计算机科学最新文献_第7页

Rail-PatchCore: unsupervised learning-based detection of visual anomalies in the railway-turnout environment

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-02-05 DOI: 10.1007/s10489-025-06294-8

YuanHao Zhang, Zujun Yu, Liqiang Zhu, Baoqing Guo, Yao Wang

{"title":"Rail-PatchCore: unsupervised learning-based detection of visual anomalies in the railway-turnout environment","authors":"YuanHao Zhang, Zujun Yu, Liqiang Zhu, Baoqing Guo, Yao Wang","doi":"10.1007/s10489-025-06294-8","DOIUrl":"10.1007/s10489-025-06294-8","url":null,"abstract":"<div><p>The complexity and openness of railway turnout environments pose great challenges to anomaly detection, and supervised methods are highly dependent on labels, making it difficult to address the diverse types of anomalies and the scarcity of samples in turnout environments. To solve these problems, this paper proposes a new method, Rail-PatchCore, which is based on unsupervised learning and effectively reduces the interference of background noise and enhances the ability to capture anomalous features by adding a Dual-Dimensional Channel Attention (DDCA) module and a projection anomaly scoring module to the PatchCore model. The experiments on our railway-turnout anomaly detection dataset(RTAD) and other datasets (RSDDs, MVTec-AD, BTAD, AEBAD-S) show that the detection performance of Rail-PatchCore is better than that of the existing methods, and the image-level and pixel-level AUCROC indices of Rail-PatchCore on the railway turnout anomaly detection dataset reach 72.2% and 95.3%, respectively. This approach provides an efficient and reliable solution for anomaly detection in railway turnout environments.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 automated incremental density-based clustering approach using unsupervised deep learning and multi-objective optimization

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-02-05 DOI: 10.1016/j.compeleceng.2025.110109

Binu Jose A. , Pranesh Das

{"title":"An automated incremental density-based clustering approach using unsupervised deep learning and multi-objective optimization","authors":"Binu Jose A. , Pranesh Das","doi":"10.1016/j.compeleceng.2025.110109","DOIUrl":"10.1016/j.compeleceng.2025.110109","url":null,"abstract":"<div><div>Incremental density-based clustering algorithms are designed to handle large datasets and streaming data. However, the automatic identification of critical input parameters and the merging threshold for dynamically merging clusters in incremental density-based algorithms presents a significant challenge. This paper addresses the above challenge by introducing a novel framework, termed Multi-Objective Incremental Density-Based Clustering using deep learning (MIDBC-DL). It leverages Pareto front generation by utilizing pseudo labels that captures non-linear relationships between objective functions. Furthermore, a novel evaluation metric, the Score Index (SI), is introduced to achieve a robust and balanced consideration of both compactness and separation between clusters. To validate the effectiveness of the proposed approach, experiments are conducted using five bench mark datasets — Iris, Glass, Wine, Pendigits and Shuttle. Experimental results demonstrate that MIDBC-DL achieves superior performance compared to the state-of-the-art methods. The source code is available at <span><span>https://github.com/BinuJoseA/MIDBC-DL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110109"},"PeriodicalIF":4.0,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143149963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models

IF 7.8 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-05 DOI: 10.1109/tro.2025.3539198

Ying Zhang, Maoliang Yin, Wenfu Bi, Haibao Yan, Shaohan Bian, Cui-Hua Zhang, Changchun Hua

引用次数: 0

Revisiting Flatness-aware Optimization in Continual Learning with Orthogonal Gradient Projection

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-02-05 DOI: 10.1109/tpami.2025.3539019

Enneng Yang, Li Shen, Zhenyi Wang, Shiwei Liu, Guibing Guo, Xingwei Wang, Dacheng Tao

引用次数: 0

Chattering Phenomena in Time-Optimal Control for High-Order Chain-of-Integrator Systems With Full State Constraints

IF 6.8 1区计算机科学

IEEE Transactions on Automatic Control Pub Date : 2025-02-05 DOI: 10.1109/tac.2025.3538775

Yunan Wang, Chuxiong Hu, Zeyang Li, Yujie Lin, Shize Lin, Suqin He

引用次数: 0

Digital Twin Online Channel Modeling: Challenges, Principles, and Applications

IF 8.1 2区计算机科学

IEEE Vehicular Technology Magazine Pub Date : 2025-02-05 DOI: 10.1109/mvt.2025.3527729

Junling Li, Cheng-Xiang Wang, Chen Huang, Tianrun Qi, Tong Wu

引用次数: 0

Generative AI for Semantic Communication: Architecture, Challenges, and Outlook

IF 12.9 1区计算机科学

IEEE Wireless Communications Pub Date : 2025-02-05 DOI: 10.1109/mwc.003.2300351

Le Xia, Yao Sun, Chengsi Liang, Lei Zhang, Muhammad Ali Imran, Dusit Niyato

引用次数: 0

Neural Codebook Design for MIMO Network Beam Management

IF 10.4 1区计算机科学

IEEE Transactions on Wireless Communications Pub Date : 2025-02-05 DOI: 10.1109/twc.2025.3536290

Ryan M. Dreifuerst, Robert W. Heath

引用次数: 0

Resilient Distributed Kalman Filtering Against Malicious Cyber Attacks

IF 4.4 2区计算机科学

IEEE Transactions on Aerospace and Electronic Systems Pub Date : 2025-02-05 DOI: 10.1109/taes.2025.3538521

Wei Xia, Mengqing Zhou

引用次数: 0

Numerical and Analytical Methods for Complex Electromagnetic Media 复杂电磁介质的数值和分析方法

IF 4.6 1区计算机科学

IEEE Transactions on Antennas and Propagation Pub Date : 2025-02-05 DOI: 10.1109/TAP.2025.3534960

引用次数: 0