计算机科学最新文献_第7页

ImagTIDS: an internet of things intrusion detection framework utilizing GADF imaging encoding and improved Transformer

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2024-12-24 DOI: 10.1007/s40747-024-01712-9

Peng Wang, Yafei Song, Xiaodan Wang, Xiangke Guo, Qian Xiang

{"title":"ImagTIDS: an internet of things intrusion detection framework utilizing GADF imaging encoding and improved Transformer","authors":"Peng Wang, Yafei Song, Xiaodan Wang, Xiangke Guo, Qian Xiang","doi":"10.1007/s40747-024-01712-9","DOIUrl":"https://doi.org/10.1007/s40747-024-01712-9","url":null,"abstract":"<p>As the Internet of Things (IoT) technology becomes extensively deployed, IoT security issues are increasingly prominent. The traffic patterns of IoT are complex and high-dimensional, which makes it difficult to distinguish the tiny differences between normal and malicious samples. To tackle the above problems, we propose an IoT intrusion detection architecture based on Gramian angular difference fields (GADF) imaging technology and improved Transformer, named ImagTIDS. Firstly, we encode the network traffic data of IoT into images using GADF to preserve more robust temporal and global features, and then we propose a model named ImagTrans for extracting local and global features from network traffic images. ImagTIDS utilizes the self-attention mechanism to dynamically adjust the attention weights and adaptively focus on the important features, effectively suppressing the adverse effects of redundant features. Furthermore, due to the serious class imbalance problem in IoT intrusion detection, we utilize Focal Loss to dynamically scale the model gradient and adaptively reduce the weights of simple samples to focus on hard-to-classify classes. Finally, we validate the effectiveness of the proposed method on the publicly available IoT intrusion detection datasets ToN_IoT and DS2OS, and the experimental results show that the proposed method achieves superior detection performance and higher robustness on class imbalance datasets compared to other remarkable methods.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"130 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884290","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 Uncertainty-Aware Continual Learning Framework for Fault Diagnosis of Rotating Machinery With Homogeneous-Heterogeneous Faults

IF 5.6 2区计算机科学

IEEE Transactions on Automation Science and Engineering Pub Date : 2024-12-24 DOI: 10.1109/tase.2024.3519608

Jipu Li, Ke Yue, Zhuyun Chen, Jingyan Xia, Weihua Li, Xiaoge Zhang

引用次数: 0

Efficient knowledge distillation using a shift window target-aware transformer

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2024-12-24 DOI: 10.1007/s10489-024-06207-1

Jing Feng, Wen Eng Ong

引用次数: 0

Cooperation with Humans of Unknown Intentions in Confined Spaces Using the Stackelberg Friend-or-Foe Game

IF 4.4 2区计算机科学

IEEE Transactions on Aerospace and Electronic Systems Pub Date : 2024-12-24 DOI: 10.1109/taes.2024.3521935

Xiaofeng Zhao, Hanyao Hu, Dengfeng Sun

引用次数: 0

Serv-HU: Service Hand-off for UAV-as-a-Service

IF 8.1 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2024-12-24 DOI: 10.1109/tsc.2024.3521684

Arijit Roy, Veera Manikantha Rayudu Tummala, Vinay Yadam

引用次数: 0

Streamlining Assembly Instruction Design (S-AID): A comprehensive systematic framework

IF 1 1区计算机科学

Computers in Industry Pub Date : 2024-12-24 DOI: 10.1016/j.compind.2024.104232

Mirco Bartolomei, Federico Barravecchia, Luca Mastrogiacomo, Davide Maria Gatta, Fiorenzo Franceschini

{"title":"Streamlining Assembly Instruction Design (S-AID): A comprehensive systematic framework","authors":"Mirco Bartolomei, Federico Barravecchia, Luca Mastrogiacomo, Davide Maria Gatta, Fiorenzo Franceschini","doi":"10.1016/j.compind.2024.104232","DOIUrl":"https://doi.org/10.1016/j.compind.2024.104232","url":null,"abstract":"Assembly instructions are detailed directives used to guide the assembly of products across various manufacturing sectors. As production processes evolve to become more flexible, the significance of assembly instructions in meeting rigorous efficiency and quality standards becomes increasingly pronounced. Nevertheless, the development of assembly instructions often remains unstructured and predominantly dependent on the experience or personal skills of the designer. This paper aims to address these issues by pursuing three main goals: (i) deciphering the assembly process and the information that characterizes it, thereby providing a taxonomy of instruction constituents; (ii) presenting a framework to assess the various formats in which such information can be communicated; and (iii) introducing a step-by-step method, named <ce:italic>S-AID</ce:italic>, which offers a consistent methodology for designers during the instruction design phase. Overall, this research provides a rigorous taxonomy of the building blocks of assembly instructions and defines their relationships with various instruction formats. Furthermore, by proposing a systematic design method, this works aims to address the redundancy and inconsistency commonly encountered in traditional instruction design processes. The proposed methodology is illustrated using a real-world case study involving the assembly of a mechanical equipment. Finally, the effectiveness of the <ce:italic>S-AID</ce:italic> method was evaluated quantitatively through comparative analysis with other instruction sets, focusing on metrics such as process failures, assembly completion time, and perceived cognitive load.","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"53 1","pages":""},"PeriodicalIF":10.0,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884277","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

KGPT: Wireless Key Generation Based on Power Tuning for Static Internet-of-Things

IF 12.3 1区计算机科学

IEEE Transactions on Industrial Informatics Pub Date : 2024-12-24 DOI: 10.1109/tii.2024.3514119

Xintao Huan, Kaitao Miao, Jiamin Liu, Changfan Wu, Wen Chen, Rui Pei, Han Hu

引用次数: 0

Invisible DNN Watermarking Against Model Extraction Attack

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2024-12-24 DOI: 10.1109/tcyb.2024.3514838

Zuping Xi, Zuomin Qu, Wei Lu, Xiangyang Luo, Xiaochun Cao

引用次数: 0

Temporal Logic Disturbance Rejection Control of Nonlinear Systems Using Control Barrier Functions

IF 11.8 1区计算机科学

IEEE Transactions on Cybernetics Pub Date : 2024-12-24 DOI: 10.1109/tcyb.2024.3515456

Chengqian Zhou, Jun Yang, Shihua Li, Wen-Hua Chen

引用次数: 0

IEEE Robotics and Automation Society Information

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-12-24 DOI: 10.1109/LRA.2024.3519235

引用次数: 0