Expert Systems with Applications最新文献_第7页

Optimal contracts for multidimensional SaaS outsourcing: screening efficiency, inducing effort, and threshold-based contract selection under hidden information 多维SaaS外包的最优契约：隐藏信息下的筛选效率、诱导努力和基于阈值的契约选择

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-07 DOI: 10.1016/j.eswa.2026.131323

Guofeng Tang , Dan Li

The misalignment of contracts in software-as-a-service (SaaS) outsourcing often leads to suboptimal outcomes, a risk exacerbated when the client cannot observe the provider’s true efficiency or development effort, and when service quality involves multiple, competing dimensions. To tackle this problem, we employ a principal-agent framework to analyze the joint effects of hidden provider information and hidden action within a multidimensional quality setting. Our findings show that information asymmetry distorts the provider’s effort allocation across quality attributes, requiring specific contractual adjustments for screening and incentivization. Crucially, we derive a practical threshold rule for contract selection: revenue-sharing is optimal when quality has high value intensity (significantly impacting revenue) and provider efficiency strongly amplifies effort’s effect on outcomes; time-and-materials contracts suit standardized tasks with moderate value intensity; otherwise, a fixed-price contract should be chosen. This rule offers managers a clear, evidence-based guide to match contract forms with their specific service profiles.

软件即服务（SaaS）外包中契约的不一致经常导致次优结果，当客户无法观察到提供商的真实效率或开发工作时，以及当服务质量涉及多个相互竞争的维度时，风险就会加剧。为了解决这个问题，我们采用了一个委托代理框架来分析多维质量设置中隐藏提供者信息和隐藏行为的联合效应。我们的研究结果表明，信息不对称扭曲了供应商在质量属性上的努力分配，需要对筛选和激励进行具体的合同调整。至关重要的是，我们得出了一个实用的合同选择阈值规则：当质量具有高价值强度（显著影响收入）并且提供者效率强烈放大努力对结果的影响时，收入共享是最优的；时料合同适合价值强度适中的标准化任务；否则，应选择固定价格合同。这条规则为管理人员提供了一个清晰的、基于证据的指导，以使合同形式与他们的具体服务概况相匹配。

{"title":"Optimal contracts for multidimensional SaaS outsourcing: screening efficiency, inducing effort, and threshold-based contract selection under hidden information","authors":"Guofeng Tang , Dan Li","doi":"10.1016/j.eswa.2026.131323","DOIUrl":"10.1016/j.eswa.2026.131323","url":null,"abstract":"<div><div>The misalignment of contracts in software-as-a-service (SaaS) outsourcing often leads to suboptimal outcomes, a risk exacerbated when the client cannot observe the provider’s true efficiency or development effort, and when service quality involves multiple, competing dimensions. To tackle this problem, we employ a principal-agent framework to analyze the joint effects of hidden provider information and hidden action within a multidimensional quality setting. Our findings show that information asymmetry distorts the provider’s effort allocation across quality attributes, requiring specific contractual adjustments for screening and incentivization. Crucially, we derive a practical threshold rule for contract selection: revenue-sharing is optimal when quality has high value intensity (significantly impacting revenue) and provider efficiency strongly amplifies effort’s effect on outcomes; time-and-materials contracts suit standardized tasks with moderate value intensity; otherwise, a fixed-price contract should be chosen. This rule offers managers a clear, evidence-based guide to match contract forms with their specific service profiles.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131323"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192783","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

An integrated framework for solving the green supplier selection and order allocation problem in steam procurement 解决蒸汽采购中绿色供应商选择与订单分配问题的集成框架

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-07 DOI: 10.1016/j.eswa.2026.131386

Sugyeong Jo , Hyeong Suk Na , Seokho Yoon , Sang Jin Kweon

Industrial steam procurement is a decision-making challenge that requires balancing cost efficiency, supplier quality, and environmental sustainability. In this study, we address the steam procurement problem by considering green supplier selection and order allocation. To account for the dynamic nature of steam pricing, block-rate pricing policies are used. Due to the discontinuous cost variations caused by block-rate pricing across consumption thresholds, we aim to improve demand forecasting accuracy by developing a time-series ensemble model based on Bayesian optimization. Additionally, we integrate hybrid multi-criteria decision-making techniques to incorporate the qualitative supplier evaluations beyond cost-based criteria. Finally, a multi-objective linear programming model is developed to optimize the trade-offs among the total cost of purchase (TCP), the total value of purchase (TVP), and carbon emissions. We validate the proposed framework with an application to a major manufacturer in Ulsan, Republic of Korea. The optimized procurement strategy increases TVP by 25% and reduces carbon emissions by 10% without raising TCP. We also present a sensitivity analysis that examines the impact of price volatility. Lastly, we further explore multiple scenarios that incorporate renewable energy sources.

工业蒸汽采购是一项决策挑战，需要平衡成本效率、供应商质量和环境可持续性。在本研究中，我们通过考虑绿色供应商选择和订单分配来解决蒸汽采购问题。为了考虑蒸汽定价的动态性，采用了整块定价策略。由于跨消费阈值的块费率定价引起的不连续成本变化，我们的目标是通过开发基于贝叶斯优化的时间序列集成模型来提高需求预测的准确性。此外，我们整合了混合多标准决策技术，将定性供应商评估纳入基于成本的标准之外。最后，建立了一个多目标线性规划模型，以优化总购买成本（TCP）、总购买价值（TVP）和碳排放之间的权衡。我们通过向大韩民国蔚山的一家主要制造商申请验证所提议的框架。优化后的采购策略使TVP提高了25%，在不提高TCP的情况下减少了10%的碳排放。我们还提出了一个敏感性分析，检验价格波动的影响。最后，我们进一步探讨了包含可再生能源的多种场景。

{"title":"An integrated framework for solving the green supplier selection and order allocation problem in steam procurement","authors":"Sugyeong Jo , Hyeong Suk Na , Seokho Yoon , Sang Jin Kweon","doi":"10.1016/j.eswa.2026.131386","DOIUrl":"10.1016/j.eswa.2026.131386","url":null,"abstract":"<div><div>Industrial steam procurement is a decision-making challenge that requires balancing cost efficiency, supplier quality, and environmental sustainability. In this study, we address the steam procurement problem by considering green supplier selection and order allocation. To account for the dynamic nature of steam pricing, block-rate pricing policies are used. Due to the discontinuous cost variations caused by block-rate pricing across consumption thresholds, we aim to improve demand forecasting accuracy by developing a time-series ensemble model based on Bayesian optimization. Additionally, we integrate hybrid multi-criteria decision-making techniques to incorporate the qualitative supplier evaluations beyond cost-based criteria. Finally, a multi-objective linear programming model is developed to optimize the trade-offs among the total cost of purchase (TCP), the total value of purchase (TVP), and carbon emissions. We validate the proposed framework with an application to a major manufacturer in Ulsan, Republic of Korea. The optimized procurement strategy increases TVP by 25% and reduces carbon emissions by 10% without raising TCP. We also present a sensitivity analysis that examines the impact of price volatility. Lastly, we further explore multiple scenarios that incorporate renewable energy sources.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131386"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192773","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

Visible-guided multigranularity prompt learning for visible-infrared person re-identification 可见制导的多粒度提示学习，用于可见红外人再识别

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-02 DOI: 10.1016/j.eswa.2026.131464

Yangyan Luo, Ying Chen

Visible-infrared person re-identification (VI-ReID) remains challenging due to substantial cross-modal discrepancies and the absence of explicit semantic correspondence. This paper presents a novel Visible-Guided Multigranularity Prompt Learning (VG-MPL) framework that integrates semantic reasoning into cross-modal alignment through language-guided prompt learning. A fine-grained adaptive prompt is constructed by decomposing textual templates into learnable semantic slots, whose activations are dynamically modulated by a Prompt Slot Router (PSR) guided by visible features. This design enables sample-specific semantic modeling and enhances interpretability. To establish coherent cross-modal representations, a multi-granularity consistency constraint is imposed across the hierarchical layers of the CLIP text encoder, ensuring that global identity and local attribute semantics remain aligned. Furthermore, an Alternative Cross-Modal Alignment (ACMA) strategy and its theoretical analysis promotes bidirectional learning between visible and infrared modalities, improving optimization stability and preventing one-sided collapse. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that VG-MPL achieves state-of-the-art performance and superior cross-modal generalization, validating the effectiveness of adaptive semantic prompting and hierarchical alignment in bridging the modality gap.

由于大量的跨模态差异和缺乏明确的语义对应，可见-红外人再识别（VI-ReID）仍然具有挑战性。本文提出了一种新的可视引导多粒度提示学习（VG-MPL）框架，通过语言引导提示学习将语义推理集成到跨模态对齐中。通过将文本模板分解为可学习的语义槽，构建了细粒度的自适应提示，这些语义槽的激活由提示槽路由器（PSR）根据可见特征进行动态调节。这种设计支持特定于示例的语义建模并增强可解释性。为了建立一致的跨模态表示，在CLIP文本编码器的分层层上施加了多粒度一致性约束，确保全局标识和本地属性语义保持一致。此外，ACMA策略及其理论分析促进了可见光和红外模态之间的双向学习，提高了优化稳定性，防止了单侧坍塌。在SYSU-MM01和RegDB数据集上的大量实验表明，VG-MPL实现了最先进的性能和卓越的跨模态泛化，验证了自适应语义提示和分层校准在弥合模态差距方面的有效性。

{"title":"Visible-guided multigranularity prompt learning for visible-infrared person re-identification","authors":"Yangyan Luo, Ying Chen","doi":"10.1016/j.eswa.2026.131464","DOIUrl":"10.1016/j.eswa.2026.131464","url":null,"abstract":"<div><div>Visible-infrared person re-identification (VI-ReID) remains challenging due to substantial cross-modal discrepancies and the absence of explicit semantic correspondence. This paper presents a novel Visible-Guided Multigranularity Prompt Learning (VG-MPL) framework that integrates semantic reasoning into cross-modal alignment through language-guided prompt learning. A fine-grained adaptive prompt is constructed by decomposing textual templates into learnable semantic slots, whose activations are dynamically modulated by a Prompt Slot Router (PSR) guided by visible features. This design enables sample-specific semantic modeling and enhances interpretability. To establish coherent cross-modal representations, a multi-granularity consistency constraint is imposed across the hierarchical layers of the CLIP text encoder, ensuring that global identity and local attribute semantics remain aligned. Furthermore, an Alternative Cross-Modal Alignment (ACMA) strategy and its theoretical analysis promotes bidirectional learning between visible and infrared modalities, improving optimization stability and preventing one-sided collapse. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that VG-MPL achieves state-of-the-art performance and superior cross-modal generalization, validating the effectiveness of adaptive semantic prompting and hierarchical alignment in bridging the modality gap.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131464"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122750","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

Robot path planning based on multi-strategy enhanced aquila optimizer algorithm in complex environments 复杂环境下基于多策略增强aquila优化算法的机器人路径规划

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-03 DOI: 10.1016/j.eswa.2026.131489

Yu Zhou , Xing Liu , Jianqiao Long , Yitian Lu , Jiaoyang Cheng , Jichun Li

Path planning is a core challenge in autonomous navigation and continuously attracts significant attention in mobile robotics. While optimization algorithms are widely employed for solving robot path planning problems, the Aquila Optimizer (AO) suffers from slow convergence and a tendency to become trapped in local optima. To address these limitations, we propose a robot path planning method based on a Multi-strategy Enhanced Aquila Optimizer (MEAO). In MEAO, the initial population is enhanced using opposition-based learning, and an adaptive parameter mechanism balances exploration and exploitation. During the narrowed exploration phase, a phasor operator enables non-parametric optimization to improve global search capability, while a differential evolution mutation strategy is embedded to strengthen local exploitation. The algorithm’s performance is validated on the CEC2022 benchmark functions with ablation studies confirming the effectiveness and synergy of the various strategies. MEAO is further applied to robot path planning, with simulations performed on various complex two-dimensional grid maps, and comparisons made against several intelligent optimization-based algorithms. In addition, to address the limitations of the traditional Dynamic Window Approach (DWA) in terms of dynamic obstacle avoidance robustness and susceptibility to local minima, we introduce a dynamic threat response mechanism and an adaptive heading trap detection strategy. A collaborative framework combining MEAO-based global planning with the improved DWA for local obstacle avoidance is then established. Experimental results demonstrate that MEAO achieves shorter path lengths and faster convergence, while the improved DWA significantly enhances obstacle avoidance robustness in complex environments. The proposed collaborative framework thus ensures globally optimal paths and reliable real-time local obstacle avoidance, demonstrating the practicality and efficiency of the MEAO algorithm and improved DWA for mobile robot navigation.

路径规划是自主导航的核心问题，一直是移动机器人研究的热点。虽然优化算法被广泛用于解决机器人路径规划问题，但Aquila Optimizer （AO）存在收敛速度慢且容易陷入局部最优的问题。为了解决这些限制，我们提出了一种基于多策略增强Aquila优化器（MEAO）的机器人路径规划方法。在MEAO中，使用基于对立的学习增强初始种群，并采用自适应参数机制平衡探索和开发。在狭窄的勘探阶段，相量算子实现非参数优化以提高全局搜索能力，而嵌入差分进化突变策略以加强局部开发。该算法的性能在CEC2022基准函数上进行了验证，并进行了消融研究，证实了各种策略的有效性和协同性。MEAO进一步应用于机器人路径规划，在各种复杂的二维网格地图上进行了仿真，并与几种基于智能优化的算法进行了比较。此外，为了解决传统动态窗口方法在动态避障鲁棒性和局部最小敏感性方面的局限性，引入了动态威胁响应机制和自适应航向陷阱检测策略。建立了基于meao的全局规划与改进DWA相结合的局部避障协作框架。实验结果表明，MEAO的路径长度更短，收敛速度更快，改进的DWA显著提高了复杂环境下的避障鲁棒性。所提出的协作框架保证了全局最优路径和可靠的实时局部避障，证明了MEAO算法和改进的DWA在移动机器人导航中的实用性和高效性。

{"title":"Robot path planning based on multi-strategy enhanced aquila optimizer algorithm in complex environments","authors":"Yu Zhou , Xing Liu , Jianqiao Long , Yitian Lu , Jiaoyang Cheng , Jichun Li","doi":"10.1016/j.eswa.2026.131489","DOIUrl":"10.1016/j.eswa.2026.131489","url":null,"abstract":"<div><div>Path planning is a core challenge in autonomous navigation and continuously attracts significant attention in mobile robotics. While optimization algorithms are widely employed for solving robot path planning problems, the Aquila Optimizer (AO) suffers from slow convergence and a tendency to become trapped in local optima. To address these limitations, we propose a robot path planning method based on a Multi-strategy Enhanced Aquila Optimizer (MEAO). In MEAO, the initial population is enhanced using opposition-based learning, and an adaptive parameter mechanism balances exploration and exploitation. During the narrowed exploration phase, a phasor operator enables non-parametric optimization to improve global search capability, while a differential evolution mutation strategy is embedded to strengthen local exploitation. The algorithm’s performance is validated on the CEC2022 benchmark functions with ablation studies confirming the effectiveness and synergy of the various strategies. MEAO is further applied to robot path planning, with simulations performed on various complex two-dimensional grid maps, and comparisons made against several intelligent optimization-based algorithms. In addition, to address the limitations of the traditional Dynamic Window Approach (DWA) in terms of dynamic obstacle avoidance robustness and susceptibility to local minima, we introduce a dynamic threat response mechanism and an adaptive heading trap detection strategy. A collaborative framework combining MEAO-based global planning with the improved DWA for local obstacle avoidance is then established. Experimental results demonstrate that MEAO achieves shorter path lengths and faster convergence, while the improved DWA significantly enhances obstacle avoidance robustness in complex environments. The proposed collaborative framework thus ensures globally optimal paths and reliable real-time local obstacle avoidance, demonstrating the practicality and efficiency of the MEAO algorithm and improved DWA for mobile robot navigation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131489"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122751","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

Knowledge-guided hyper-heuristic evolutionary algorithm for large-scale Boolean network inference 大规模布尔网络推理的知识引导超启发式进化算法

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-10 DOI: 10.1016/j.eswa.2026.131418

Xiang Liu , Yan Wang , Xiayu Jiang , Zhicheng Ji , Shan He

Boolean network provides an efficient and qualitative insight into gene regulatory networks in that it can unveil the causal relationships between different genes and excavate their dynamics. Numerous approaches have been investigated to infer Boolean networks from the observed gene expression time-series data. Nevertheless, existing algorithms fail to precisely infer large-scale Boolean networks owing to the complex state transitions and the noisy data. Moreover, these algorithms suffer performance deterioration when encountering novel Boolean network architectures. To address these problems, this study proposes a novel knowledge-guided hyper-heuristic genetic programming combined with the mutual information theory called KMHHGP. Firstly, a novel hyper-heuristic genetic programming with the dual-domain encoding scheme is proposed to enhance generalization capability for inferring large-scale Boolean networks. Secondly, six novel operators are developed to compose a set of knowledge-guided low-level heuristics. Thirdly, a novel mutual information scheme is introduced to evaluate the correlation among target nodes and their regulatory nodes. In addition, a parsimony pressure mechanism is introduced to mitigate the overfitting phenomenon. Comprehensive experiments demonstrate that the proposed method robustly outperforms state-of-the-art methods in accurately inferring various large-scale networks.

布尔网络可以揭示不同基因之间的因果关系，挖掘基因之间的动态关系，为研究基因调控网络提供了一种高效、定性的方法。已经研究了许多方法来从观察到的基因表达时间序列数据推断布尔网络。然而，现有的算法由于状态转换复杂和数据有噪声，无法精确地推断出大规模布尔网络。此外，当遇到新颖的布尔网络架构时，这些算法的性能会下降。为了解决这些问题，本研究提出了一种新的知识导向的超启发式遗传规划，并结合互信息理论称为KMHHGP。首先，提出了一种基于双域编码的超启发式遗传规划方法，提高了大规模布尔网络推理的泛化能力。其次，提出了6个新算子，组成了一套知识引导的低级启发式算法。第三，引入了一种新的互信息机制来评估目标节点与其调控节点之间的相关性。此外，还引入了一种简化压力机制来缓解过拟合现象。综合实验表明，该方法在准确推断各种大规模网络方面明显优于现有方法。

{"title":"Knowledge-guided hyper-heuristic evolutionary algorithm for large-scale Boolean network inference","authors":"Xiang Liu , Yan Wang , Xiayu Jiang , Zhicheng Ji , Shan He","doi":"10.1016/j.eswa.2026.131418","DOIUrl":"10.1016/j.eswa.2026.131418","url":null,"abstract":"<div><div>Boolean network provides an efficient and qualitative insight into gene regulatory networks in that it can unveil the causal relationships between different genes and excavate their dynamics. Numerous approaches have been investigated to infer Boolean networks from the observed gene expression time-series data. Nevertheless, existing algorithms fail to precisely infer large-scale Boolean networks owing to the complex state transitions and the noisy data. Moreover, these algorithms suffer performance deterioration when encountering novel Boolean network architectures. To address these problems, this study proposes a novel knowledge-guided hyper-heuristic genetic programming combined with the mutual information theory called KMHHGP. Firstly, a novel hyper-heuristic genetic programming with the dual-domain encoding scheme is proposed to enhance generalization capability for inferring large-scale Boolean networks. Secondly, six novel operators are developed to compose a set of knowledge-guided low-level heuristics. Thirdly, a novel mutual information scheme is introduced to evaluate the correlation among target nodes and their regulatory nodes. In addition, a parsimony pressure mechanism is introduced to mitigate the overfitting phenomenon. Comprehensive experiments demonstrate that the proposed method robustly outperforms state-of-the-art methods in accurately inferring various large-scale networks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131418"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191897","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

Visual intelligent diagnosis method for surface defects of construction hoisting machinery based on UAV images 基于无人机图像的工程起重机械表面缺陷视觉智能诊断方法

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-09 DOI: 10.1016/j.eswa.2026.131607

Hao Feng , Shuwen Yu , Hao Gong , Xiaodan Chang , Chenbo Yin

Manual inspection of construction lifting machinery presents significant challenges, including high costs, low efficiency, operational complexity, and safety risks. To address these limitations, this paper proposes an intelligent surface defect detection method named FRE (Faster-RepViT-EMA), which utilizes drone imagery for automated visual inspection. Surface defects in such machinery are characterized by diversity, small scale, and complex backgrounds, which often limit the detection accuracy of conventional deep learning models such as the standard YOLOv8. The proposed FRE model enhances YOLOv8 architecture through three key modifications: replacing the C2F module in the backbone with a RepViT block to improve computational efficiency and training speed; integrating a FasterNet block in the neck network to enhance defect localization and small-target detection capability; and incorporating an Efficient Multiscale Attention (EMA) module into the backbone to suppress background interference and strengthen focus on defect features. To validate the approach, three dedicated datasets were constructed for typical defects in construction machinery—wire rope damage, metal corrosion, and structural cracking. Experimental results show that the FRE model achieves a detection accuracy of 91.7%, outperforming existing methods, while reducing parameter count by 23.26% compared to the baseline YOLOv8. These findings demonstrate that the proposed method enables fast, accurate, and lightweight defect detection, offering a practical and efficient solution for automated inspection in industrial applications.

人工检测工程起重机械存在成本高、效率低、操作复杂、安全风险大等问题。为了解决这些限制，本文提出了一种名为FRE （faster - repviti - ema）的智能表面缺陷检测方法，该方法利用无人机图像进行自动视觉检测。此类机械的表面缺陷具有多样性、规模小、背景复杂等特点，这往往限制了传统深度学习模型（如标准YOLOv8）的检测精度。提出的FRE模型通过三个关键的修改来增强YOLOv8架构：用RepViT块替换主干中的C2F模块，以提高计算效率和训练速度；在颈部网络中集成FasterNet块，增强缺陷定位和小目标检测能力；在主干网中加入高效多尺度注意（EMA）模块，抑制背景干扰，加强对缺陷特征的关注。为了验证该方法，构建了三个专用数据集，分别针对工程机械中的典型缺陷——钢丝绳损伤、金属腐蚀和结构开裂。实验结果表明，FRE模型的检测准确率达到91.7%，优于现有方法，同时与基线YOLOv8相比，参数数量减少了23.26%。这些发现表明，所提出的方法能够实现快速、准确和轻量级的缺陷检测，为工业应用中的自动检测提供了实用和有效的解决方案。

{"title":"Visual intelligent diagnosis method for surface defects of construction hoisting machinery based on UAV images","authors":"Hao Feng , Shuwen Yu , Hao Gong , Xiaodan Chang , Chenbo Yin","doi":"10.1016/j.eswa.2026.131607","DOIUrl":"10.1016/j.eswa.2026.131607","url":null,"abstract":"<div><div>Manual inspection of construction lifting machinery presents significant challenges, including high costs, low efficiency, operational complexity, and safety risks. To address these limitations, this paper proposes an intelligent surface defect detection method named FRE (Faster-RepViT-EMA), which utilizes drone imagery for automated visual inspection. Surface defects in such machinery are characterized by diversity, small scale, and complex backgrounds, which often limit the detection accuracy of conventional deep learning models such as the standard YOLOv8. The proposed FRE model enhances YOLOv8 architecture through three key modifications: replacing the C2F module in the backbone with a RepViT block to improve computational efficiency and training speed; integrating a FasterNet block in the neck network to enhance defect localization and small-target detection capability; and incorporating an Efficient Multiscale Attention (EMA) module into the backbone to suppress background interference and strengthen focus on defect features. To validate the approach, three dedicated datasets were constructed for typical defects in construction machinery—wire rope damage, metal corrosion, and structural cracking. Experimental results show that the FRE model achieves a detection accuracy of 91.7%, outperforming existing methods, while reducing parameter count by 23.26% compared to the baseline YOLOv8. These findings demonstrate that the proposed method enables fast, accurate, and lightweight defect detection, offering a practical and efficient solution for automated inspection in industrial applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131607"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192561","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 : 2026-05-25 Epub 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":"2026-05-25","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

MagTCN: A multi-scale adaptive graph-enhanced temporal convolutional network for variance-imbalanced multivariate passenger flow forecasting MagTCN：基于多尺度自适应图增强时间卷积网络的方差不平衡多元客流预测

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-03 DOI: 10.1016/j.eswa.2026.131486

Rui Zhang , Jianyuan Guo , Yong Qin , Limin Jia

Station-level passenger flow prediction is crucial for passenger flow regulation, crew scheduling, and train dispatching. However, existing deep learning models are difficult to apply to intra-station multi-point passenger flow forecasting tasks characterized by multivariate interactions and variance imbalance. To address this, we propose a deep learning model–the Multi-Scale Adaptive Graph-Enhanced Temporal Convolutional Network (MagTCN). The model balances high- and low-variance channels through parallel multi-scale one-dimensional (1-D) convolutions and a squeeze-and-excitation mechanism. Meanwhile, it dynamically constructs temporal graphs using cosine similarity and enhances cross-time-step pattern reuse via a Graph Convolutional Network (GCN), thereby improving predictive robustness under peak-demand scenarios. On this basis, information fusion is performed by a fusion attention layer, and the residual-gated decoder simultaneously generates multi-point, multi-step forecasts within a station in a single forward pass. We evaluate the model’s performance on real station passenger flow data from Guangzhou and Suzhou, China. The experimental results demonstrate that MagTCN outperforms advanced baselines such as iTransformer and TimeMixer, in terms of prediction accuracy across the four prediction horizons, while exhibiting superior stability and channel adaptability.

车站客流预测对客流调控、班组调度和列车调度具有重要意义。然而，现有的深度学习模型难以应用于多变量交互和方差不平衡的车站内多点客流预测任务。为了解决这个问题，我们提出了一种深度学习模型-多尺度自适应图增强时态卷积网络（MagTCN）。该模型通过并行多尺度一维（1-D）卷积和挤压激励机制平衡高方差和低方差通道。同时，利用余弦相似度动态构建时间图，并通过图卷积网络（GCN）增强跨时间步模式重用，从而提高高峰需求场景下的预测鲁棒性。在此基础上，通过融合注意层进行信息融合，残差门控解码器在单次前向通中同时生成站点内的多点、多步预测。我们用广州和苏州的真实车站客流数据来评估模型的性能。实验结果表明，在四个预测层的预测精度方面，MagTCN优于iTransformer和TimeMixer等先进基线，同时具有优越的稳定性和信道适应性。

{"title":"MagTCN: A multi-scale adaptive graph-enhanced temporal convolutional network for variance-imbalanced multivariate passenger flow forecasting","authors":"Rui Zhang , Jianyuan Guo , Yong Qin , Limin Jia","doi":"10.1016/j.eswa.2026.131486","DOIUrl":"10.1016/j.eswa.2026.131486","url":null,"abstract":"<div><div>Station-level passenger flow prediction is crucial for passenger flow regulation, crew scheduling, and train dispatching. However, existing deep learning models are difficult to apply to intra-station multi-point passenger flow forecasting tasks characterized by multivariate interactions and variance imbalance. To address this, we propose a deep learning model–the Multi-Scale Adaptive Graph-Enhanced Temporal Convolutional Network (MagTCN). The model balances high- and low-variance channels through parallel multi-scale one-dimensional (1-D) convolutions and a squeeze-and-excitation mechanism. Meanwhile, it dynamically constructs temporal graphs using cosine similarity and enhances cross-time-step pattern reuse via a Graph Convolutional Network (GCN), thereby improving predictive robustness under peak-demand scenarios. On this basis, information fusion is performed by a fusion attention layer, and the residual-gated decoder simultaneously generates multi-point, multi-step forecasts within a station in a single forward pass. We evaluate the model’s performance on real station passenger flow data from Guangzhou and Suzhou, China. The experimental results demonstrate that MagTCN outperforms advanced baselines such as iTransformer and TimeMixer, in terms of prediction accuracy across the four prediction horizons, while exhibiting superior stability and channel adaptability.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131486"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192712","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

Label-wise reliability-aware classifier for robust chest X-ray multi-label classification 基于标签的可靠性感知分类器，用于稳健的胸部x线多标签分类

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-02-03 DOI: 10.1016/j.eswa.2026.131438

Wenkai Ye, Xichen Ye, Hang Yao, Kequan Yang, Xiaoqiang Li

Chest X-ray (CXR) multi-label classifiers are commonly trained with labels extracted from clinical reports, which are often incomplete and noisy. Under such label noise, we observe that performance degrades severely on tail classes (e.g., rare diseases), because these categories are under-represented and easily overwhelmed by corrupted annotations. As a result, existing methods can misidentify tail classes as noise and downweight their contribution to optimization during training. To address this issue, we propose LRC-CXR (Label-wise Reliability-aware Classifier for Chest X-ray), which calculates per-label reliability and selectively corrects noisy labels, preventing tail classes from being inadvertently under-trained. First, a Medical Description Bank provides lesion-aware textual prompts that guide the visual encoder toward diagnostically relevant patterns. Second, LRC-CXR models per-label reliability with a two-component Gaussian Mixture Model to distinguish clean, inseparable, and noisy labels. Third, only labels identified as noisy are refined via feature-space k-nearest-neighbor smoothing, while clean and inseparable labels are trained with stronger objectives through a hierarchical loss. Experiments on ChestX-ray14, CheXpert, and PadChest, including high-noise stress tests, show that LRC-CXR improves overall AUC/F1 and substantially boosts tail-class recall and robustness under label noise.

胸部x线（CXR）多标签分类器通常使用从临床报告中提取的标签进行训练，这些标签通常是不完整和嘈杂的。在这样的标签噪声下，我们观察到尾部类（例如罕见疾病）的性能严重下降，因为这些类别代表性不足，很容易被损坏的注释淹没。因此，现有的方法可能会错误地将尾类识别为噪声，并在训练过程中降低它们对优化的贡献。为了解决这个问题，我们提出了LRC-CXR（用于胸部x射线的标签可靠性感知分类器），它计算每个标签的可靠性并有选择地纠正噪声标签，防止尾类无意中训练不足。首先，医学描述库提供病变感知文本提示，引导视觉编码器找到诊断相关的模式。其次，LRC-CXR使用双分量高斯混合模型对每个标签的可靠性进行建模，以区分干净、不可分割和有噪声的标签。第三，通过特征空间k近邻平滑，只对被识别为有噪声的标签进行细化，而通过分层损失，用更强的目标训练干净和不可分割的标签。在ChestX-ray14、CheXpert和PadChest上进行的实验（包括高噪声压力测试）表明，LRC-CXR提高了总体AUC/F1，并显著提高了标签噪声下的尾级召回率和鲁棒性。

{"title":"Label-wise reliability-aware classifier for robust chest X-ray multi-label classification","authors":"Wenkai Ye, Xichen Ye, Hang Yao, Kequan Yang, Xiaoqiang Li","doi":"10.1016/j.eswa.2026.131438","DOIUrl":"10.1016/j.eswa.2026.131438","url":null,"abstract":"<div><div>Chest X-ray (CXR) multi-label classifiers are commonly trained with labels extracted from clinical reports, which are often incomplete and noisy. Under such label noise, we observe that performance degrades severely on tail classes (e.g., rare diseases), because these categories are under-represented and easily overwhelmed by corrupted annotations. As a result, existing methods can misidentify tail classes as noise and downweight their contribution to optimization during training. To address this issue, we propose LRC-CXR (<strong>L</strong>abel-wise <strong>R</strong>eliability-aware <strong>C</strong>lassifier for Chest X-ray), which calculates per-label reliability and selectively corrects noisy labels, preventing tail classes from being inadvertently under-trained. First, a Medical Description Bank provides lesion-aware textual prompts that guide the visual encoder toward diagnostically relevant patterns. Second, LRC-CXR models per-label reliability with a two-component Gaussian Mixture Model to distinguish clean, inseparable, and noisy labels. Third, only labels identified as noisy are refined via feature-space k-nearest-neighbor smoothing, while clean and inseparable labels are trained with stronger objectives through a hierarchical loss. Experiments on ChestX-ray14, CheXpert, and PadChest, including high-noise stress tests, show that LRC-CXR improves overall AUC/F1 and substantially boosts tail-class recall and robustness under label noise.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131438"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192694","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

An efficient dominance decomposition-based deep graph evolutionary algorithm for the expensive multi-objective optimization 一种高效的基于优势分解的深度图进化算法，用于昂贵的多目标优化

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

Expert Systems with Applications

Pub Date : 2026-05-25 Epub Date: 2026-01-29 DOI: 10.1016/j.eswa.2026.131379

Xing Cai , Tong Zhang , Zhen Cui

To efficiently solve expensive multi-objective optimization problems (EMOPs), it is essential to identify valuable evaluation points that lead to optimal solutions with minimal computational cost. In this work, we propose a deep graph-based evolutionary algorithm, named the multi-objective evolutionary algorithm based on dominance decomposition and graph neural networks (MOEA-DDG). To model the complex dominance relationships among candidate solutions, an adjacency graph is constructed that integrates both evaluated and unevaluated individuals. A collaborative surrogate framework based on graph neural networks is proposed to guide the selection of promising candidates. This framework comprises two specialized models: the relational model (R-model), which decomposes dominance prediction into simpler sub-tasks by comparing solution quality across individual objectives-thus improving robustness and accuracy; and the metric model (M-model), which estimates solution quality by predicting Hypervolume (HV) improvement, enabling effective ranking when objective values are unavailable. To ensure thorough exploration of the solution space, a cluster-based selection strategy is designed, which partitions the objective domain and selects representative candidates from each cluster during each iteration. Extensive experiments on two benchmark test suites and a real-world molecular design task demonstrate that MOEA-DDG achieves a strong balance between exploration and exploitation, and significantly outperforms state-of-the-art algorithms under limited evaluation budgets.

为了有效地解决昂贵的多目标优化问题，必须确定有价值的评估点，从而以最小的计算成本获得最优解。本文提出了一种基于深度图的进化算法，称为基于优势分解和图神经网络的多目标进化算法（MOEA-DDG）。为了对候选解之间复杂的优势关系进行建模，构建了一个包含评估个体和未评估个体的邻接图。提出了一种基于图神经网络的协同代理框架来指导有前途的候选物的选择。该框架包括两个专门的模型：关系模型（r -模型），它通过比较各个目标的解决方案质量将优势预测分解为更简单的子任务，从而提高鲁棒性和准确性；度量模型（M-model），通过预测Hypervolume （HV）的改进来估计解决方案的质量，从而在无法获得目标值时实现有效的排序。为了保证对解空间的深入探索，设计了一种基于聚类的选择策略，该策略在每次迭代中划分目标域并从每个聚类中选择具有代表性的候选对象。在两个基准测试套件和现实世界的分子设计任务上进行的大量实验表明，MOEA-DDG在勘探和开发之间取得了良好的平衡，并且在有限的评估预算下显着优于最先进的算法。

{"title":"An efficient dominance decomposition-based deep graph evolutionary algorithm for the expensive multi-objective optimization","authors":"Xing Cai , Tong Zhang , Zhen Cui","doi":"10.1016/j.eswa.2026.131379","DOIUrl":"10.1016/j.eswa.2026.131379","url":null,"abstract":"<div><div>To efficiently solve expensive multi-objective optimization problems (EMOPs), it is essential to identify valuable evaluation points that lead to optimal solutions with minimal computational cost. In this work, we propose a deep graph-based evolutionary algorithm, named the multi-objective evolutionary algorithm based on dominance decomposition and graph neural networks (MOEA-DDG). To model the complex dominance relationships among candidate solutions, an adjacency graph is constructed that integrates both evaluated and unevaluated individuals. A collaborative surrogate framework based on graph neural networks is proposed to guide the selection of promising candidates. This framework comprises two specialized models: the relational model (R-model), which decomposes dominance prediction into simpler sub-tasks by comparing solution quality across individual objectives-thus improving robustness and accuracy; and the metric model (M-model), which estimates solution quality by predicting Hypervolume (HV) improvement, enabling effective ranking when objective values are unavailable. To ensure thorough exploration of the solution space, a cluster-based selection strategy is designed, which partitions the objective domain and selects representative candidates from each cluster during each iteration. Extensive experiments on two benchmark test suites and a real-world molecular design task demonstrate that MOEA-DDG achieves a strong balance between exploration and exploitation, and significantly outperforms state-of-the-art algorithms under limited evaluation budgets.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131379"},"PeriodicalIF":7.5,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192695","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