International Journal of Intelligent Networks最新文献

CA-DA: Class-adaptive deformable attention for semantic segmentation in internet-enabled visual sensing networks CA-DA：基于类自适应的视觉感知网络语义分割的可变形注意

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-07-10 DOI: 10.1016/j.ijin.2026.07.002

Chenhao Ye, Cunkang Wu, Duanpo Wu, Liwei Che, Meng Han, Xuyang Teng

{"title":"CA-DA: Class-adaptive deformable attention for semantic segmentation in internet-enabled visual sensing networks","authors":"Chenhao Ye, Cunkang Wu, Duanpo Wu, Liwei Che, Meng Han, Xuyang Teng","doi":"10.1016/j.ijin.2026.07.002","DOIUrl":"10.1016/j.ijin.2026.07.002","url":null,"abstract":"<div><div>Semantic segmentation is a fundamental component of Internet-enabled visual sensing networks, where distributed cameras, edge devices, and networked sensors collect large-scale visual data from complex environments. However, such data often exhibit severe pixel-level imbalance and category heterogeneity, with semantic classes differing in frequency, spatial extent, boundary complexity, and structural patterns. These characteristics make standard pixel-wise training prone to biased decision boundaries and insufficient representations for underrepresented categories. In this paper, we identify two key limitations in this setting: the misalignment between standard optimization objectives and class-balanced evaluation criteria, and the lack of class-adaptive feature aggregation under heterogeneous category statistics. To address them, we propose a unified category-aware prior-compensation framework that combines output-level calibration with sampling-level adaptive feature learning. Specifically, we adopt relative-prior logit adjustment to alleviate pixel-wise decision bias toward dominant classes. Meanwhile, we introduce a spatial-demand-aware class-adaptive deformable attention mechanism that modulates deformable offsets during training according to class frequency and class-wise spatial demand. This design encourages flexible contextual aggregation for underrepresented and spatially complex categories while maintaining stable aggregation for dominant ones. During inference, the offset predictor remains fully feature-driven and requires no ground-truth labels, pseudo-labels, or external class annotations. Experiments on Cityscapes and ADE20K show that the proposed method improves segmentation performance for underrepresented classes while maintaining competitive overall accuracy, achieving superior class-balanced performance over representative baselines.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 77-87"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148565619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A collaborative framework for rapid fault repair and service restoration in distribution networks 配电网快速故障修复与服务恢复的协同框架

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2025-11-29 DOI: 10.1016/j.ijin.2025.11.006

Hanwen Wang , Sheng Lu , Yanxin Jiang , Ying Shi , Chaoran Song , Guoqiang Liu

{"title":"A collaborative framework for rapid fault repair and service restoration in distribution networks","authors":"Hanwen Wang , Sheng Lu , Yanxin Jiang , Ying Shi , Chaoran Song , Guoqiang Liu","doi":"10.1016/j.ijin.2025.11.006","DOIUrl":"10.1016/j.ijin.2025.11.006","url":null,"abstract":"<div><div>Distribution networks constitute the terminal stage of the electric power system, delivering electricity from transmission grids to end users. Owing to their wide geographic dispersion and the outdoor installation of most equipment, these networks are highly exposed to extreme weather events that may damage facilities and interrupt power supply services. Ensuring timely fault repair and service restoration is therefore essential for maintaining system reliability. However, large numbers of faults often occur simultaneously and may further deteriorate if not repaired promptly, reducing the overall efficiency of restoration activities. Moreover, effective recovery requires the coordinated use of multiple resources, such as repair crews, vehicles, and spare parts, whose limited availability, time constraints, and operational dependencies create additional challenges. To overcome these issues, a <u>co</u>llaborative framework for <u>ra</u>pid fault repair and service restoration in <u>di</u>stribution <u>n</u>etworks, called Coradin, is proposed. It is composed of three layers, including the data integration layer responsible for data collection, the scheduling optimization layer responsible for strategy formulation and optimization, and the repair execution layer responsible for repair and restoration. Extensive experiments on the IEEE 33-bus and 123-bus systems verify the framework’s effectiveness in improving restoration efficiency and service reliability.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 1-9"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145993612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computation offloading optimization for UAV-assisted power industrial internet of things mobile edge computing system 无人机辅助电力工业物联网移动边缘计算系统的计算卸载优化

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2025-11-18 DOI: 10.1016/j.ijin.2025.11.009

Zhenkun Wang, Jingyu Fan, Congcong Mu, Ruimin Wang, Hu Tan, Junxing Rong

{"title":"Computation offloading optimization for UAV-assisted power industrial internet of things mobile edge computing system","authors":"Zhenkun Wang, Jingyu Fan, Congcong Mu, Ruimin Wang, Hu Tan, Junxing Rong","doi":"10.1016/j.ijin.2025.11.009","DOIUrl":"10.1016/j.ijin.2025.11.009","url":null,"abstract":"<div><div>With the advancement of the power industrial internet of things (PIIoT), the volume of data generated by intelligent power devices in smart power plants is rapidly increasing. Large-scale real-time data processing necessitates the utilization of edge servers’ computational capabilities to reduce delay and energy consumption. Meanwhile, unmanned aerial vehicles (UAVs), with their flexible deployment and wide coverage, play a significant role in enhancing communication quality within mobile edge computing (MEC) systems. To address the computational demands in PIIoT scenarios, this paper introduces a UAV-assisted PIIoT MEC system, where UAVs provide processing support to nearby PDGs by accepting offloaded tasks. The remaining workloads are computed locally by the PDGs. Facing the challenges posed by discrete control variables and energy constraints, we perform joint optimization of scheduling, offloading decisions, and UAV mobility parameters to reduce the overall delay-energy trade-off. To effectively solve this complex, non-convex problem characterized by a large state–action space, this paper propose a deep deterministic policy gradient-based computation offloading optimization (DDPG-COO) algorithm. Simulation results confirm the fast convergence behavior of the proposed DDPG-COO scheme. Compared to existing baselines, notable enhancements are observed in delay reduction and energy saving performance.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 69-76"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148565621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum regarding previously published article 关于先前发表的文章的更正

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-08-17 DOI: 10.1016/j.ijin.2026.08.001

引用次数: 0

MAGNET-Bot: A machine learning framework employing multilevel ensemble feature selection for botnet group activity detection MAGNET-Bot：一种采用多级集成特征选择的机器学习框架，用于僵尸网络组活动检测

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-06-30 DOI: 10.1016/j.ijin.2026.06.002

Muhammad Aidiel Rachman Putra, Tohari Ahmad, Dandy Pramana Hostiadi

{"title":"MAGNET-Bot: A machine learning framework employing multilevel ensemble feature selection for botnet group activity detection","authors":"Muhammad Aidiel Rachman Putra, Tohari Ahmad, Dandy Pramana Hostiadi","doi":"10.1016/j.ijin.2026.06.002","DOIUrl":"10.1016/j.ijin.2026.06.002","url":null,"abstract":"<div><div>Botnets represent a considerable threat to network security due to their ability to exploit compromised systems for coordinated malicious activities. While many existing botnet detection models achieve high detection performance, they often fail to address the vital aspect of computational efficiency. This research presents a new machine learning framework called MAGNET-Bot that employs a multilevel ensemble feature selection approach designed to improve detection performance while reducing the execution time. Unlike previous studies that typically rely on straightforward selection methods, the proposed approach incorporates multiple ensemble feature selection techniques integrated with machine learning classification models. To evaluate the effectiveness of this method, graph metadata extraction results from network traffic were analyzed using three recognized datasets: CTU-13 (characterizing sporadic behavior), NCC (representing periodic behavior), and NCC-2 (exhibiting simultaneous behavior). Experimental results indicate significant improvements in detection performance compared to traditional methods. Notably, the combination of the proposed feature selection method with the XGBoost algorithm achieved an average accuracy of 97.52%, a precision of 43.31%, a recall of 47.80%, while ensuring computational efficiency with a processing time of merely 0.12 s. Given its efficiency, performance, and thorough analytical approach, this proposed method is deemed suitable to assist network administrators in conducting forensic investigations of botnet attacks.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 50-68"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148565481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing blockchain network security: A targetable machine learning model for effective vulnerability repair 增强区块链网络安全：有效修复漏洞的目标机器学习模型

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2025-12-01 DOI: 10.1016/j.ijin.2025.11.005

Li Yu , Jiao Jian , Jin-Ping Shi , Hong-Sheng Cao

{"title":"Enhancing blockchain network security: A targetable machine learning model for effective vulnerability repair","authors":"Li Yu , Jiao Jian , Jin-Ping Shi , Hong-Sheng Cao","doi":"10.1016/j.ijin.2025.11.005","DOIUrl":"10.1016/j.ijin.2025.11.005","url":null,"abstract":"<div><div>Smart contracts have been widely used on blockchain to automate financial and business transactions. While they are susceptible to attacks because of their involvement in operations like asset transfers. Researchers have suggested various methods to address vulnerabilities in these contracts and improve their reliability. Nevertheless, when the contract code is excessively lengthy, redundant contextual information may adversely affect repair performance. To address this problem, we propose a localizable machine learning model to repair long contracts. Firstly, we extract a data collection that includes code structure information from the abstract syntax tree of the smart contract source code. Then we leverage a pre-trained BERT model to generate code embeddings and use BiLSTM for training the vulnerability localization model. Finally, the vulnerable code lines in the contract are localized based on statistical thresholding of the model’s output values. On this basis, we construct the corresponding code extraction algorithms to generate code repair fragments and use machine learning techniques to repair contracts. We compare our method with existing approaches using public datasets. The results demonstrate a significant improvement in performance over direct repair methods, effectively addressing the challenges associated with the repair of long-code smart contracts.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 10-17"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal transport enhanced text-assisted discriminative clustering for intelligent network images analytics 优化传输增强文本辅助判别聚类智能网络图像分析

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-05-19 DOI: 10.1016/j.ijin.2026.05.004

Chong Li, Lianyong Qi

{"title":"Optimal transport enhanced text-assisted discriminative clustering for intelligent network images analytics","authors":"Chong Li, Lianyong Qi","doi":"10.1016/j.ijin.2026.05.004","DOIUrl":"10.1016/j.ijin.2026.05.004","url":null,"abstract":"<div><div>In digital network, the uncontrolled flow of massive web image data poses a severe challenge to efficient organization and retrieval. Traditional deep clustering methods are often costly to train and may lack sufficient discriminative power to solve these problem. This paper proposes a model to support intelligent network image analysis: Optimal Transport enhanced discriminative text-Assisted Clustering (OTAC). The OTAC model aims to enhance the discriminative power of clustering models for intelligent network image analysis. OTAC first uses a pretrained vision-language model to extract image features to reduce training cost. OTAC then utilizes an improved optimal transport mechanism to select more discriminative words for network image data, and constructs a more distinguishing text space. Subsequently, it combines optimal transport with learnable prompts to more effectively focus on fine-grained features of images in digital networks. This design further significantly improves the model’s discriminative ability and clustering performance. Extensive experiments on 7 datasets demonstrate that OTAC significantly outperforms current state-of-the-art models, validating its effectiveness for intelligent network image clustering and robust downstream automated analytics.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 31-39"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148167852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

User coverage-oriented k-model deployment in edge computing systems 边缘计算系统中面向用户覆盖的k模型部署

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-07-15 DOI: 10.1016/j.ijin.2026.07.004

Hui Peng, Hongkai Zhang, Adeem Ali Anwar

{"title":"User coverage-oriented k-model deployment in edge computing systems","authors":"Hui Peng, Hongkai Zhang, Adeem Ali Anwar","doi":"10.1016/j.ijin.2026.07.004","DOIUrl":"10.1016/j.ijin.2026.07.004","url":null,"abstract":"<div><div>This paper focuses on the key problem of maximizing user service coverage under a limited deployment budget in edge computing scenarios. To meet the demand of service providers to select <span><math><mi>k</mi></math></span> locations from a set of candidate edge servers for model deployment so as to maximize coverage of end-user groups, we formally define the <span><math><mi>k</mi></math></span>-Model Deployment Coverage Maximization (<span><math><mi>k</mi></math></span>MD-C) problem and prove that it is NP-hard. For this problem, we propose two methods: MD-O, an exact benchmark method based on integer programming suitable for small-scale problems, and MD-A, an efficient heuristic algorithm with superior empirical performance. Experimental validation on real-world datasets shows that MD-A significantly outperforms several state-of-the-art baseline methods in terms of coverage performance and computational efficiency, demonstrating its superior practicality and scalability for solving large-scale <span><math><mi>k</mi></math></span>MD-C problems. This study provides a theoretical foundation and efficient tools for the scientific deployment of edge intelligent services, and helps improve service coverage and user satisfaction under resource-constrained conditions.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 88-98"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148565620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Retraction notice to “Autonomous Intelligent Vehicles (AIV): Research statements, open issues, challenges and road for future” [Int. J. Intell. Netw. 2 (2021) 83 - 102] 对“自动智能汽车（AIV）：研究陈述、开放性问题、挑战和未来之路”的撤回通知[英]。j .智能。Netw. 2 (2021) 83 - 102]

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-05-12 DOI: 10.1016/j.ijin.2026.05.001

Amit Kumar Tyagi , S.U. Aswathy

引用次数: 0

RSE-YOLOv8n: A robust and real-time framework for fatigue driving detection in low-light and occluded environments RSE-YOLOv8n：一种用于低光照和闭塞环境下疲劳驾驶检测的鲁棒实时框架

International Journal of Intelligent Networks Pub Date : 2026-01-01 Epub Date: 2026-06-29 DOI: 10.1016/j.ijin.2026.06.001

Xiao Chen, Liang Wang, Jingyi Lan, Hui Guo, Zhuobao Wei

{"title":"RSE-YOLOv8n: A robust and real-time framework for fatigue driving detection in low-light and occluded environments","authors":"Xiao Chen, Liang Wang, Jingyi Lan, Hui Guo, Zhuobao Wei","doi":"10.1016/j.ijin.2026.06.001","DOIUrl":"10.1016/j.ijin.2026.06.001","url":null,"abstract":"<div><div>Fatigue driving is a leading cause of traffic accidents, necessitating robust and real-time detection methods. However, existing facial feature-based approaches often suffer from significant performance degradation under low-light conditions and facial occlusions. To address these challenges, we propose an enhanced RSE-YOLOv8n framework. Specifically, a Retinexformer-based module is introduced for illumination compensation, SAC is employed to enable efficient multi-scale feature extraction while reducing computational complexity, and an Efficient Group-wise Multi-scale Attention (EGMA) mechanism is integrated to refine feature representation. Furthermore, the dataset is augmented with occlusion and head pose variations to improve generalization. Experimental results demonstrate that the proposed method achieves a 4.5% improvement in [email protected] over the baseline YOLOv8n, reaching 96.9%, while maintaining real-time inference capability. The proposed framework exhibits strong robustness and effectiveness for fatigue driving detection in challenging environments.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 99-108"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148640257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0