Expert Systems with Applications最新文献

{"title":"Corrigendum to “Class distance weighted cross entropy loss for classification of disease severity”[Expert Syst. Appl. 269 (2025) 126372]","authors":"Gorkem Polat, Ümit Mert Çağlar, Alptekin Temizel","doi":"10.1016/j.eswa.2025.128626","DOIUrl":"10.1016/j.eswa.2025.128626","url":null,"abstract":"","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"287 ","pages":"Article 128626"},"PeriodicalIF":7.5,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518547","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":"AGGNM Vis: Allosteric pocket prediction based on multidimensional feature comparison visual analysis","authors":"Dongliang Guo ,&nbsp;Xiyuan Zhang ,&nbsp;Li Feng ,&nbsp;Yapeng Liu","doi":"10.1016/j.eswa.2025.128790","DOIUrl":"10.1016/j.eswa.2025.128790","url":null,"abstract":"<div><div>Accurate identification of allosteric pockets is key to the development of allosteric drugs. Pockets within the same protein often have certain topological connections, and traditional methods that rely on static features to predict allosteric pockets may ignore the topological relationships between pockets. To address this issue, this paper proposes a new visual analysis method called AGGNM Vis. Firstly, to address the weakness in model prediction due to the lack of dynamic pocket features, static and dynamic features of pockets are calculatedand integrated as multidimensional features of pockets. Then, an allosteric pocket prediction method named AGGNM is constructed based on AutoGluon. Secondly, to solve the problem of missing potential allosteric pockets due to the lack of topological relationship analysis between pockets, AGGNM Vis conducts multi-scale comparative visual analysis on the allosteric pockets predicted by AGGNM and other pockets. The analysis compares spatial correlations, feature values, and spatial structures between pockets, assisting users in identifying potential allosteric pockets. This provides a new research perspective for allosteric pocket prediction. The experimental results show that AGGNM Vis can effectively predict the allosteric pocket, which is helpful for the development of allosteric drugs.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128790"},"PeriodicalIF":7.5,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501573","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":"TEPP: A robust trust-enhanced privacy-preserving quality of service prediction method for web service recommendation","authors":"Wei-wei Wang ,&nbsp;Wenping Ma ,&nbsp;Kun Yan","doi":"10.1016/j.eswa.2025.128786","DOIUrl":"10.1016/j.eswa.2025.128786","url":null,"abstract":"<div><div>In today’s service-oriented digital environment, ensuring the quality of service (QoS) is crucial, which makes QoS prediction a prominent topic in current research on Web service recommendation. Recently, some existing works have made significant advancements in modeling both users and services. However, several key issues have not been well studied in existing research, including issues related to bilateral trust, user preferences, and privacy protection. To effectively resolve these concerns, we put forward TEPP, a robust trust-enhanced privacy-preserving QoS prediction method for Web service recommendation. First, we evaluate user reputation values through the Dirichlet distribution and integrate user similarity to jointly compute trust values between users, thereby identifying a group of trustworthy and similar users. At the same time, we utilize an exponential mechanism to protect the privacy of user information. Secondly, we calculate the preference similarity between users, taking into account their preferences. Finally, we determine a set of trustworthy similar services by combining the reputation value and similarity of the service providers, and predict missing QoS by a fusion model that integrates the above three methods. To make TEPP more practical and robust in Web service recommendation, we embed a bilateral trust model in TEPP based on evolutionary game theory to constrain and guide users and service providers to honestly participate in the Web service recommendation. Experimental simulation results demonstrate that the proposed scheme not only outperforms existing schemes in prediction accuracy but also can fully motivate both users and service providers to choose trusted strategic behaviors in the Web service recommendation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128786"},"PeriodicalIF":7.5,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501580","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":"Local plane estimation network with multi-scale fusion for efficient monocular depth estimation","authors":"Lei Song,&nbsp;Bo Jiang,&nbsp;Huaibo Song","doi":"10.1016/j.eswa.2025.128746","DOIUrl":"10.1016/j.eswa.2025.128746","url":null,"abstract":"<div><div>Estimating scene depth from a single image is a critical yet challenging task in computer vision, with widespread applications in autonomous driving, 3D reconstruction, and scene understanding. In monocular depth estimation, effective depth representation and accurate extraction and integration of local details are crucial for reliable results. However, existing methods face two major challenges in dealing with complex depth relationships. (a) a lack of efficient feature representation mechanisms, often relying on pixel-level dense depth estimation to capture local details, which leads to significant computational overhead and (b) inefficiency in extending the depth representation range, particularly when distinguishing near and far objects, making it difficult to effectively balance global depth relationships and local details. To address these challenges, this study introduces the Local Plane Estimation with Multi-Scale Fusion Network (LMNet) for monocular depth estimation. The encoder utilizes stacked Transformer blocks to extract multi-scale global depth features and capture long-range dependencies. The decoder incorporates a Local Plane Estimation (LPE) module that generates local plane parameters from multi-scale features, enabling efficient recovery of depth details and improving local accuracy. Furthermore, the Multi-scale Attentive Fusion (MAF) module performs weighted fusion of multi-scale depth features using attention mechanisms, adaptively assigning contribution weights, reducing redundancy, and dynamically prioritizing feature integration to ensure structural consistency and detailed representation in the depth map. The synergistic design of these modules significantly enhances both the quality and efficiency of monocular depth estimation. Extensive experiments show that LMNet achieves significant advantages in both depth estimation accuracy and computational efficiency. Compared to NeWCRFs, LMNet achieves a 15.05 % reduction in RMSE error and a 10.63 % decrease in inference time on the NYU Depth V2 dataset, while compressing its model size to just 11.3 MB. In zero-shot evaluation on the high-resolution HRWSI dataset, LMNet attains an average inference latency of only 90.9 ms and an RMSE of 0.355, further validating its excellent balance between fast inference and high-precision estimation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"293 ","pages":"Article 128746"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144481035","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":"Intelligent generation of personalized cardiovascular healthcare program based on knowledge network","authors":"Yaqin Lin ,&nbsp;Weiqiang Zhang ,&nbsp;Quanchen Liu","doi":"10.1016/j.eswa.2025.128718","DOIUrl":"10.1016/j.eswa.2025.128718","url":null,"abstract":"<div><div>We convert a knowledge base for Cardiovascular disease into a fuzzy Petri net and use the parallel inference method based on matrix operations to intelligently generate the healthcare programs involving exercise, diet, living, and auxiliary medication plans. The algorithms used by our system consider personal health characteristics and environmental factors to extract valuable health information. By analyzing this information, the system can provide users with accurate recommendations and personalized health insights, significantly enhancing their overall well-being. Besides, the method can automatically identify and resolve contradictory rules in knowledge inference, ensuring the validity and accuracy of program recommendations. Our recommendation algorithms create personalized diet plans based on income, preferences, and restrictions. We also classify and suggest diet plans based on the nine diet categories in the Chinese Food Guide Pagoda. We present a case study of Cardiovascular disease to showcase the effectiveness and efficiency of our method.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128718"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501575","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":"HyperMem: Hypernetwork with memory for forgetting problem in federated reinforcement learning","authors":"Suhang Wei,&nbsp;Xiang Feng,&nbsp;Yang Xu,&nbsp;Huiqun Yu","doi":"10.1016/j.eswa.2025.128671","DOIUrl":"10.1016/j.eswa.2025.128671","url":null,"abstract":"<div><div>Federated reinforcement learning plays a crucial role in decentralized and privacy-preserving policy optimization but is challenged by task heterogeneity and client dropout. Several approaches proposed for these issues, but few consider their combined impact. In this paper, we reveal the catastrophic forgetting phenomenon arising from their coexistence, which significantly degrades the global model’s performance on offline clients. We formally define this forgetting problem and establish an exponential convergence rate for hypernetwork-based federated learning methods, highlighting the adverse effects of embedding length on forgetting. Furthermore, we demonstrate the equivalence between the mean squared error loss and the chain rule in hypernetwork updates, introducing a novel updating paradigm. Based on our theoretical insights, we propose HyperMem with three key components: (1) Constrained Principal Component Embedding, which limits embedding length and enhances hypernetwork priors; (2) In-cluster and Out-cluster Losses, designed under the new updating paradigm to dynamically select fitting targets and mitigate, or even resolve, forgetting problems; and (3) Adapter Pool, enabling federated training of structurally heterogeneous client models caused by greater task heterogeneity. Comprehensive experiments demonstrate that HyperMem effectively overcomes the forgetting problem, improving training performance by 14.95 % compared to state-of-the-art methods. We implemented HyperMem as a pluggable Spark service for practical applications, reducing job runtime by 42.38 % and communication costs by 98.6 %, while ensuring data security.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128671"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513536","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 optimal document clustering method using hybrid optimal feature selection and efficient soft computing classifier","authors":"Perumal Pitchandi,&nbsp;R. Kingsy Grace","doi":"10.1016/j.eswa.2025.128762","DOIUrl":"10.1016/j.eswa.2025.128762","url":null,"abstract":"<div><div>In general, document grouping is an important area of text extraction commonly used for document organization, browsing, abstraction, and categorization. This is an important process used for data recovery, data processing and document management. Recently several document grouping methods have been suggested to improve system performance. However, these document grouping methods face serious challenges. The main problem with document grouping is choosing the appropriate document features and similar tools. Moreover, due to the high computational cost and memory usage of those grouping methods, they are not suitable for many documents that need to be processed on a daily basis. This paper presents the optimal method of document clustering based on hybrid optimization selection and efficient computer classification. The proposed method consists three tire processes. First, we introduce a fuzzy density fruit fly optimization (FD-FFO) algorithm for data pre-processing which removes the unwanted artifacts and redundant content from the documents. Second, we illustrate the teaching–learning-based Harris Hawks optimization (TL-HHO) algorithm for optimal feature selection which computes best and optimal features among multiple features in document. Then, we offer a support vector regression probabilistic neural network (SVR-PNN) for optimal document clustering which improves the performance of clustering. Finally, the proposed SVR-PNN method which is evaluated by Reuters, 20 Press database and Web-snippets database. The performance of proposed SVR-PNN method can compare with existing methods such as Rider-Moth Flame optimization algorithm (RMFO), Correlation Based Incremental Clustering Algorithm (CBICA), Incremental Construction of GMM Tree (ICGT) and Weighted Probabilistic Latent Semantic Analysis (WPLSA) using Precision, Accuracy, F-Measure and Recall.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128762"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144513538","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":"FIGS-SLAM: Gaussian splatting SLAM with dynamic frequency control and influence-based pruning","authors":"Zhangzhen Zhao ,&nbsp;Qiang Liu ,&nbsp;Jinglong Zhu ,&nbsp;Zikai Yao ,&nbsp;Yu Lu ,&nbsp;Qing Li","doi":"10.1016/j.eswa.2025.128763","DOIUrl":"10.1016/j.eswa.2025.128763","url":null,"abstract":"<div><div>Recent advancements in 3D Gaussian Splatting (3DGS)-based SLAM have significantly improved scene reconstruction compared to traditional SLAM and Neural Radiance Field (NeRF) SLAM, enabling high-quality reconstruction, precise pose estimation, and real-time scene rendering. However, existing approaches still suffer from limitations in detail representation, resulting in mediocre rendering quality. To address these challenges, we propose a new SLAM system, FIGS-SLAM, which utilizes a dynamic frequency-controlled coarse-to-detail map building strategy. Initially, low-frequency components are used to establish a coarse map representation, avoiding premature reliance on high-frequency details and effectively mitigating ambiguities introduced by noise and inaccurate data. As the map construction advances, high-frequency components are gradually incorporated, allowing the system to capture and render intricate geometric details accurately. This coarse-to-fine mapping approach progressively refines the scene representation to achieve higher detail and accuracy. Considering that frequency regularization may generate a large number of redundant 3D Gaussian ellipsoids, we further introduce an influence-based Gaussian pruning strategy. This strategy dynamically prunes Gaussian points with minimal impact on the map by evaluating their transparency, transmission rates, and consensus relationships, thereby enhancing the system’s overall accuracy and efficiency. Experimental results on two datasets show that our method improves PSNR, SSIM, and LPIPS metrics by 4% to 11% compared to existing methods, while achieving an effective balance between map memory management, rendering quality, and runtime efficiency.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128763"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144510839","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":"Nighttime airport runway FOD intrusive detection through frequency-domain interference of spatially aggregated dynamic feature","authors":"Guangchen Chen,&nbsp;Yinhui Zhang,&nbsp;Zifen He,&nbsp;Ying Huang","doi":"10.1016/j.eswa.2025.128719","DOIUrl":"10.1016/j.eswa.2025.128719","url":null,"abstract":"<div><div>Accidental intrusion of foreign object debris (FOD) on the airport runway often causes fatal safety hazards in aviation transportation during take-off and landing especially at night as the degraded imaging quality. To address the false and missed detections in low-light images by current advanced methods, the Frequency-Domain Interference Network of spatially aggregated dynamic feature (FDI-Net) is proposed to improve the recognition accuracy of threatening FOD at nighttime. Firstly, to deal with the challenges posed by degraded low-quality imaging at night, we propose the Frequency-Domain Adaptive Tuning (FDAT) spatial pooling module, which utilizes fast Fourier transformation to construct frequency-domain features from the row and column pixels of FOD images. Subsequently, generating the wave function signal through the superposition of row and column components, and adaptively tuning the frequency and phase spectra using dynamically learnable weights within the network structure. This process effectively suppresses redundant information while enhancing the grayscale and texture feature space. Secondly, the Dynamic Granular Aggregated Interference (DGAI) module is developed to transform the FOD spatial features into amplitude and phase representations, enabling the extraction of fine-grained feature information through dynamic depth fusion. This module then aggregates the fine-grained features using the interference effects of sine and cosine waves to enhance positive FOD target information and suppress negative interference. Finally, the detection model is deployed on an embedded edge computing platform to develop a mobile nighttime airport runway foreign object debris detection system. Experimental results demonstrate that the proposed model effectively detects ten categories of small and medium-scale FOD targets, achieving optimal accuracy results of 97.9 %, 89.8 %, and 77.6 % on the mAP50, mAP75, and mAP50-95 metrics, respectively. In addition, our method achieves the accuracy of 94.5 %, 89.9 %, 85.2 %, 76.2 %, 92.4 %, 92.2 %, 95.5 %, 74.4 %, 97.5 %, and 99.5 % on ten categories, respectively. Consequently, the intelligent detection system holds significant potential for preventing accidents caused by FOD in the aviation transportation safety field.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"294 ","pages":"Article 128719"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518227","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":"EfficientPEAL: Efficient prior-embedded attention learning for partially overlapping point cloud registration","authors":"Junle Yu ,&nbsp;Wenhui Zhou ,&nbsp;Zhehao Shen ,&nbsp;Yongwei Miao","doi":"10.1016/j.eswa.2025.128591","DOIUrl":"10.1016/j.eswa.2025.128591","url":null,"abstract":"<div><div>Learning discriminative point-wise features is critical for partially overlapping point cloud registration. In recent years, the integration of a Transformer into point cloud feature representation has demonstrated remarkable success, which typically involves a self-attention module to learn intra-point-cloud features, followed by a cross-attention module for feature exchange between input point clouds. Transformer models mainly benefit from the use of self-attention to capture the global correlations in feature space. However, the global correlations involved in self-attention may not only result in a significant amount of redundant computational overhead but also introduce feature ambiguities, especially in low-overlap scenarios. This is because overlapping regions of point clouds typically do not span a wide range but are rather concentrated around a localized area. Therefore, the correlations with an extensive range of non-overlapping points are ineffective and may degrade the discriminability of features. To address this issue, we present a <strong>E</strong>fficient <strong>P</strong>rior-<strong>E</strong>mbedded <strong>A</strong>ttention <strong>L</strong>earning model (<strong>E</strong>fficientPEAL). By incorporating overlap prior to the learning process, the point clouds are divided into two parts. One part includes points lying in the putative overlapping region and the other includes points located in the putative non-overlapping region. Then, EfficientPEAL performs localized attention with the putative overlapping points. The proposed attention module significantly reduces the computational complexity of the model while achieving competitive performance. Extensive experiments on 3DMatch/3DLoMatch, ScanNet, and KITTI datasets demonstrate its effectiveness.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"293 ","pages":"Article 128591"},"PeriodicalIF":7.5,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144481021","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}