Expert Systems with Applications最新文献_第2页

Multi-perspective domain-invariant network with energy density-based data augmentation for domain generalization fault diagnosis 基于能量密度数据增强的多视角域不变网络用于域泛化故障诊断

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

Expert Systems with Applications

Pub Date : 2026-02-08 DOI: 10.1016/j.eswa.2026.131583

Sukeun Hong, Jaewook Lee, Jongsoo Lee

Existing domain generalization fault diagnosis methods achieve satisfactory interpolation performance but struggle with extrapolation owing to two fundamental limitations: insufficient source domain coverage and the inability to verify whether learned features represent causal fault characteristics or spurious correlations. To address these challenges, this study proposes a multi-perspective domain-invariant network (MPDIN) with energy–density-based data augmentation. MPDIN employs bootstrap aggregation to train multiple feature extractors on strategically defined domain subsets, establishing hierarchical domain invariance by enforcing subset-level invariance through triplet loss and inter-subset consistency via correlation alignment. This multi-perspective framework effectively suppresses subset-specific spurious correlations while preserving genuine fault characteristics. The energy–density-based augmentation leverages the

ω^{2}

-proportional relationship between rotational speed and vibration energy to generate realistic extrapolation data beyond source domain boundaries, utilizing raw short-time Fourier transform power spectrograms to preserve absolute energy information essential for physics-based scaling. Experimental validation across four diverse datasets demonstrated substantial improvements in challenging extrapolation scenarios, achieving gains of 19–47%, whereas conventional methods showed significant performance degradation. Manifold analysis confirmed continuity and complete target–source integration, validating the attainment of true domain-invariant learning. Although limitations exist in time-varying scenarios, the proposed methodology provides a principled framework for industrial deployment where targets frequently exceed training envelopes.

现有的领域泛化故障诊断方法可以获得令人满意的内插性能，但由于源域覆盖范围不足以及无法验证学习到的特征是代表因果故障特征还是虚假相关，因此在外推方面存在困难。为了解决这些挑战，本研究提出了一种基于能量密度的数据增强的多视角域不变网络（MPDIN）。MPDIN采用自举聚合在策略定义的领域子集上训练多个特征提取器，通过三元组损失强制子集级不变性建立层次域不变性，通过相关对齐强制子集间一致性建立层次域不变性。这种多视角框架有效地抑制了子集特定的伪相关，同时保留了真实的故障特征。基于能量密度的增强利用转速和振动能量之间的ω2比例关系，在源域边界之外生成真实的外推数据，利用原始的短时傅立叶变换功率谱来保留基于物理的缩放所必需的绝对能量信息。在四个不同数据集上的实验验证表明，在具有挑战性的外推场景中有了实质性的改进，实现了19-47%的增益，而传统方法表现出显著的性能下降。流形分析证实了连续性和完整的目标-源集成，验证了真正的领域不变学习的实现。虽然在时变的情况下存在局限性，但拟议的方法为工业部署提供了一个原则性框架，其中目标经常超过培训范围。

{"title":"Multi-perspective domain-invariant network with energy density-based data augmentation for domain generalization fault diagnosis","authors":"Sukeun Hong, Jaewook Lee, Jongsoo Lee","doi":"10.1016/j.eswa.2026.131583","DOIUrl":"10.1016/j.eswa.2026.131583","url":null,"abstract":"<div><div>Existing domain generalization fault diagnosis methods achieve satisfactory interpolation performance but struggle with extrapolation owing to two fundamental limitations: insufficient source domain coverage and the inability to verify whether learned features represent causal fault characteristics or spurious correlations. To address these challenges, this study proposes a multi-perspective domain-invariant network (MPDIN) with energy–density-based data augmentation. MPDIN employs bootstrap aggregation to train multiple feature extractors on strategically defined domain subsets, establishing hierarchical domain invariance by enforcing subset-level invariance through triplet loss and inter-subset consistency via correlation alignment. This multi-perspective framework effectively suppresses subset-specific spurious correlations while preserving genuine fault characteristics. The energy–density-based augmentation leverages the <span><math><mrow><msup><mrow><mi>ω</mi></mrow><mn>2</mn></msup></mrow></math></span>-proportional relationship between rotational speed and vibration energy to generate realistic extrapolation data beyond source domain boundaries, utilizing raw short-time Fourier transform power spectrograms to preserve absolute energy information essential for physics-based scaling. Experimental validation across four diverse datasets demonstrated substantial improvements in challenging extrapolation scenarios, achieving gains of 19–47%, whereas conventional methods showed significant performance degradation. Manifold analysis confirmed continuity and complete target–source integration, validating the attainment of true domain-invariant learning. Although limitations exist in time-varying scenarios, the proposed methodology provides a principled framework for industrial deployment where targets frequently exceed training envelopes.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131583"},"PeriodicalIF":7.5,"publicationDate":"2026-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192784","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

ZPD-guided adversarial learning for safety-critical autonomous driving zpd引导的安全关键型自动驾驶对抗学习

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

Expert Systems with Applications

Pub Date : 2026-02-08 DOI: 10.1016/j.eswa.2026.131547

Wei Wu , Xiaohui Hou , Minggang Gan , Jie Chen

Ensuring the safety and robustness of autonomous vehicles (AVs) in complex and safety–critical driving scenarios remains a fundamental challenge in the advancement of autonomous driving technology. Traditional training methods often exhibit limitations in coping with uncertainty and rare extreme events encountered in real-world driving environments. To address these challenges, this paper proposes an adversarial learning framework guided by the Zone of Proximal Development (ZPD), aiming to enhance the adaptability and robustness of autonomous driving decision-making policies in complex environments. Specifically, the proposed approach embeds ZPD-inspired guidance into adversarial learning to generate safety–critical traffic interactions that are both extreme and learnable. To regulate adversarial behaviors and maintain a balance between challenge and solvability, the framework incorporates structured constraints based on the Ideal Return Ceiling (IRC) and fine-grained collision severity modeling. Furthermore, a Vehicle Potential Threat Level (VPTL) mechanism is employed to adaptively adjust adversarial training difficulty in accordance with the evolving capability of the ego vehicle, thereby facilitating continuous learning and policy adaptation. Experimental results indicate that, compared with representative baseline methods such as SAC and TD3, the proposed approach reduces the Damage Index by approximately 20–40% across a wide range of evaluation settings, while simultaneously lowering collision severity and maintaining task executability. These results suggest that the proposed framework provides a viable approach for improving safety-oriented learning behavior in complex traffic environments.

确保自动驾驶汽车（AVs）在复杂和安全关键驾驶场景中的安全性和鲁棒性仍然是自动驾驶技术进步的根本挑战。传统的训练方法在应对现实驾驶环境中遇到的不确定性和罕见的极端事件时往往表现出局限性。为了应对这些挑战，本文提出了一种基于近端发展区（Zone of Proximal Development， ZPD）的对抗学习框架，旨在增强自动驾驶决策策略在复杂环境下的适应性和鲁棒性。具体来说，提出的方法将受zpd启发的指导嵌入到对抗性学习中，以生成对安全至关重要的交通交互，这些交互既极端又可学习。为了调节对抗行为并保持挑战和可解决性之间的平衡，该框架结合了基于理想回报上限（IRC）和细粒度碰撞严重性建模的结构化约束。利用车辆潜在威胁等级（VPTL）机制，根据自我车辆的演化能力自适应调整对抗训练难度，实现持续学习和政策适应。实验结果表明，与具有代表性的基线方法（如SAC和TD3）相比，该方法在广泛的评估设置范围内将损伤指数降低了约20-40%，同时降低了碰撞严重性并保持了任务的可执行性。这些结果表明，所提出的框架为改善复杂交通环境中以安全为导向的学习行为提供了一种可行的方法。

{"title":"ZPD-guided adversarial learning for safety-critical autonomous driving","authors":"Wei Wu , Xiaohui Hou , Minggang Gan , Jie Chen","doi":"10.1016/j.eswa.2026.131547","DOIUrl":"10.1016/j.eswa.2026.131547","url":null,"abstract":"<div><div>Ensuring the safety and robustness of autonomous vehicles (AVs) in complex and safety–critical driving scenarios remains a fundamental challenge in the advancement of autonomous driving technology. Traditional training methods often exhibit limitations in coping with uncertainty and rare extreme events encountered in real-world driving environments. To address these challenges, this paper proposes an adversarial learning framework guided by the Zone of Proximal Development (ZPD), aiming to enhance the adaptability and robustness of autonomous driving decision-making policies in complex environments. Specifically, the proposed approach embeds ZPD-inspired guidance into adversarial learning to generate safety–critical traffic interactions that are both extreme and learnable. To regulate adversarial behaviors and maintain a balance between challenge and solvability, the framework incorporates structured constraints based on the Ideal Return Ceiling (IRC) and fine-grained collision severity modeling. Furthermore, a Vehicle Potential Threat Level (VPTL) mechanism is employed to adaptively adjust adversarial training difficulty in accordance with the evolving capability of the ego vehicle, thereby facilitating continuous learning and policy adaptation. Experimental results indicate that, compared with representative baseline methods such as SAC and TD3, the proposed approach reduces the Damage Index by approximately 20–40% across a wide range of evaluation settings, while simultaneously lowering collision severity and maintaining task executability. These results suggest that the proposed framework provides a viable approach for improving safety-oriented learning behavior in complex traffic environments.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"313 ","pages":"Article 131547"},"PeriodicalIF":7.5,"publicationDate":"2026-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154280","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

Coherence-aware and snap-triggered: A novel mechanism for audio-visual cooperative tasks 连贯感知和快照触发：一种新的视听合作任务机制

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

Expert Systems with Applications

Pub Date : 2026-02-07 DOI: 10.1016/j.eswa.2026.131559

Cunhan Guo, Heyan Huang, Ruiqi Hu, Danjie Han

Audio-Visual Cooperative tasks underpin multimodal scene understanding and compel models to reconcile continuous temporal evolution with abrupt sensory transitions. We propose the Coherence-Aware and Snap-Triggered mechanism (CAST) mechanism, a plug-in temporal refinement layer without perturbing backbone parameters or demanding additional modalities. The Exponential Memory based Coherence-Aware module attenuates distant frame contributions through an exponentially decaying weight envelope, thereby preventing the persistent influence of obsolete disruptions. Complementarily, the Optical Flow based Snap-Triggered Module module registers instantaneous motion discontinuities and reallocates attention toward nascent events. Operating in concert, these modules yield a representation that remains coherent across smooth transitions yet responsive to sudden perturbations. Empirical evaluation across multiple AVC benchmarks demonstrates consistent superiority over established baselines, corroborating that CAST enhances temporal fidelity and, by extension, the reliability of downstream multimodal decisions.

视听合作任务支持多模态场景理解，并迫使模型协调连续的时间演变与突然的感觉转变。我们提出了一致性感知和快照触发机制（CAST）机制，这是一种不干扰骨干参数或要求额外模式的插件时间优化层。基于指数内存的相干感知模块通过指数衰减权重包络来衰减远端帧贡献，从而防止过时中断的持续影响。此外，基于光流的快照触发模块模块记录瞬时运动不连续并将注意力重新分配给新生事件。这些模块协同工作，产生了一种表示，在平稳过渡期间保持连贯，但对突然的扰动做出反应。对多个AVC基准的实证评估表明，CAST优于已建立的基线，证实了CAST提高了时间保真度，进而提高了下游多式联运决策的可靠性。

{"title":"Coherence-aware and snap-triggered: A novel mechanism for audio-visual cooperative tasks","authors":"Cunhan Guo, Heyan Huang, Ruiqi Hu, Danjie Han","doi":"10.1016/j.eswa.2026.131559","DOIUrl":"10.1016/j.eswa.2026.131559","url":null,"abstract":"<div><div>Audio-Visual Cooperative tasks underpin multimodal scene understanding and compel models to reconcile continuous temporal evolution with abrupt sensory transitions. We propose the Coherence-Aware and Snap-Triggered mechanism (CAST) mechanism, a plug-in temporal refinement layer without perturbing backbone parameters or demanding additional modalities. The Exponential Memory based Coherence-Aware module attenuates distant frame contributions through an exponentially decaying weight envelope, thereby preventing the persistent influence of obsolete disruptions. Complementarily, the Optical Flow based Snap-Triggered Module module registers instantaneous motion discontinuities and reallocates attention toward nascent events. Operating in concert, these modules yield a representation that remains coherent across smooth transitions yet responsive to sudden perturbations. Empirical evaluation across multiple AVC benchmarks demonstrates consistent superiority over established baselines, corroborating that CAST enhances temporal fidelity and, by extension, the reliability of downstream multimodal decisions.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"313 ","pages":"Article 131559"},"PeriodicalIF":7.5,"publicationDate":"2026-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154272","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

Doctors ranking based on PSO-BP model and attention mechanism with variable weights from the perspective of online medical consultation platforms 基于PSO-BP模型和变权关注机制的医生排名——基于在线医疗咨询平台的视角

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

Expert Systems with Applications

Pub Date : 2026-02-07 DOI: 10.1016/j.eswa.2026.131349

Na Zhao , Zihao Zhang , Fengjun Liu , Zeshui Xu , Yongqing Yang

Current online medical consultation platforms face the challenge of low doctor engagement, significantly hindering the service quality and sustainable development. Existing doctor ranking mechanisms fail to effectively motivate doctors’ active participation and fully harness their contribution potential. Therefore, this paper proposes a novel doctor ranking method from the perspective of online medical consultation platforms to stimulate doctors’ engagement. Specifically, this paper first constructs a comprehensive doctor evaluation attribute system based on incomplete online data. Then, we apply the particle swarm optimization-backpropagation model and an attention mechanism to calculate the initial weights of evaluation attributes for reflecting the influence of different attributes on doctor rankings. After that, based on doctors’ behaviors and performances, and their impact on platform ecology and patient experience, we obtain the variable weights by modifying the initial weights of contribution attributes through an incentive and penalty mechanism and a state variable weight function, thereby reflecting the impact of doctors’ contributions on attribute weights. Additionally, we employ a score function with variable weights to calculate doctors’ scores and rankings, highlighting the effect of doctors’ contributions on their rankings. The proposed doctor ranking method is validated with a real dataset of 131,721 messages about 11,539 cardiovascular doctors from the well-known Chinese online medical consultation platform, Haodf.com. Ranking results of ten randomly selected doctors show that six doctors experience ranking changes due to their higher or lower levels of contribution, confirming the method’s effectiveness. Sensitivity analysis and evaluations of accuracy and usability further validate the robustness and reliability. Comparative experiments with state-of-the-art large language models and baseline methods reveal that the proposed method captures the complex interactions and latent relationships within large-scale online medical data, and more directly and clearly reflects the influence of doctors’ different levels of contribution on their rankings, providing a distinct advantage in incentivizing or penalizing doctors with exceptional or subpar performance.

当前在线医疗咨询平台面临医生参与度低的挑战，严重影响了服务质量和可持续发展。现有的医生排名机制未能有效调动医生的积极参与，充分发挥医生的贡献潜力。因此，本文从在线医疗咨询平台的角度出发，提出了一种新颖的医生排名方法，以激发医生的参与度。具体而言，本文首先构建了一个基于不完全在线数据的综合医生评价属性体系。然后，我们应用粒子群优化-反向传播模型和注意机制计算评价属性的初始权重，以反映不同属性对医生排名的影响。然后，根据医生的行为和表现，以及对平台生态和患者体验的影响，通过激励惩罚机制和状态变量权重函数对贡献属性的初始权重进行修改，得到变量权重，从而反映医生的贡献对属性权重的影响。此外，我们使用了一个可变权重的分数函数来计算医生的分数和排名，突出了医生的贡献对他们排名的影响。通过中国知名在线医疗咨询平台好医生网的11,539名心血管医生的131,721条消息的真实数据集验证了所提出的医生排名方法。随机选取的10位医生的排名结果显示，有6位医生因贡献水平的高低而出现排名变化，证实了该方法的有效性。灵敏度分析和准确性和可用性评价进一步验证了鲁棒性和可靠性。与最先进的大型语言模型和基线方法的比较实验表明，该方法捕获了大规模在线医疗数据中复杂的相互作用和潜在关系，更直接、更清晰地反映了医生不同贡献水平对其排名的影响，在激励或惩罚表现优异或差等的医生方面提供了明显的优势。

{"title":"Doctors ranking based on PSO-BP model and attention mechanism with variable weights from the perspective of online medical consultation platforms","authors":"Na Zhao , Zihao Zhang , Fengjun Liu , Zeshui Xu , Yongqing Yang","doi":"10.1016/j.eswa.2026.131349","DOIUrl":"10.1016/j.eswa.2026.131349","url":null,"abstract":"<div><div>Current online medical consultation platforms face the challenge of low doctor engagement, significantly hindering the service quality and sustainable development. Existing doctor ranking mechanisms fail to effectively motivate doctors’ active participation and fully harness their contribution potential. Therefore, this paper proposes a novel doctor ranking method from the perspective of online medical consultation platforms to stimulate doctors’ engagement. Specifically, this paper first constructs a comprehensive doctor evaluation attribute system based on incomplete online data. Then, we apply the particle swarm optimization-backpropagation model and an attention mechanism to calculate the initial weights of evaluation attributes for reflecting the influence of different attributes on doctor rankings. After that, based on doctors’ behaviors and performances, and their impact on platform ecology and patient experience, we obtain the variable weights by modifying the initial weights of contribution attributes through an incentive and penalty mechanism and a state variable weight function, thereby reflecting the impact of doctors’ contributions on attribute weights. Additionally, we employ a score function with variable weights to calculate doctors’ scores and rankings, highlighting the effect of doctors’ contributions on their rankings. The proposed doctor ranking method is validated with a real dataset of 131,721 messages about 11,539 cardiovascular doctors from the well-known Chinese online medical consultation platform, Haodf.com. Ranking results of ten randomly selected doctors show that six doctors experience ranking changes due to their higher or lower levels of contribution, confirming the method’s effectiveness. Sensitivity analysis and evaluations of accuracy and usability further validate the robustness and reliability. Comparative experiments with state-of-the-art large language models and baseline methods reveal that the proposed method captures the complex interactions and latent relationships within large-scale online medical data, and more directly and clearly reflects the influence of doctors’ different levels of contribution on their rankings, providing a distinct advantage in incentivizing or penalizing doctors with exceptional or subpar performance.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131349"},"PeriodicalIF":7.5,"publicationDate":"2026-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192787","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 : 2026-02-07 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":"2026-02-07","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

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 : 2026-02-07 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":"2026-02-07","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

Robust and explainable multi-objective dynamic scheduling of an ANFIS-driven PSO using IT2FS 基于IT2FS的anfis_pso鲁棒可解释多目标动态调度

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

Expert Systems with Applications

Pub Date : 2026-02-07 DOI: 10.1016/j.eswa.2026.131553

Yu-Cheng Wang

Manufacturing scheduling increasingly operates under dynamic conditions where processing times and machine availability are uncertain and subject to frequent disruptions. While particle swarm optimization (PSO) performs strongly in flexible job shop scheduling, solutions often rely on deterministic assumptions and provide limited transparency that restricts reliability and adoption in real shop-floor environments. This paper presents a fuzzy-neural explainable PSO (FNE-PSO) framework for multi-objective dynamic flexible job shop scheduling (DFJSP). The framework integrates interval type-2 fuzzy sets (IT2FS) to model dual uncertainty in processing times and machine availability, an adaptive neuro-fuzzy inference system (ANFIS) to regulate PSO parameters based on swarm-state indicators, and a hybrid SHAP decision-tree explanation module to interpret particle movement and search behavior. It also introduces dynamic contribution radar (DCR) visualization to support understanding multi-objective trade-offs and solution evolution. Experiments on synthetic dynamic scenarios and adapted benchmark instances demonstrate that the proposed approach achieves more robust scheduling performance than representative baselines, particularly in terms of makespan and tardiness stability under uncertainty. Beyond optimization results, evaluation of explainability indicate that the proposed framework enhances transparency and interpretability of scheduling decisions, supporting more trustworthy and accountable industrial decision-making.

制造调度越来越多地在动态条件下运行，其中加工时间和机器可用性是不确定的，并且受到频繁中断的影响。虽然粒子群优化（PSO）在灵活的作业车间调度中表现出色，但解决方案通常依赖于确定性假设，并且提供有限的透明度，这限制了在实际车间环境中的可靠性和采用。针对多目标动态柔性作业车间调度问题，提出了一个模糊神经网络可解释粒子群算法框架。该框架集成了区间2型模糊集（IT2FS）来模拟处理时间和机器可用性的双重不确定性，一个自适应神经模糊推理系统（ANFIS）来调节基于群体状态指标的PSO参数，以及一个混合SHAP决策树解释模块来解释粒子运动和搜索行为。它还引入了动态贡献雷达（DCR）可视化，以支持理解多目标权衡和解决方案演化。在综合动态场景和自适应基准实例上的实验表明，该方法比代表性基线具有更强的鲁棒性，特别是在不确定条件下的最大完工时间和延迟稳定性方面。除了优化结果外，可解释性评估表明，所提出的框架提高了调度决策的透明度和可解释性，支持更可信和负责任的工业决策。

{"title":"Robust and explainable multi-objective dynamic scheduling of an ANFIS-driven PSO using IT2FS","authors":"Yu-Cheng Wang","doi":"10.1016/j.eswa.2026.131553","DOIUrl":"10.1016/j.eswa.2026.131553","url":null,"abstract":"<div><div>Manufacturing scheduling increasingly operates under dynamic conditions where processing times and machine availability are uncertain and subject to frequent disruptions. While particle swarm optimization (PSO) performs strongly in flexible job shop scheduling, solutions often rely on deterministic assumptions and provide limited transparency that restricts reliability and adoption in real shop-floor environments. This paper presents a fuzzy-neural explainable PSO (FNE-PSO) framework for multi-objective dynamic flexible job shop scheduling (DFJSP). The framework integrates interval type-2 fuzzy sets (IT2FS) to model dual uncertainty in processing times and machine availability, an adaptive neuro-fuzzy inference system (ANFIS) to regulate PSO parameters based on swarm-state indicators, and a hybrid SHAP decision-tree explanation module to interpret particle movement and search behavior. It also introduces dynamic contribution radar (DCR) visualization to support understanding multi-objective trade-offs and solution evolution. Experiments on synthetic dynamic scenarios and adapted benchmark instances demonstrate that the proposed approach achieves more robust scheduling performance than representative baselines, particularly in terms of makespan and tardiness stability under uncertainty. Beyond optimization results, evaluation of explainability indicate that the proposed framework enhances transparency and interpretability of scheduling decisions, supporting more trustworthy and accountable industrial decision-making.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131553"},"PeriodicalIF":7.5,"publicationDate":"2026-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192844","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

IVYA-FMGRU: A frequency-domain context interaction model with bio-inspired optimization for significant wave height prediction IVYA-FMGRU：一个具有生物启发优化的频域上下文相互作用模型，用于显著波高预测

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

Expert Systems with Applications

Pub Date : 2026-02-06 DOI: 10.1016/j.eswa.2026.131534

Xiujing Gao , Yongfeng Xie , Fanchao Lin , Chiwang Lin , Hongwu Huang , Ziru Wang

Accurate prediction of significant wave heights is crucial for the safety of marine structures and ships. Traditional models struggle to capture the key frequency and periodic characteristics in wave height data. To address this issue, a novel Ivy Algorithm-Fast Fourier Transform Mogrifier Gated Recurrent Unit (IVYA-FMGRU) model is proposed, which integrates the gated recurrent unit (GRU) with the fast Fourier transform (FFT) and Mogrifier operations. The FFT extracts periodic features, the Mogrifier enhances the interaction between the GRU and frequency information, and the Ivy algorithm (IVYA), a bio-inspired optimization method, optimizes the model parameters. In addition, random forest (RF) is employed for feature selection. Experimental results show that the IVYA-FMGRU model achieves R² scores of 0.8505, 0.8683, and 0.8910 on datasets 46027, 46083, and 46084, respectively outperforming other baseline models. Furthermore, error statistical analysis across different wave height intervals confirms the model’s accuracy and stability within each interval, demonstrating its superior performance and generalization capability in wave height prediction.

有效浪高的准确预测对海洋结构物和船舶的安全至关重要。传统模式难以捕捉波高数据中的关键频率和周期特征。为了解决这一问题，提出了一种新的Ivy算法-快速傅里叶变换Mogrifier门控循环单元（IVYA-FMGRU）模型，该模型将门控循环单元（GRU）与快速傅里叶变换（FFT）和Mogrifier运算相结合。FFT提取周期特征，Mogrifier增强GRU和频率信息之间的交互作用，Ivy算法（IVYA）是一种仿生优化方法，用于优化模型参数。此外，采用随机森林（RF）进行特征选择。实验结果表明，IVYA-FMGRU模型在数据集46027、46083和46084上的R2得分分别为0.8505、0.8683和0.8910，优于其他基线模型。通过不同波高区间的误差统计分析，证实了模型在每个区间内的准确性和稳定性，证明了模型在波高预测方面的优越性能和泛化能力。

{"title":"IVYA-FMGRU: A frequency-domain context interaction model with bio-inspired optimization for significant wave height prediction","authors":"Xiujing Gao , Yongfeng Xie , Fanchao Lin , Chiwang Lin , Hongwu Huang , Ziru Wang","doi":"10.1016/j.eswa.2026.131534","DOIUrl":"10.1016/j.eswa.2026.131534","url":null,"abstract":"<div><div>Accurate prediction of significant wave heights is crucial for the safety of marine structures and ships. Traditional models struggle to capture the key frequency and periodic characteristics in wave height data. To address this issue, a novel Ivy Algorithm-Fast Fourier Transform Mogrifier Gated Recurrent Unit (IVYA-FMGRU) model is proposed, which integrates the gated recurrent unit (GRU) with the fast Fourier transform (FFT) and Mogrifier operations. The FFT extracts periodic features, the Mogrifier enhances the interaction between the GRU and frequency information, and the Ivy algorithm (IVYA), a bio-inspired optimization method, optimizes the model parameters. In addition, random forest (RF) is employed for feature selection. Experimental results show that the IVYA-FMGRU model achieves R<sup>2</sup> scores of 0.8505, 0.8683, and 0.8910 on datasets 46027, 46083, and 46084, respectively outperforming other baseline models. Furthermore, error statistical analysis across different wave height intervals confirms the model’s accuracy and stability within each interval, demonstrating its superior performance and generalization capability in wave height prediction.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"313 ","pages":"Article 131534"},"PeriodicalIF":7.5,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146154273","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

Deep global-ranking hashing via average precision approximation for large-scale image retrieval 基于平均精度近似的深度全局排序哈希算法用于大规模图像检索

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

Expert Systems with Applications

Pub Date : 2026-02-06 DOI: 10.1016/j.eswa.2026.131557

Lei Wang , Yongyue Fu , Qibing Qin , Lei Huang , Wenfang Zhang

Deep hashing algorithms have become a mainstream solution for large-scale multimedia retrieval due to their advantages in search efficiency and storage space. The algorithm is able to jointly learn semantic features and hash functions to encode raw data into compact binary codes, with significant differentiation. For the retrieval task, the central goal is to learn a ranking relation that can efficiently rank candidate results. Most of the existing hash methods adopt pair-wise or multi-wise strategies to learn the ranking results by minimizing the relative distance between similar samples or maximizing the distance between dissimilar samples. This type of approach can indeed improve the consistency of the local neighborhood, but its optimization objective is essentially limited to the local ranking relationship and fails to globally rank the samples in the entire retrieval set. Ultimately, this leads to the model possibly achieving good performance in local ranking but being unable to guarantee the overall relevance and stability of the global retrieval list. Especially when the sample distribution is complex or there is significant semantic overlap within or between categories; the local ranking method cannot fully capture the relationships among different samples, thereby limiting the discriminative ability and ranking quality of hash codes in actual retrieval scenarios. To address this issue, by introducing the average precision (AP) metric as the optimization objective, a novel Deep Global-ranking Hashing framework via average precision approximation (DGrH) is proposed to learn hash spaces with ranking relationships. Specifically, based on the discrete Heaviside function, a novel Ranking-AP optimization strategy is introduced into deep hashing to learn the global semantic relationships. The Sigmoid function is employed to smoothly approximate the non-differentiable discrete Heaviside function, making it differentiable. On this basis, the overall objective function and the novel Ranking-AP loss could enhance the learning of global ranking information. This helps capture and preserve high-quality high-quality global ranking relationships among samples more effectively in hash code learning. Extensive experiments on several benchmark datasets validate the efficacy of our designed DGrH framework, which consistently outperforms the mainstream deep hashing by large gaps. The code for the implementation of our DGrH framework is available at https://github.com/QinLab-WFU/DGrH.

深度哈希算法以其在搜索效率和存储空间方面的优势，成为大规模多媒体检索的主流解决方案。该算法能够联合学习语义特征和哈希函数，将原始数据编码为紧凑的二进制代码，具有显著的差异性。对于检索任务，中心目标是学习一种排序关系，可以有效地对候选结果进行排序。现有的哈希方法大多采用对智或多智策略，通过最小化相似样本之间的相对距离或最大化不相似样本之间的距离来学习排序结果。这种方法确实可以提高局部邻域的一致性，但其优化目标本质上局限于局部排序关系，无法对整个检索集中的样本进行全局排序。最终，这将导致该模型可能在局部排序中获得良好的性能，但无法保证全局检索列表的整体相关性和稳定性。特别是当样本分布复杂或类别内或类别之间存在明显的语义重叠时；局部排序方法不能充分捕捉不同样本之间的关系，从而限制了实际检索场景中哈希码的判别能力和排序质量。为了解决这一问题，通过引入平均精度（AP）度量作为优化目标，提出了一种新的基于平均精度近似（DGrH）的深度全局排序哈希框架，以学习具有排序关系的哈希空间。具体而言，基于离散的Heaviside函数，在深度哈希中引入了一种新的rank - ap优化策略来学习全局语义关系。利用Sigmoid函数平滑逼近不可微的离散Heaviside函数，使其可微。在此基础上，总体目标函数和新的rank - ap损失可以增强全局排名信息的学习。这有助于在哈希码学习中更有效地捕获和保存样本之间的高质量的高质量全局排序关系。在多个基准数据集上进行的大量实验验证了我们设计的DGrH框架的有效性，该框架始终优于主流深度哈希。实现DGrH框架的代码可从https://github.com/QinLab-WFU/DGrH获得。

{"title":"Deep global-ranking hashing via average precision approximation for large-scale image retrieval","authors":"Lei Wang , Yongyue Fu , Qibing Qin , Lei Huang , Wenfang Zhang","doi":"10.1016/j.eswa.2026.131557","DOIUrl":"10.1016/j.eswa.2026.131557","url":null,"abstract":"<div><div>Deep hashing algorithms have become a mainstream solution for large-scale multimedia retrieval due to their advantages in search efficiency and storage space. The algorithm is able to jointly learn semantic features and hash functions to encode raw data into compact binary codes, with significant differentiation. For the retrieval task, the central goal is to learn a ranking relation that can efficiently rank candidate results. Most of the existing hash methods adopt pair-wise or multi-wise strategies to learn the ranking results by minimizing the relative distance between similar samples or maximizing the distance between dissimilar samples. This type of approach can indeed improve the consistency of the local neighborhood, but its optimization objective is essentially limited to the local ranking relationship and fails to globally rank the samples in the entire retrieval set. Ultimately, this leads to the model possibly achieving good performance in local ranking but being unable to guarantee the overall relevance and stability of the global retrieval list. Especially when the sample distribution is complex or there is significant semantic overlap within or between categories; the local ranking method cannot fully capture the relationships among different samples, thereby limiting the discriminative ability and ranking quality of hash codes in actual retrieval scenarios. To address this issue, by introducing the average precision (AP) metric as the optimization objective, a novel Deep Global-ranking Hashing framework via average precision approximation (DGrH) is proposed to learn hash spaces with ranking relationships. Specifically, based on the discrete Heaviside function, a novel Ranking-AP optimization strategy is introduced into deep hashing to learn the global semantic relationships. The Sigmoid function is employed to smoothly approximate the non-differentiable discrete Heaviside function, making it differentiable. On this basis, the overall objective function and the novel Ranking-AP loss could enhance the learning of global ranking information. This helps capture and preserve high-quality high-quality global ranking relationships among samples more effectively in hash code learning. Extensive experiments on several benchmark datasets validate the efficacy of our designed DGrH framework, which consistently outperforms the mainstream deep hashing by large gaps. The code for the implementation of our DGrH framework is available at <span><span>https://github.com/QinLab-WFU/DGrH</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131557"},"PeriodicalIF":7.5,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192701","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

Bayesian inference of nonlinear malaria dynamics in Ghana via an ensemble Markov chain Monte Carlo sampler 基于马尔可夫链蒙特卡罗采样器的加纳非线性疟疾动力学贝叶斯推断

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

Expert Systems with Applications

Pub Date : 2026-02-06 DOI: 10.1016/j.eswa.2026.131540

T. Ansah-Narh , Y. Asare Afrane , J. Bremang Tandoh

Reliable quantification of malaria dynamics in sub-Saharan Africa remains hindered by short, noisy, and spatially heterogeneous surveillance records that challenge the assumptions of conventional deterministic models. In Ghana, health-facility data between 2014 and 2023 reveal highly non-linear and age-specific fluctuations in hospital admissions, yet existing approaches struggle to capture such stochastic variability or provide credible uncertainty bounds. This study develops a Bayesian nonlinear inference framework that integrates a cubic deterministic baseline with a damped oscillatory kernel, estimated via an affine-invariant ensemble Markov Chain Monte Carlo sampler. The framework accommodates limited data, explicitly models parameter uncertainty, and generates probabilistic forecasts of malaria admissions for children under five years and individuals aged five years or more. Results demonstrate that the proposed hybrid cubic-damped oscillatory kernel model achieves strong empirical adequacy (

R^{2} = 0.9958

for  < 5 years;

R^{2} = 0.9956

for  ≥ 5 years) with residual errors below 2% and unimodal, well-mixed posterior distributions confirming robust convergence. District-level analysis reveals pronounced spatial heterogeneity, with coefficients of variation ranging from  < 0.07 in stable urban centres such as Kumasi to  > 3.3 in peripheral districts including Mpohor and Bia East. Forecasts for 2024–2026 indicate a gradual resurgence in admissions, increasing from approximately 137,000 to 149,000 cases among children under five and from 348,000 to 375,000 among older individuals, with uncertainty widening modestly over time. By producing interpretable probabilistic forecasts, this Bayesian framework provides a principled tool for anticipating short-term malaria fluctuations, guiding resource allocation, and strengthening data-driven decision-making within Ghana’s national malaria control strategy.

撒哈拉以南非洲疟疾动态的可靠量化仍然受到短期、嘈杂和空间异质性监测记录的阻碍，这些记录挑战了传统确定性模型的假设。在加纳，2014年至2023年期间的卫生设施数据显示，住院人数的波动高度非线性，且随年龄而异，但现有方法难以捕捉这种随机变异性，或提供可信的不确定性界限。本研究开发了一个贝叶斯非线性推理框架，该框架集成了三次确定性基线和阻尼振荡核，通过仿射不变系综马尔可夫链蒙特卡罗采样器估计。该框架可容纳有限的数据，明确模拟参数的不确定性，并生成5岁以下儿童和5岁或5岁以上个人疟疾入院的概率预测。结果表明，所提出的混合三阻尼振荡核模型具有较强的经验充分性（对于 <； 5年，R2=0.9958；对于 ≥ 5年，R2=0.9956），残差小于2%，单峰、混合良好的后验分布证实了鲁棒性收敛。区级分析显示出明显的空间异质性，变异系数从库马西等稳定城市中心的 <； 0.07到包括Mpohor和Bia East在内的外围地区的 >； 3.3不等。对2024-2026年的预测表明，入院人数逐渐回升，五岁以下儿童的病例从大约13.7万增加到14.9万，老年人的病例从34.8万增加到37.5万，不确定性随着时间的推移而适度扩大。通过产生可解释的概率预测，该贝叶斯框架为预测短期疟疾波动、指导资源分配和加强加纳国家疟疾控制战略中的数据驱动决策提供了一个原则性工具。

{"title":"Bayesian inference of nonlinear malaria dynamics in Ghana via an ensemble Markov chain Monte Carlo sampler","authors":"T. Ansah-Narh , Y. Asare Afrane , J. Bremang Tandoh","doi":"10.1016/j.eswa.2026.131540","DOIUrl":"10.1016/j.eswa.2026.131540","url":null,"abstract":"<div><div>Reliable quantification of malaria dynamics in sub-Saharan Africa remains hindered by short, noisy, and spatially heterogeneous surveillance records that challenge the assumptions of conventional deterministic models. In Ghana, health-facility data between 2014 and 2023 reveal highly non-linear and age-specific fluctuations in hospital admissions, yet existing approaches struggle to capture such stochastic variability or provide credible uncertainty bounds. This study develops a Bayesian nonlinear inference framework that integrates a cubic deterministic baseline with a damped oscillatory kernel, estimated via an affine-invariant ensemble Markov Chain Monte Carlo sampler. The framework accommodates limited data, explicitly models parameter uncertainty, and generates probabilistic forecasts of malaria admissions for children under five years and individuals aged five years or more. Results demonstrate that the proposed hybrid cubic-damped oscillatory kernel model achieves strong empirical adequacy (<span><math><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.9958</mn></mrow></math></span> for  < 5 years; <span><math><mrow><msup><mi>R</mi><mn>2</mn></msup><mo>=</mo><mn>0.9956</mn></mrow></math></span> for  ≥ 5 years) with residual errors below 2% and unimodal, well-mixed posterior distributions confirming robust convergence. District-level analysis reveals pronounced spatial heterogeneity, with coefficients of variation ranging from  < 0.07 in stable urban centres such as Kumasi to  > 3.3 in peripheral districts including Mpohor and Bia East. Forecasts for 2024–2026 indicate a gradual resurgence in admissions, increasing from approximately 137,000 to 149,000 cases among children under five and from 348,000 to 375,000 among older individuals, with uncertainty widening modestly over time. By producing interpretable probabilistic forecasts, this Bayesian framework provides a principled tool for anticipating short-term malaria fluctuations, guiding resource allocation, and strengthening data-driven decision-making within Ghana’s national malaria control strategy.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"312 ","pages":"Article 131540"},"PeriodicalIF":7.5,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192714","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