Expert Systems with Applications最新文献_第10页

Protecting the interests of owners of intelligent fault diagnosis models: A style relationship-preserving privacy protection method

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126730

Xilin Yang , Xianfeng Yuan , Xinxin Yao , Yansong Zhang , Jianjie Liu , Fengyu Zhou

{"title":"Protecting the interests of owners of intelligent fault diagnosis models: A style relationship-preserving privacy protection method","authors":"Xilin Yang , Xianfeng Yuan , Xinxin Yao , Yansong Zhang , Jianjie Liu , Fengyu Zhou","doi":"10.1016/j.eswa.2025.126730","DOIUrl":"10.1016/j.eswa.2025.126730","url":null,"abstract":"<div><div>The training process of intelligent fault diagnosis models requires data collection and computational cost, which is laborious and time-consuming. Due to the similarity of the fault categories to be classified between different models, an unauthorized user may easily transfer a diagnosis model to his own domain, infringing the interests of the model owner. Therefore, it is important to protect the intellectual property of fault diagnosis models. The existing privacy protection methods use a metric to increase the feature divergence or construct un-transferable isolation domains, but the generalization boundaries of the deep learning models cannot be minimized enough, leading to certain availability in unauthorized domains. To tackle this issue, a style relationship preserving based model property protection method is proposed for fault diagnosis in this paper. The proposed method utilizes style transfer technique to simulate the extreme situation, which further compacts the generalization areas and limits the application of the model to unauthorized domains. Comprehensive experiments are established on a public fault diagnosis dataset and a practical rolling bearing fault diagnosis test platform, demonstrating the effectiveness and superiority of the proposed method in model privacy protection.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126730"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143360217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid image splicing detection: Integrating CLAHE, improved CNN, and SVM for digital image forensics

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126756

Navneet Kaur

{"title":"Hybrid image splicing detection: Integrating CLAHE, improved CNN, and SVM for digital image forensics","authors":"Navneet Kaur","doi":"10.1016/j.eswa.2025.126756","DOIUrl":"10.1016/j.eswa.2025.126756","url":null,"abstract":"<div><div>This article introduces a novel hybrid method for the detection of image splicing forgery (ISF) that integrates an improved convolutional neural network (CNN), support vector machine (SVM) classifier, and contrast-limited adaptive histogram equalization (CLAHE). The imperceptibility of counterfeit images has made detection a challenge, as the increasing accessibility of image editing applications has resulted in a surge in amateur image manipulation. The proposed methodology employs CLAHE to enhance the extraction of hidden features that forgery has obscured. The improved CNN employs sophisticated feature extraction techniques to achieve superior classification accuracy without the necessity of custom algorithms. Furthermore, SVM is incorporated due to its exceptional processing speed and efficiency. The objective of this hybrid framework is to address the constraints of current deep learning models in terms of computational efficiency and accuracy, thereby demonstrating substantial enhancements in performance metrics for image splicing forgery detection (ISFD). The findings suggest that the proposed system effectively differentiates between authentic and manipulated images, offering an effective solution to the challenges of image splicing forgery.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"273 ","pages":"Article 126756"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420465","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

DPFSI: A legal judgment prediction method based on deontic logic prompt and fusion of law article statistical information

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126722

Chunyun Meng , Yuki Todo , Cheng Tang , Li Luan , Zheng Tang

{"title":"DPFSI: A legal judgment prediction method based on deontic logic prompt and fusion of law article statistical information","authors":"Chunyun Meng , Yuki Todo , Cheng Tang , Li Luan , Zheng Tang","doi":"10.1016/j.eswa.2025.126722","DOIUrl":"10.1016/j.eswa.2025.126722","url":null,"abstract":"<div><div>The application of large language models in legal text processing faces challenges due to a lack of specialized legal knowledge and difficulty in handling complex legal logic and long texts. To address these issues, this paper introduces a legal judgment prediction method that combines deontic prompt learning, multi-granularity graph representation fusion, and law article statistical information integration. The model first modifies a pre-trained language model through deontic prompt learning, enhancing the semantic richness and interpretability of word vectors in structured texts. Additionally, it constructs multiple heterogeneous graphs to capture semantic and syntactic relationships, and applies a Gated Graph Neural Network for multi-granularity graph representation fusion. This fusion provides a comprehensive understanding of legal texts by effectively integrating semantic and structural information. Furthermore, the model calculates word frequency statistics between law articles and text sequences, using a <span><math><mi>β</mi></math></span>-variational autoencoder to align and integrate statistical information into text sequence features. This adaptive fusion reduces overfitting by replacing low-confidence neurons with global statistical information. Experimental results on the CAIL2018 dataset show that our approach achieves a significant improvement over existing methods, particularly in law article prediction, demonstrating its effectiveness and potential for enhancing legal AI applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126722"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143348538","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

Truck-multidrone same-day delivery strategies: On-road resupply vs depot return

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126757

David Sanchez-Wells , José L. Andrade-Pineda , Pedro L. Gonzalez-R

{"title":"Truck-multidrone same-day delivery strategies: On-road resupply vs depot return","authors":"David Sanchez-Wells , José L. Andrade-Pineda , Pedro L. Gonzalez-R","doi":"10.1016/j.eswa.2025.126757","DOIUrl":"10.1016/j.eswa.2025.126757","url":null,"abstract":"<div><div>This paper explores an enhanced two-waved same-day delivery (SDD) system that leverages a mothership truck equipped with multiple drones supported by an auxiliary “resupply” truck. Under standard SDD operations, this mothership truck, also capable of performing deliveries, must return to the depot to reload, incurring extra travel time and mileage. In contrast, the proposed resupply strategy enables the second delivery wave by dispatching a secondary vehicle to meet the mothership truck on-road, reloading parcels without interrupting ongoing deliveries by the drones. A single unified routing framework, the Genetic Algorithm with Iterated Estimations for Resupply (GAIER), is presented to optimise both strategies under two selectable criteria: minimising total service time or total truck mileage.</div><div>In tests with benchmark networks of different sizes (20, 50, and 75 nodes), incorporating a resupply truck reduced every selected criterion when compared to the strategy where the mothership vehicle returns to the depot. Subsequent comparative analysis points an average reduction of 17 % in service time and 21 % in truck mileage while statistical analyses support the strategy choice significancy, confirming resupply strategy’s potential for cost savings and reduced environmental impact. These findings bolster our proposition that incorporating a resupply truck into hybrid truck-multidrone systems enhances flexibility in drone delivery scheduling and improves the system’s ability to meet urban demand.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126757"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403697","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

Boundary semantic interactive aggregation network for scene segmentation

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126754

Fan Zhang, Qijun Lv, Binrong Pan, Yun Wang

{"title":"Boundary semantic interactive aggregation network for scene segmentation","authors":"Fan Zhang, Qijun Lv, Binrong Pan, Yun Wang","doi":"10.1016/j.eswa.2025.126754","DOIUrl":"10.1016/j.eswa.2025.126754","url":null,"abstract":"<div><div>Deep learning-based road scene segmentation has been paid significantly attention for autonomous driving. Most approaches focus on extracting semantic information of target and neglect boundary feature, resulting in difficultly improving holistically semantics modeling. To handle this challenge, we propose boundary semantic interactive aggregation network (BSIA-Net) to segment road scene, which embeds boundary feature into multi-scale semantic features and aggregates interactive information for promoting semantic understanding. The designed BSIA-Net consists of three parts including semantic flow, boundary flow, and aggregation flow. The semantic flow is used to extract multi-scale semantic information and constructs astrous stack pooling (ASP) module to capture rich context information by expanding the receptive field. The boundary flow is specifically designed to refine low-level boundary feature from edge extracting operator (EEO) by multi-scale semantic features. The aggregation flow constructs interactive aggregation module (IAM) to capture long-range dependencies between the inner objects and boundaries by interactively enhancing intra-class consistency. The BSIA-Net successively achieves 81.1 % and 45.41 % in mean intersection over union on Cityscapes and ADE20K datasets. Extensive experiments compared to some other methods demonstrates the effectiveness and advancement of our method.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126754"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143372142","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

Illuminating the black box: An interpretable machine learning based on ensemble trees

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126720

Yue-Shi Lee , Show-Jane Yen , Wendong Jiang , Jiyuan Chen , Chih-Yung Chang

{"title":"Illuminating the black box: An interpretable machine learning based on ensemble trees","authors":"Yue-Shi Lee , Show-Jane Yen , Wendong Jiang , Jiyuan Chen , Chih-Yung Chang","doi":"10.1016/j.eswa.2025.126720","DOIUrl":"10.1016/j.eswa.2025.126720","url":null,"abstract":"<div><div>Deep learning has achieved significant success in the analysis of unstructured data, but its inherent black-box nature has led to numerous limitations in security-sensitive domains. Although many existing interpretable machine learning methods can partially address this issue, they often face challenges such as model limitations, interpretability randomness, and a lack of global interpretability. To address these challenges, this paper introduces an innovative interpretable ensemble tree method, EnEXP. This method generates a sample set by applying fixed masking perturbation to individual samples, then constructs multiple decision trees using bagging and boosting techniques and interprets them based on the importance outputs of these trees, thereby achieving a global interpretation of the entire dataset through the aggregation of all sample insights. Experimental results demonstrate that EnEXP possesses superior explanatory power compared to other interpretable methods. In text processing experiments, the bag-of-words model optimized by EnEXP outperformed the GPT-3 Ada fine-tuned model.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126720"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379256","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

Dynamic link prediction: Using language models and graph structures for temporal knowledge graph completion with emerging entities and relations

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126648

Ryan Ong , Jiahao Sun , Yi-Ke Guo , Ovidiu Serban

{"title":"Dynamic link prediction: Using language models and graph structures for temporal knowledge graph completion with emerging entities and relations","authors":"Ryan Ong , Jiahao Sun , Yi-Ke Guo , Ovidiu Serban","doi":"10.1016/j.eswa.2025.126648","DOIUrl":"10.1016/j.eswa.2025.126648","url":null,"abstract":"<div><div>Knowledge graphs (KGs) represent real-world facts through entities and relations. However, static KGs fail to capture continuously emerging entities and relations over time. Temporal knowledge graphs address this by incorporating time information or providing multiple sequential snapshots of a static knowledge graph. Most existing work focuses on static KGs with fixed sets of entities and relations, meaning existing methods still struggle to encode emerging entities and relations. Therefore, we propose a novel methodology of combining language models and graph structure to enable the encoding of unseen entities and relations for temporal KG completion. Specifically, we encode relations with RoBERTa and entities using neighbouring relations alongside the entity’s relation type to provide contextual information. We evaluate our methodology on three datasets with emerging entities and relations over temporal snapshots: LKGE-Hybrid, FB-MBE, and the mergers and acquisitions domain TKGQA dataset. Our experiments show that our model achieves new state-of-the-art results on FB-MBE and LKGE-Hybrid while providing strong benchmark results for the TKGQA dataset. Our ablation studies show us that graph structure information is only beneficial if there is sufficient connectivity with the knowledge graph since sparser knowledge graphs can lead to noisy signals. We also explore the performance of Llama v2 on temporal link prediction, and the results show that current LLMs struggle with domain-specific temporal link prediction. Overall, our work provides an essential advance around effectively encoding continuously emerging entities and relations for temporal link prediction across evolving knowledge graphs over time.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126648"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377203","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

TAMS: A CNN-based time attention network for time series sensor data with feature points of bicycle accident

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126739

So-Hyeon Jo , Joo Woo , Jae-Hoon Jeong

引用次数: 0

Prescribed-time formation tracking in multi-agent systems via reinforcement learning-based hybrid impulsive control with time delays

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126723

Zhanlue Liang , Yanlin Gu , Ping Li , Yiwen Tao

{"title":"Prescribed-time formation tracking in multi-agent systems via reinforcement learning-based hybrid impulsive control with time delays","authors":"Zhanlue Liang , Yanlin Gu , Ping Li , Yiwen Tao","doi":"10.1016/j.eswa.2025.126723","DOIUrl":"10.1016/j.eswa.2025.126723","url":null,"abstract":"<div><div>This paper addresses the prescribed-time formation stabilization in nonlinear multi-agent systems using a novel reinforcement learning-based hybrid impulsive control framework that incorporates delayed control impulses. The approach leverages Lyapunov functionals, impulsive comparison theory, average impulsive interval methods, and graph theory to derive sufficient conditions for achieving prescribed-time formation stabilization. These conditions are formulated in terms of continuous and impulsive feedback gains, time delay durations, and average impulsive interval lengths. Importantly, the inclusion of stabilizing control impulses counteracts the destabilizing effects of continuous dynamics. Additionally, deep reinforcement learning techniques are employed to optimize the impulsive control sequence, aiming to maximize rewards derived from the control objectives and system states. Numerical simulation examples are presented to demonstrate the effectiveness and validity of the proposed analytical results, providing comparative assessments of overall control performance.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126723"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379260","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

MFAR-Net: Multi-level feature interaction and Dual-Dimension adaptive reinforcement network for breast lesion segmentation in ultrasound images

IF 7.5 1区计算机科学

Expert Systems with Applications Pub Date : 2025-02-06 DOI: 10.1016/j.eswa.2025.126727

Guoqi Liu , Shaocong Dong , Yanan Zhou , Sheng Yao , Dong Liu

{"title":"MFAR-Net: Multi-level feature interaction and Dual-Dimension adaptive reinforcement network for breast lesion segmentation in ultrasound images","authors":"Guoqi Liu , Shaocong Dong , Yanan Zhou , Sheng Yao , Dong Liu","doi":"10.1016/j.eswa.2025.126727","DOIUrl":"10.1016/j.eswa.2025.126727","url":null,"abstract":"<div><h3>Objective:</h3><div>Precise segmentation of breast ultrasound images is essential for early breast cancer screening. Convolutional neural networks (CNNs) have made great progress in lesion segmentation in breast ultrasound images. These methods still have three limitations: (1) They lack the ability to model global information; (2) The importance of interaction between different scale features is not sufficiently emphasized; (3) The abilities of feature fusion and lesion region correction in the decoding process are ignored.</div></div><div><h3>Methods:</h3><div>Considering the above problems, we propose a Multi-level feature interaction and Dual-Dimension adaptive reinforcement network (MFAR-Net). Our design is as follows: (1) Introduce transformer as a global context-aided encoding branch (GCA) to establish long-term dependencies; (2) The multi-level feature interaction (MFI) module uses the feature interaction of different receptive fields to capture detailed information and alleviate the influence of grid; (3) Dual-dimension adaptive reinforcement (DAR) enhances and corrects the original features in both spatial and channel dimension, providing a reliable premise for subsequent supplementary detailed information. <strong>Main results:</strong> Extensive experiments results on four public ultrasound datasets show that the proposed MFAR-Net outperforms other state-of-the-art (SOTA) methods. Furthermore, compared with the suboptimal method, we significantly improve the Dice metrics by 2.68% on the BUSI-malignant datasets, showing strong competitiveness. <strong>Significance:</strong> (1) The segmentation accuracy of breast lesions is further improved under the premise of a small number of parameters; (2) The ability to adapt to other ultrasonic images is maintained, and our network has strong robustness and good generalization performance.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"272 ","pages":"Article 126727"},"PeriodicalIF":7.5,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349055","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