{"title":"Truck scheduling optimization at a cold chain cross-docking terminal considering uncertainties and the door-mixed service mode","authors":"Feifeng Zheng , Yuzhi Yi , Ming Liu , Huaxin Qiu","doi":"10.1016/j.eswa.2025.129849","DOIUrl":"10.1016/j.eswa.2025.129849","url":null,"abstract":"<div><div>The increasing global demand for perishable agricultural products necessitates advancements in cold chain logistics. Cross-docking, known for its efficiency, is particularly well-suited for the transfer and distribution of such goods. However, truck scheduling at cold chain cross-dock terminals (CDTs) presents unique challenges, including product perishability, stringent time windows, and temperature-controlled environments. This work investigates a truck scheduling problem within a cold chain CDT, explicitly addressing uncertainties in refrigerated product damage (affecting supply) and repackaging times. A two-stage stochastic programming model is developed to capture these uncertainties. To solve this model, a scenario reduction approach employing K-means++ and K-medoids clustering is used, followed by Sample Average Approximation. Small-scale instances are solved optimally using CPLEX. For larger instances, a novel hybrid heuristic algorithm, combining the global search capabilities of Genetic Algorithms with the local search capabilities of Adaptive Large Neighborhood Search and Simulated Annealing, is proposed. Numerical experiments demonstrate the effectiveness of this algorithm, and sensitivity analysis provides valuable managerial insights.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129849"},"PeriodicalIF":7.5,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221872","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}
{"title":"An RL-NSGA-DP algorithm for optimization of robot placement and trajectory allocation in mobile robotic grinding of wind turbine blades","authors":"Yi Hua, Xuewu Wang","doi":"10.1016/j.eswa.2025.129876","DOIUrl":"10.1016/j.eswa.2025.129876","url":null,"abstract":"<div><div>Mobile robot machining, offering a more flexible and reconfigurable approach compared to fixed-base robots, has therefore become a promising solution for efficiently machining large and complex wind turbine blades. In this context, determining proper machining placements and allocating machining trajectories are two pivotal factors in the mobile robotic automation grinding of wind turbine blades, directly affecting machining efficiency and quality. However, the highly nonlinear performance distribution of the robot in the task space, combined with the complexity of the machining surface, presents significant challenges. To address these challenges, this paper presents a general optimization model of this problem with the objectives of completion time and robot manipulability, considering singularity avoidance and collision avoidance. Based on this model, an improved non-dominated sorting genetic algorithm integrated with reinforcement learning and dual population co-evolution (RL-NSGA-DP) is developed. In RL-NSGA-DP, each solution is coded using a novel two-layer metavariable encoding scheme, and a tailored dominated-recessive crossover operator is designed. Moreover, a dual-population collaborative search strategy employing different operators and an adaptive switching environmental selection mechanism based on reinforcement learning are implemented to ensure the convergence and maintain population diversity. Comparative experiments on test instances and a practical case study demonstrate that RL-NSGA-DP outperforms five well-known multi-objective evolutionary algorithms, and effectively addresses robot placement and trajectory allocation problem in mobile robotic machining systems.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129876"},"PeriodicalIF":7.5,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222094","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}
{"title":"Adaptive energy management for battery swapping stations using HMDE-PSO: optimizing charge-discharge control against cyber-physical attacks","authors":"Mehdi Ahmadi Jirdehi , Hamdi Abdi , Hazhir Dousti","doi":"10.1016/j.eswa.2025.129860","DOIUrl":"10.1016/j.eswa.2025.129860","url":null,"abstract":"<div><div>Battery Swapping Stations (BSSs) are emerging as critical components in smart power systems, offering rapid energy refueling, grid load balancing, and improved battery lifecycle management for electric vehicles (EVs). However, the economic operation and cyber-physical security of BSSs remain underexplored, particularly in microgrids that integrate distributed generation (DG) and face increasing vulnerability to cyber-attacks. This paper presents a novel, adaptive energy management framework that optimally schedules the charge and discharge cycles of BSSs under uncertain EV user behavior and potential cyber-physical disruptions. A key innovation lies in modeling two types of cyber-attacks—power disruption and control hijacking—and embedding their technical and economic impacts directly into the optimization process. To solve this multi-objective problem, a Hybrid multi-objective Differential Evolution–Particle Swarm Optimization (HMDE-PSO) algorithm is proposed, which efficiently balances cost minimization, system reliability, and resilience. The framework is validated using the IEEE 69-bus distribution system, demonstrating substantial improvements: over 40% reduction in power losses, enhanced voltage stability, and lower operational costs compared to conventional methods. This work distinguishes itself by integrating cyber-defense considerations with real-time energy scheduling, providing a comprehensive and resilient solution for future BSS-integrated microgrids.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129860"},"PeriodicalIF":7.5,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145189961","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}
Md.Reduanul Haque , Andrew Mehnert , William Huxley Morgan , Graham Mann , Ferdous Sohel
{"title":"A computational learning pipeline for glaucoma progression detection based on the prediction of visual field changes from fundus photographs","authors":"Md.Reduanul Haque , Andrew Mehnert , William Huxley Morgan , Graham Mann , Ferdous Sohel","doi":"10.1016/j.eswa.2025.129907","DOIUrl":"10.1016/j.eswa.2025.129907","url":null,"abstract":"<div><div>Detection of glaucoma progression is crucial to managing patients, permitting individualized care plans and treatment. It is a challenging task requiring the assessment of structural changes to the optic nerve head and functional changes based on visual field testing. Artificial intelligence, especially deep learning techniques, has shown promising results in many applications, including glaucoma diagnosis. This paper proposes a two-stage computational learning pipeline for detecting glaucoma progression using only fundus photographs. In the first stage, a deep learning model takes a time series of fundus photographs as input and outputs a vector of predictions where each element represents the overall rate of change in visual field (VF) sensitivity values for a sector (region) of the optic nerve head (ONH). We implemented two deep learning models—ResNet50 and InceptionResNetV2—for this stage. In the second stage, a binary classifier (weighted logistic regression) takes the predicted vector as input to detect progression. We also propose a novel method for constructing annotated datasets from temporal sequences of clinical fundus photographs and corresponding VF data suitable for machine learning. Each dataset <em>element</em> comprises a temporal sequence of photographs together with a vector-valued label. The label is derived by computing the pointwise linear regression of VF sensitivity values at each VF test location, mapping these locations to eight ONH sectors, and assigning the overall rate of change in each sector to one of the elements of the vector. We used a retrospective clinical dataset with 82 patients collected at multiple timepoints over five years in our experiments. The InceptionResNetV2-based implementation yielded the best performance, achieving detection accuracies of 97.28 ± 1.10 % for unseen test data (i.e., each dataset element is unseen but originates from the same set of patients appearing in the training dataset), and 87.50 ± 0.70 % for test data from unseen patients (training and testing patients are entirely different). The testing throughput was 11.60 ms per patient. These results demonstrate the efficacy of the proposed method for detecting glaucoma progression from fundus photographs.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129907"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222008","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}
{"title":"Fuzzy prototype transfer learning for non-overlapping cross-domain recommendation","authors":"Ruxia Liang , Qinglin Huang , Xiaoxuan Shen","doi":"10.1016/j.eswa.2025.129852","DOIUrl":"10.1016/j.eswa.2025.129852","url":null,"abstract":"<div><div>Cross-domain recommendation (CDR) offers an efficient and effective solution to mitigate data sparsity in recommender systems. Existing research primarily focuses on exploring knowledge transfer based on overlapping entities or auxiliary contents between domains. However, there is little research on the real non-overlapping cross-domain recommendation (NCDR) problems, even though it poses a more general and applicable prospect. The core challenge of NCDR lies in the difficulty of finding the correct and useful knowledge transfer bridge between domains without relying on the explicit overlapping identities. Utilizing the inherent similarity and fuzzy characteristics of users and items in the latent feature space, this paper investigates a Fuzzy Prototype Transfer (FPT) learning method for the NCDR problem. FPT jointly optimizes prototypes and individual features for both users and items in target domain under the guidance of source features. An end-to-end learnable fuzzy clustering module based on maximum entropy regularization is proposed to learn both user and item fuzzy clustering assignments and fuzzy fusion prototypes. Lastly, by constructing an asymmetric dual-prototype fuzzy transfer module, similar user and item features across domains are found and aligned effectively. Extensive experiments demonstrate FPT’s superior performance over the state-of-the-art methods while maintaining lower inference and memory costs than those of the baselines.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129852"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221878","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}
{"title":"GRDGNN: A directed graph neural network framework for multi-relational inference of gene regulatory networks","authors":"Wanhong Zhang , Zhenyu Guo","doi":"10.1016/j.eswa.2025.129827","DOIUrl":"10.1016/j.eswa.2025.129827","url":null,"abstract":"<div><div>Inferring gene regulatory networks (GRNs) from gene expression data is a central challenge in systems biology. Graph neural networks (GNNs) offer a promising approach due to their ability to process graph-structured data. However, existing GNN methods for GRN inference often treat the problem as binary classification, limiting their ability to capture comprehensive regulatory relationships. This paper introduces two learning algorithms that utilize an end-to-end gene regulatory directed graph neural network (GRDGNN) schema for efficient inference of causal relationships in large-scale networks. These algorithms incorporate a directed graph neural network (DGNN) and a graph multi-classification task to identify explicit interactions between transcription factors (TFs) and target genes. The proposed approach consists of four key steps: (1) constructing a directed initial network using regression Pearson correlation and mutual information analysis, (2) extracting subgraphs of observed TF-gene pairs and applying a DGNN for information aggregation, (3) projecting the aggregated information into a low-dimensional space using graph pooling to generate graph representations of TF-gene pairs, and (4) classifying subgraphs using a multilayer perceptron (MLP) for link prediction and inference of explicit regulatory relationships. Evaluation of the DREAM5 microarray and scRNA-seq datasets demonstrates that our transductive and inductive learning methods can accurately and effectively infer explicit regulatory relationships compared to benchmark methods. These results demonstrate that the proposed GRDGNN schema exhibits strong generalization across species, data types, and modalities in cross-species, cross-data type, and cross-modality learning.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129827"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221876","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}
Yongzhe Xiang , Zili Wang , Shuyou Zhang , Le Wang , Caicheng Wang , Yaochen Lin , Jianrong Tan
{"title":"Operator learning-based springback behavior prediction for complex-shaped tube free-bending forming","authors":"Yongzhe Xiang , Zili Wang , Shuyou Zhang , Le Wang , Caicheng Wang , Yaochen Lin , Jianrong Tan","doi":"10.1016/j.eswa.2025.129899","DOIUrl":"10.1016/j.eswa.2025.129899","url":null,"abstract":"<div><div>Free-bending (FB) technology enables the efficient processing of spatially complex-shaped tubes. Springback causes variations in curvature and torsion of the tube axis during the FB process. The mapping relationship of bent tube curvature and torsion from ideal to actual values can be abstracted as nonlinear physical operators. This paper first proposes a novel six-axis FB processing method that can control geometric features of tube transition segments. Then, an operator learning-based springback behavior prediction (OL-SBP) framework is presented, which includes an OL module and an SBP module. A feature-information-enhanced deep operator network (FIE-DeepONet) is integrated into the first module to learn tube springback operators. The curvature and torsion predicted by the OL module are then fed into the SBP module to calculate the overall shape of the springback axis. This paper also introduces a set of similarity evaluation indicators that are independent of the curve’s spatial attitude. Planar and spatial bent tubes are selected as case studies. Results show that the framework yields more accurate predictions compared to the analytical model. The framework also exhibits excellent generalization performance. Once FIE-DeepONet has learned the springback operators, it can accurately predict the springback curvature and torsion, even for tube shapes not present during training.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129899"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222002","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}
Thi-Phuong Nguyen , Chin-Lung Huang , Louis Cheng-Lu Yeng , Yi-Kuei Lin
{"title":"Exact reliability of cold chain networks with multi-state travel time and transport capacity","authors":"Thi-Phuong Nguyen , Chin-Lung Huang , Louis Cheng-Lu Yeng , Yi-Kuei Lin","doi":"10.1016/j.eswa.2025.129892","DOIUrl":"10.1016/j.eswa.2025.129892","url":null,"abstract":"<div><div>Post-pandemic lifestyle changes have increased reliance on e-commerce, boosting the logistics sector. One of the most highly regarded industries is cold chain logistics, especially for vaccines and refrigerated foods. In cold chain networks, transport routes have varying capacities based on customer orders, and travel times fluctuate due to traffic and weather. Thus, this study focuses on evaluating network reliability, i.e., the probability to meet given demands within the specified time threshold, of cold chain networks considering the two multi-state factors: travel time and transport capacity. To account for practical situations, a multi-state cold chain network (MCCN) is constructed with retailers, third-party logistics companies, and suppliers as nodes, and transportation routes as arcs. The concept of minimal path is used to determine the transport flow that complies with the time threshold and to determine the transport capacity vectors that satisfy the demands. An algorithm is proposed to resolve different characteristics of time thresholds and demand requirements for efficient assessment. Network reliability is successfully calculated, as shown in the case and sensitivity analysis. This allows managers to grasp the performance of MCCN and make informed decisions based on the achieved network reliability.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129892"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222005","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}
Kang An , Ming-Yu Lu , Yan-Kai Tian , Yi-Jia Zhang
{"title":"DFHD: dual-granularity fusion network using historical drugs for drug recommendation","authors":"Kang An , Ming-Yu Lu , Yan-Kai Tian , Yi-Jia Zhang","doi":"10.1016/j.eswa.2025.129693","DOIUrl":"10.1016/j.eswa.2025.129693","url":null,"abstract":"<div><div>Drug recommendation is a task in clinical medicine aimed at suggesting a set of safe and effective medications based on a patient’s electronic health records. Current approaches either rely on diagnoses and procedures documented in electronic health records to recommend drug combinations or focus on enhancing drug recommendation safety by considering drug-drug interactions. However, these approaches often overlook the significance of historical medication information in drug recommendation despite its strong correlation with current diagnostic and prescription recommendation. Therefore, we propose a Dual-granularity Fusion Network using Historical Drugs. Specifically, at the time-series modeling level, recurrent neural networks are used to extract time-series features from historical drug data to construct coarse-grained drug characterizations. At the molecular structure modeling level, a graph neural network is used to build a relationship map between drug molecular structures and drug substructures to capture the fine-grained interactions within drug molecules. In addition, we designed a historical drug molecule awareness module to capture historical drug information during drug molecule modeling so as to identify the drugs that really help to cure patients. To effectively integrate dual-granularity information, we design a dual-granularity fusion module to realize the synergistic learning of temporal and structural features. To ensure drug safety, we introduce the DDI loss function to adaptively adjust the loss weights based on the drug interaction risk results, taking into account the optimization goals of efficacy and safety. Our source code is available at <span><span>https://github.com/AK-321/DFHD</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129693"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220908","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}
Jing Zhang , Aibin Zhu , Bingsheng Bao , Xinyu Wu , Chunli Zheng , Meng Li , Jing Wang , Yu Zhang , Xue Wu , Xiao Li
{"title":"Novel design and speed-adaptive control of a cable-driven parallel elastic hip exoskeleton for compliant locomotion assistance","authors":"Jing Zhang , Aibin Zhu , Bingsheng Bao , Xinyu Wu , Chunli Zheng , Meng Li , Jing Wang , Yu Zhang , Xue Wu , Xiao Li","doi":"10.1016/j.eswa.2025.129871","DOIUrl":"10.1016/j.eswa.2025.129871","url":null,"abstract":"<div><div>Robotic hip exoskeletons hold enormous potential to enhance human locomotion. However, the rigid structures and predefined control laws limit their compliance and adaptability during dynamic human-robot interactions. Here, a novel parallel elastic hip exoskeleton is developed for human locomotion assistance. The exoskeleton utilizes a remote cable actuation system to improve compliance and incorporates a parallel elastic mechanism at the hip wearable components to enhance actuator energy efficiency by generating a compensatory torque. For exoskeleton control, a speed-adaptive torque control strategy is implemented to modulate the assistance torque in real time, based on the user’s gait phase and hip movement frequency estimated by adaptive oscillators. The system was tested on seven healthy subjects, and preliminary results indicate that the parallel elastic element achieves a 40.2 % reduction in peak motor torque through energy conversion. The controller exhibits excellent torque tracking performance and effectively extracts human gait features across walking speeds with hip frequency correlation (<em>R</em><span><math><msup><mrow></mrow><mn>2</mn></msup></math></span> = 0.89). Furthermore, the hip exoskeleton significantly reduced users’ peak hip moments and muscle activity while preserving natural kinematics. The parallel elastic hip exoskeleton demonstrates strong adaptive assistive capabilities and is expected to enhance locomotion in real-world applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"298 ","pages":"Article 129871"},"PeriodicalIF":7.5,"publicationDate":"2025-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145221473","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}