目标函数相对于切换时间和控制参数的精确梯度，为候选解的精确局部细化提供理论依据。最后，在非线性TDSS上进行了数值仿真，验证了多目标混合智能优化方法的有效性，与MOEA/D和ϵ-constrained方法相比，该方法产生了更均匀的Pareto前沿，具有更好的目标性能。

{"title":"Multi-objective hybrid intelligent optimization for time-delay switched systems","authors":"Huan Li, Ying Jin, Chi Zhang, Jun Fu","doi":"10.1016/j.eswa.2026.131384","DOIUrl":"10.1016/j.eswa.2026.131384","url":null,"abstract":"<div><div>The multi-objective dynamic optimization of time-delay switched systems (TDSS) presents considerable challenges, stemming from the complex interplay among time-delay-induced dynamic lag, discrete switching logic, and conflicting performance objectives. To address these difficulties, a multi-objective hybrid intelligent optimization method is proposed, aimed at generating a well-distributed and comprehensive Pareto solution set. First, an improved Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) is developed, which adopts uniformly distributed weight vectors to ensure comprehensive Pareto front coverage and integrates neighborhood-based collaboration to improve computational efficiency. The algorithm also incorporates a constraint-handling mechanism to maintain solution feasibility throughout the search process, thereby enabling effective global exploration within the feasible domain. Then, Hamiltonian-based costate analysis is employed to derive exact gradients of the scalarized objective function with respect to switching times and control parameters, providing a theoretical basis for precise local refinement of candidate solutions. Finally, numerical simulations on a nonlinear TDSS validate the effectiveness of the multi-objective hybrid intelligent optimization method, as it generates a more uniform Pareto front, delivers better objective performance than the MOEA/D and ϵ-constrained method.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"311 ","pages":"Article 131384"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146190895","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}

引用次数: 0

PQS-BFL: A post-quantum secure blockchain-based federated learning framework PQS-BFL：一个后量子安全的基于区块链的联邦学习框架

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131449

Daniel Commey , Garth V. Crosby

Federated Learning (FL) enables collaborative model training while preserving data privacy, but its classical cryptographic underpinnings are vulnerable to quantum attacks. This vulnerability is particularly critical in sensitive domains like healthcare, where data requires long-term forward secrecy. This paper introduces PQS-BFL (Post-Quantum Secure Blockchain-based Federated Learning), a framework integrating post-quantum cryptography (PQC) with blockchain verification to secure FL against quantum adversaries. We employ ML-DSA-65 (standardized in FIPS 204, formerly Dilithium) signatures to authenticate model updates and leverage optimized smart contracts for decentralized validation. Designed for permissioned consortium environments (e.g., healthcare research networks), our framework ensures update integrity independent of the underlying ledger’s quantum resistance. Extensive evaluations on diverse datasets (MNIST, SVHN, HAR) demonstrate that PQS-BFL achieves feasible cryptographic operations (average PQC sign time: 0.65 ms, verify time: 0.53 ms) with a fixed signature size of 3309 Bytes. While blockchain integration incurs higher gas usage averaging 1.72 × 10⁶ units per update due to PQC verification complexity, we demonstrate that this cost is negligible in private consortium settings where gas fees are nominal. Importantly, the cryptographic overhead relative to transaction time remains minimal (typically  < 0.2%), confirming that PQS-BFL is a viable architecture for securing critical infrastructure against future quantum threats.

联邦学习（FL）支持协作模型训练，同时保护数据隐私，但其经典加密基础容易受到量子攻击。此漏洞在医疗保健等敏感领域尤其严重，因为这些领域的数据需要长期向前保密。本文介绍了PQS-BFL（后量子安全基于区块链的联邦学习），这是一个将后量子密码学（PQC）与区块链验证集成在一起的框架，以保护FL免受量子对手的攻击。我们使用ML-DSA-65（在FIPS 204中标准化，以前是diiliium）签名来验证模型更新，并利用优化的智能合约进行分散验证。我们的框架专为许可的联盟环境（例如，医疗保健研究网络）而设计，可确保独立于底层分类账的量子阻力的更新完整性。在不同数据集（MNIST， SVHN， HAR）上的广泛评估表明，PQS-BFL在固定签名大小为3309字节的情况下实现了可行的加密操作（平均PQC签名时间：0.65 ms，验证时间：0.53 ms）。虽然由于PQC验证的复杂性，区块链集成会导致更高的天然气使用量，平均每次更新1.72 × 106单位，但我们证明，在天然气费用微不足道的私人财团设置中，这种成本可以忽略不计。重要的是，相对于交易时间的加密开销仍然很小（通常为 <； 0.2%），这证实了PQS-BFL是保护关键基础设施免受未来量子威胁的可行架构。

{"title":"PQS-BFL: A post-quantum secure blockchain-based federated learning framework","authors":"Daniel Commey , Garth V. Crosby","doi":"10.1016/j.eswa.2026.131449","DOIUrl":"10.1016/j.eswa.2026.131449","url":null,"abstract":"<div><div>Federated Learning (FL) enables collaborative model training while preserving data privacy, but its classical cryptographic underpinnings are vulnerable to quantum attacks. This vulnerability is particularly critical in sensitive domains like healthcare, where data requires long-term forward secrecy. This paper introduces PQS-BFL (Post-Quantum Secure Blockchain-based Federated Learning), a framework integrating post-quantum cryptography (PQC) with blockchain verification to secure FL against quantum adversaries. We employ ML-DSA-65 (standardized in FIPS 204, formerly Dilithium) signatures to authenticate model updates and leverage optimized smart contracts for decentralized validation. Designed for permissioned consortium environments (e.g., healthcare research networks), our framework ensures update integrity independent of the underlying ledger’s quantum resistance. Extensive evaluations on diverse datasets (MNIST, SVHN, HAR) demonstrate that PQS-BFL achieves feasible cryptographic operations (average PQC sign time: 0.65 ms, verify time: 0.53 ms) with a fixed signature size of 3309 Bytes. While blockchain integration incurs higher gas usage averaging 1.72 × 10<sup>6</sup> units per update due to PQC verification complexity, we demonstrate that this cost is negligible in private consortium settings where gas fees are nominal. Importantly, the cryptographic overhead relative to transaction time remains minimal (typically  < 0.2%), confirming that PQS-BFL is a viable architecture for securing critical infrastructure against future quantum threats.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131449"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192558","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}

引用次数: 0

Vul2image: A quick image-inspired and CNN-based vulnerability detection system Vul2image：基于cnn的快速图像漏洞检测系统

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131468

Rong Ren , Mushi Zhou , Ni Liao , Bing Zhang , Guoyan Huang , Haitao He , Qian Wang

Given the accuracy of deep learning (DL) in image classification, some studies have applied DL algorithms to vulnerability detection by characterizing software source code as RGB images. However, effectively utilizing RGB images to store multiple code semantics remains a challenge, impacting the effectiveness of vulnerability detection. To address this, we developed Vul2image, a quick Image-inspired and CNN-based Vulnerability Detection System. By focusing on Potential Vulnerable Code Fragments (PVCFs) and their context code, Vul2image minimized interference from irrelevant information and achieved comprehensive coverage of vulnerability features. It constructed an RGB fine-grained image model incorporating textual, semantic, and structural information from code text, Control Dependency Graphs (CDGs), and Data Dependency Graphs (DDGs), resulting in improved detection efficiency. Evaluated on three datasets with increasing vulnerability types (including our self-collected, VulCNN, and Devign), Vul2image achieved the best results on our dataset, outperforming 9 classic (incl. 4 LLM-based) and 2 SOTA image-based detectors (VulCNN, VulGAI) and demonstrating performance comparable to 7 transformer-encoder-based methods, showing strong precision for specific vulnerability types. In practice, Vul2image was 35 times faster than VulCNN and successfully identified 21 reported and 5 unreported vulnerabilities in various real-world systems and software within 67,352,085 lines of code, showcasing its large-scale vulnerability detection capability.

考虑到深度学习在图像分类中的准确性，一些研究通过将软件源代码表征为RGB图像，将深度学习算法应用于漏洞检测。然而，有效地利用RGB图像存储多种代码语义仍然是一个挑战，影响了漏洞检测的有效性。为了解决这个问题，我们开发了Vul2image，一个快速的图像启发和基于cnn的漏洞检测系统。通过关注潜在脆弱代码片段（pvcf）及其上下文代码，Vul2image最大限度地减少了不相关信息的干扰，实现了对漏洞特征的全面覆盖。它构建了一个RGB细粒度图像模型，结合了来自代码文本、控制依赖图（cdg）和数据依赖图（ddg）的文本、语义和结构信息，从而提高了检测效率。在三个漏洞类型不断增加的数据集（包括我们的自收集、VulCNN和Devign）上进行评估，Vul2image在我们的数据集上取得了最好的结果，优于9个经典（包括4个基于llm的）和2个基于SOTA图像的检测器（VulCNN、VulGAI），并展示了与7种基于变压器编码器的方法相当的性能，对特定漏洞类型显示出很强的精度。在实践中，Vul2image比VulCNN快35倍，在67,352,085行代码中成功识别了各种现实系统和软件中的21个报告漏洞和5个未报告漏洞，展示了其大规模漏洞检测能力。

{"title":"Vul2image: A quick image-inspired and CNN-based vulnerability detection system","authors":"Rong Ren , Mushi Zhou , Ni Liao , Bing Zhang , Guoyan Huang , Haitao He , Qian Wang","doi":"10.1016/j.eswa.2026.131468","DOIUrl":"10.1016/j.eswa.2026.131468","url":null,"abstract":"<div><div>Given the accuracy of deep learning (DL) in image classification, some studies have applied DL algorithms to vulnerability detection by characterizing software source code as RGB images. However, effectively utilizing RGB images to store multiple code semantics remains a challenge, impacting the effectiveness of vulnerability detection. To address this, we developed Vul2image, a quick Image-inspired and CNN-based Vulnerability Detection System. By focusing on Potential Vulnerable Code Fragments (PVCFs) and their context code, Vul2image minimized interference from irrelevant information and achieved comprehensive coverage of vulnerability features. It constructed an RGB fine-grained image model incorporating textual, semantic, and structural information from code text, Control Dependency Graphs (CDGs), and Data Dependency Graphs (DDGs), resulting in improved detection efficiency. Evaluated on three datasets with increasing vulnerability types (including our self-collected, VulCNN, and Devign), Vul2image achieved the best results on our dataset, outperforming 9 classic (incl. 4 LLM-based) and 2 SOTA image-based detectors (VulCNN, VulGAI) and demonstrating performance comparable to 7 transformer-encoder-based methods, showing strong precision for specific vulnerability types. In practice, Vul2image was 35 times faster than VulCNN and successfully identified 21 reported and 5 unreported vulnerabilities in various real-world systems and software within 67,352,085 lines of code, showcasing its large-scale vulnerability detection capability.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131468"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192559","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}

引用次数: 0

Privacy preservation in face soft biometrics via attribute disentanglement 基于属性解缠的人脸软生物识别隐私保护

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131520

Yue Wang , Biao Jin , Zheyu Chen , Jinsen Lin , Zhiqiang Yao

Soft biometric privacy enhancement techniques have been widely adopted in face recognition systems to prevent attackers from inferring sensitive attributes such as gender, age, and ethnicity from facial images. Although existing facial attribute privacy protection methods can conceal multiple attributes simultaneously, they still face three key challenges: (1) precisely modifying target attributes while preserving non-target attributes; (2) achieving a balanced trade-off between privacy preservation and identity recognition utility; and (3) providing flexible and user-controllable options for attribute protection. To address these challenges, this paper proposes a novel face soft biometric privacy protection framework based on attribute disentanglement, which effectively conceals sensitive facial attributes while maximizing identity recognition accuracy. First, a mapping module guided by an attribute supervision loss is introduced to learn a disentangled latent space, where the semantic representations of different attributes are separated for controllable manipulation. Second, a face matcher combined with a dedicated face matching loss enforces identity consistency, enabling the model to preserve recognition utility while suppressing sensitive attribute leakage. Finally, an attribute selection module (ASM) is incorporated during the inference stage, allowing users to flexibly specify which attributes (e.g., gender, age, and smile) to protect, thereby enhancing adaptability and user-level controllability in privacy-sensitive applications. Experimental results demonstrate that the proposed method effectively safeguards the privacy of facial attributes while maintaining high identity recognition utility. Code is available at https://github.com/Forestmumu/PrivAD.

软生物特征隐私增强技术已广泛应用于人脸识别系统中，以防止攻击者从人脸图像中推断出性别、年龄和种族等敏感属性。现有的面部属性隐私保护方法虽然可以同时隐藏多个属性，但仍然面临三个关键挑战：(1)在保留非目标属性的同时精确修改目标属性；(2)在隐私保护和身份识别效用之间取得平衡；(3)提供灵活可控的属性保护选项。针对这些问题，本文提出了一种基于属性解纠缠的人脸软生物特征隐私保护框架，该框架在有效隐藏敏感人脸属性的同时，最大限度地提高了身份识别的准确性。首先，引入以属性监督损失为导向的映射模块学习解纠缠潜空间，在潜空间中分离不同属性的语义表示以进行可控操作；其次，人脸匹配器与专用的人脸匹配损失相结合，增强身份一致性，使模型在保持识别效用的同时抑制敏感属性泄漏。最后，在推理阶段引入属性选择模块（ASM），允许用户灵活指定需要保护的属性（如性别、年龄、微笑），从而增强隐私敏感应用的适应性和用户级可控性。实验结果表明，该方法有效地保护了人脸属性的隐私，同时保持了较高的身份识别效用。代码可从https://github.com/Forestmumu/PrivAD获得。

{"title":"Privacy preservation in face soft biometrics via attribute disentanglement","authors":"Yue Wang , Biao Jin , Zheyu Chen , Jinsen Lin , Zhiqiang Yao","doi":"10.1016/j.eswa.2026.131520","DOIUrl":"10.1016/j.eswa.2026.131520","url":null,"abstract":"<div><div>Soft biometric privacy enhancement techniques have been widely adopted in face recognition systems to prevent attackers from inferring sensitive attributes such as gender, age, and ethnicity from facial images. Although existing facial attribute privacy protection methods can conceal multiple attributes simultaneously, they still face three key challenges: (1) precisely modifying target attributes while preserving non-target attributes; (2) achieving a balanced trade-off between privacy preservation and identity recognition utility; and (3) providing flexible and user-controllable options for attribute protection. To address these challenges, this paper proposes a novel face soft biometric privacy protection framework based on attribute disentanglement, which effectively conceals sensitive facial attributes while maximizing identity recognition accuracy. First, a mapping module guided by an attribute supervision loss is introduced to learn a disentangled latent space, where the semantic representations of different attributes are separated for controllable manipulation. Second, a face matcher combined with a dedicated face matching loss enforces identity consistency, enabling the model to preserve recognition utility while suppressing sensitive attribute leakage. Finally, an attribute selection module (ASM) is incorporated during the inference stage, allowing users to flexibly specify which attributes (e.g., gender, age, and smile) to protect, thereby enhancing adaptability and user-level controllability in privacy-sensitive applications. Experimental results demonstrate that the proposed method effectively safeguards the privacy of facial attributes while maintaining high identity recognition utility. Code is available at <span><span>https://github.com/Forestmumu/PrivAD</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131520"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192851","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}

引用次数: 0

Adaptive bottleneck transformer for multimodal EEG, audio, and vision fusion 多模态脑电、音频和视觉融合的自适应瓶颈变压器

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131487

Sabina Bralina , Adnan Yazici , Cuntai Guan , Min-Ho Lee

Facial and speech expressions are primary cues for emotion recognition, while EEG provides a complementary neural perspective when external signals are ambiguous or absent. Although each modality contributes unique affective information, integrating such heterogeneous signals remains a major challenge in multimodal fusion research. To address this, the Adaptive Multimodal Bottleneck Transformer (AMBT) is introduced as a novel architecture, enabling efficient cross-modal interaction through adapters embedded within intermediate Transformer layers. These adapters 1) enhance stability by leveraging bottleneck tokens to prevent premature collapse, 2) enrich backbone representations while preserving unimodal capacity, 3) enable seamless integration across heterogeneous Transformer architectures, and 4) enable parameter-efficient training with fewer than 1% additional trainable parameters. AMBT was evaluated on three benchmark datasets: EAV (85.1%), CREMA-D (90.9%), and DEAP (98.7%), demonstrating competitive performance across all datasets. This results demonstrate the ability of AMBT to exploit complementary multimodal signals in a computationally efficient manner.

面部和言语表达是情绪识别的主要线索，而脑电图在外部信号模糊或缺失时提供了补充的神经视角。尽管每种情态都提供了独特的情感信息，但如何整合这种异质性信号仍然是多情态融合研究的主要挑战。为了解决这个问题，引入了自适应多模态瓶颈变压器（AMBT）作为一种新的体系结构，通过嵌入在中间变压器层中的适配器实现高效的跨模态交互。这些适配器1)通过利用瓶颈令牌来防止过早崩溃来增强稳定性，2)在保留单模态容量的同时丰富骨干表示，3)支持跨异构Transformer架构的无缝集成，以及4)使用少于1%的额外可训练参数实现参数高效训练。AMBT在三个基准数据集上进行了评估：EAV（85.1%）、CREMA-D（90.9%）和DEAP(98.7%)，在所有数据集上都表现出竞争力。这一结果证明了AMBT以计算效率高的方式利用互补多模态信号的能力。

{"title":"Adaptive bottleneck transformer for multimodal EEG, audio, and vision fusion","authors":"Sabina Bralina , Adnan Yazici , Cuntai Guan , Min-Ho Lee","doi":"10.1016/j.eswa.2026.131487","DOIUrl":"10.1016/j.eswa.2026.131487","url":null,"abstract":"<div><div>Facial and speech expressions are primary cues for emotion recognition, while EEG provides a complementary neural perspective when external signals are ambiguous or absent. Although each modality contributes unique affective information, integrating such heterogeneous signals remains a major challenge in multimodal fusion research. To address this, the Adaptive Multimodal Bottleneck Transformer (AMBT) is introduced as a novel architecture, enabling efficient cross-modal interaction through adapters embedded within intermediate Transformer layers. These adapters 1) enhance stability by leveraging bottleneck tokens to prevent premature collapse, 2) enrich backbone representations while preserving unimodal capacity, 3) enable seamless integration across heterogeneous Transformer architectures, and 4) enable parameter-efficient training with fewer than 1% additional trainable parameters. AMBT was evaluated on three benchmark datasets: EAV (85.1%), CREMA-D (90.9%), and DEAP (98.7%), demonstrating competitive performance across all datasets. This results demonstrate the ability of AMBT to exploit complementary multimodal signals in a computationally efficient manner.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131487"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192713","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}

引用次数: 0

DORF-EASNet: physics-driven real-time seafloor classification via entropy‑regularized acoustic features and adaptive model activation DORF-EASNet：物理驱动的实时海底分类，通过熵正则化声学特征和自适应模型激活

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131461

Xi Zhao, Qiangqiang Yuan, Quanyin Zhang, Jiadan Xu

Real-time seabed sediment classification (SSC) is crucial for underwater navigation, operations, and habitat assessment. Conventional methods relying on post-mission multibeam-echosounder (MBES) data processing impede in situ decision-making. We propose a novel, real-time SSC method deployable on both shipborne and Autonomous Underwater Vehicle (AUV) platforms, integrating three core components. Primarily, an efficient preprocessing pipeline comprising georeferencing, radiometric normalization, noise suppression, and incidence-angle correction enables rapid conversion of raw MBES backscatter into geometry-consistent tiles, supporting real-time operation with sub-second responsiveness. Afterwards, the system extracts multi-modal descriptors by combining entropy-regularised angular-response fitting for acoustic backscatter, object-level texture analysis using adaptive graph segmentation, and curvature-aware terrain metrics derived from quadratic surface fitting under entropy constraints by considering the physical responses and spatial distribution of MBES images and point clouds. Finally, a Dynamic Optimal Random Forest with Entropy-Adaptive Subnetwork Selection (DORF-EASNet) dynamically selects between a global classifier and lightweight domain-specific sub-models to match local acoustic complexity, achieving a balance between inference efficiency and physical interpretability. Field experiments conducted in Jiaozhou Bay and the South China Sea demonstrate the proposed framework’s robustness across platforms and sensing configurations, achieving macro-F1 scores of 0.881 and 0.913, respectively, while maintaining real-time processing capability exceeding that of conventional offline methods.

实时海底沉积物分类（SSC）对水下导航、作业和栖息地评估至关重要。依靠任务后多波束测深（MBES）数据处理的传统方法阻碍了现场决策。我们提出了一种新型的实时SSC方法，可部署在舰载和自主水下航行器（AUV）平台上，集成了三个核心组件。首先，高效的预处理管道包括地理参考、辐射归一化、噪声抑制和入射角校正，可以将原始MBES背散射快速转换为几何一致的瓷砖，支持亚秒级响应的实时操作。然后，考虑MBES图像和点云的物理响应和空间分布，结合声学后向散射的熵正则化角响应拟合、自适应图分割的目标级纹理分析以及熵约束下二次曲面拟合的曲率感知地形度量，提取多模态描述符。最后，基于熵自适应子网络选择的动态最优随机森林（DORF-EASNet）在全局分类器和轻量化领域特定子模型之间动态选择以匹配局部声学复杂性，实现了推理效率和物理可解释性之间的平衡。在胶州湾和南海进行的现场实验表明，该框架具有跨平台、跨感知配置的鲁棒性，宏观f1得分分别达到0.881和0.913，同时保持了超过传统离线方法的实时处理能力。

{"title":"DORF-EASNet: physics-driven real-time seafloor classification via entropy‑regularized acoustic features and adaptive model activation","authors":"Xi Zhao, Qiangqiang Yuan, Quanyin Zhang, Jiadan Xu","doi":"10.1016/j.eswa.2026.131461","DOIUrl":"10.1016/j.eswa.2026.131461","url":null,"abstract":"<div><div>Real-time seabed sediment classification (SSC) is crucial for underwater navigation, operations, and habitat assessment. Conventional methods relying on post-mission multibeam-echosounder (MBES) data processing impede in situ decision-making. We propose a novel, real-time SSC method deployable on both shipborne and Autonomous Underwater Vehicle (AUV) platforms, integrating three core components. Primarily, an efficient preprocessing pipeline comprising georeferencing, radiometric normalization, noise suppression, and incidence-angle correction enables rapid conversion of raw MBES backscatter into geometry-consistent tiles, supporting real-time operation with sub-second responsiveness. Afterwards, the system extracts multi-modal descriptors by combining entropy-regularised angular-response fitting for acoustic backscatter, object-level texture analysis using adaptive graph segmentation, and curvature-aware terrain metrics derived from quadratic surface fitting under entropy constraints by considering the physical responses and spatial distribution of MBES images and point clouds. Finally, a Dynamic Optimal Random Forest with Entropy-Adaptive Subnetwork Selection (DORF-EASNet) dynamically selects between a global classifier and lightweight domain-specific sub-models to match local acoustic complexity, achieving a balance between inference efficiency and physical interpretability. Field experiments conducted in Jiaozhou Bay and the South China Sea demonstrate the proposed framework’s robustness across platforms and sensing configurations, achieving macro-F1 scores of 0.881 and 0.913, respectively, while maintaining real-time processing capability exceeding that of conventional offline methods.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131461"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122660","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}

引用次数: 0

Preventing Cascading Failures in Supply Networks: The Role of Dynamic Coupling and Targeted Reinforcement 防止供应网络中的级联故障：动态耦合和目标强化的作用

IF 7.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Expert Systems with Applications

Pub Date : 2026-02-04 DOI: 10.1016/j.eswa.2026.131533

Zhu Xiaoxin , Yang Yongqi, Ran Menghuan, Sun Lu

As global supply-chain structures become increasingly complex and disruption risks intensify, enhancing their dynamic robustness against cascading failures has become a critical challenge for ensuring supply-chain security and stability. This study focuses on three core challenges in multilayer supply chain networks: suppressing intra-layer failure propagation, preventing bottleneck effects at weak links, and controlling cross-layer cascading failures while maintaining material flows. We constructed a heterogeneous four-layer cascading failure model comprising suppliers, manufacturers, distributors, and retailers. Through a three-level coordinated mechanism of “intra-layer load-balanced allocation, elastic regulation of cross-layer coupling, and targeted reinforcement of vulnerable layers”, we achieved global robustness optimization and simulated the dynamic processes of failure redistribution within layers and diffusion across-layers. Based on this, we proposed a dynamically coupled, guidance-oriented multilayer collaborative protection strategy. The results show that: a node degree-based dynamic load allocation strategy can significantly delay intra-layer cascading failure propagation; reinforcing vulnerable layers through enhanced node capacity buffers and optimized topological balance effectively reduces their failure risk and mitigates global disruptions; and dynamically adjusting cross-layer coupling strength significantly suppresses cross-layer “ripple effects”. This research provides both theoretical support and actionable decision guidance for resilience optimization in complex supply chain networks.

随着全球供应链结构的日益复杂和中断风险的加剧，增强其对级联故障的动态鲁棒性已成为确保供应链安全和稳定的关键挑战。本研究聚焦于多层供应链网络的三个核心挑战：抑制层内故障传播，防止薄弱环节的瓶颈效应，以及在保持物料流动的同时控制跨层级联故障。我们构建了一个由供应商、制造商、分销商和零售商组成的异构四层级联故障模型。通过“层内负载均衡分配、层间耦合弹性调节、脆弱层针对性加固”三级协调机制，实现全局鲁棒性优化，模拟了层内故障重分布和层间扩散的动态过程。在此基础上，提出了一种动态耦合、导向的多层协同保护策略。结果表明：基于节点度的动态负载分配策略可以显著延缓层内级联故障的传播；通过增强节点容量缓冲和优化拓扑平衡来增强脆弱层，有效降低其失效风险，减轻全局中断；动态调节跨层耦合强度可显著抑制跨层“涟漪效应”。本研究为复杂供应链网络弹性优化提供了理论支持和可操作的决策指导。

{"title":"Preventing Cascading Failures in Supply Networks: The Role of Dynamic Coupling and Targeted Reinforcement","authors":"Zhu Xiaoxin , Yang Yongqi, Ran Menghuan, Sun Lu","doi":"10.1016/j.eswa.2026.131533","DOIUrl":"10.1016/j.eswa.2026.131533","url":null,"abstract":"<div><div>As global supply-chain structures become increasingly complex and disruption risks intensify, enhancing their dynamic robustness against cascading failures has become a critical challenge for ensuring supply-chain security and stability. This study focuses on three core challenges in multilayer supply chain networks: suppressing intra-layer failure propagation, preventing bottleneck effects at weak links, and controlling cross-layer cascading failures while maintaining material flows. We constructed a heterogeneous four-layer cascading failure model comprising suppliers, manufacturers, distributors, and retailers. Through a three-level coordinated mechanism of “intra-layer load-balanced allocation, elastic regulation of cross-layer coupling, and targeted reinforcement of vulnerable layers”, we achieved global robustness optimization and simulated the dynamic processes of failure redistribution within layers and diffusion across-layers. Based on this, we proposed a dynamically coupled, guidance-oriented multilayer collaborative protection strategy. The results show that: a node degree-based dynamic load allocation strategy can significantly delay intra-layer cascading failure propagation; reinforcing vulnerable layers through enhanced node capacity buffers and optimized topological balance effectively reduces their failure risk and mitigates global disruptions; and dynamically adjusting cross-layer coupling strength significantly suppresses cross-layer “ripple effects”. This research provides both theoretical support and actionable decision guidance for resilience optimization in complex supply chain networks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131533"},"PeriodicalIF":7.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192772","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}

引用次数: 0