检索结果-内蒙古大学图书馆

Federated learning-based hybrid convolutional recurrent neural network for multi-class intrusion detection in IoT networks

引用

Discover Internet of Things 2025年第1期5卷 1-22页

作者： Selvam, Prabu Karthikeyan, P. Manochitra, S. Sujith, A.V.L.N. Ganesan, T. Ayyasamy, Rajaram Shuaib, Mohammed Alam, Shadab Rajendran, A. School of Computing SRM Institute of Science and Technology Tiruchirappalli621105 India Department of Electronics and Communication Engineering Velammal College of Engineering and Technology Tamil Nadu Madurai625009 India Department of Computer Science Engineering St Joseph’s College of Engineering Tamil Nadu Chennai600119 India School of Engineering Malla Reddy University Telangana Hyderabad500043 India Department of Computer Science Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of Electronics and Communication Engineering E.G.S Pillay Engineering College Tamil Nadu Nagapattinam611002 India Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of ECE Karpagam College of Engineering Tamil Nadu Othakkal Mandapam India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

As Internet of Things (IoT) devices leads an significant challenges in securing the systems from cyber-attacks in large-scale IoT networks. Traditional methods faces struggle to precisely detecting the complex intrusion patterns due to the heterogeneity and distributed IoT devices. There is a pressing need for scalable, real-time, and privacy-preserving solutions to secure IoT and IIoT systems. For multi-class intrusion detection in IoT networks, this study proposed an novel hybrid convolutional recurrent neural network (CRNN) model based on federated learning. By integrating federated learning, the proposed approach ensures privacy by enabling decentralized model training among IoT devices without exchanging sensitive data. The hybrid CRNN model improves detection accuracy for a variety of attack types in IoT networks by combining Recurrent Neural Networks for sequential pattern recognition and Convolutional Neural Networks for feature extraction from raw data. The proposed model classifies incoming network traffic into different attack classes. The experimental results conducted on the Edge-IIoT dataset reveal that the proposed model has attained the detection accuracy of 98.93% with balanced precision and recall for all the attack types and low-support classes such as SQL Injection and Man-in-the-Middle. This balance improves model’s ability to reduce both false negatives and false positives compared with conventional approaches. Together with real-time detection, our approach excels in a privacy-preserving manner, providing a practical, scalable solution for securing complex IoT networks, and addressing critical gaps in current IDS frameworks. © The Author(s) 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

RRSC-128/64-V1: a two-variant simple, fast, and secure lightweight stream cipher

引用

International Journal of Information Technology (Singapore) 2025年 1-9页

作者： Chatterjee, Runa Chakraborty, Rajdeep Department of Computer Science and Engineering Netaji Subhash Engineering College West Bengal Kolkata 700152 India Department of Computer Science and Engineering Medi-Caps University Madhya Pradesh Indore India

Lightweight cryptography is now emerging as a new method for providing security to resource-constrained devices. Securing those devices from external hackers during data transmission is now becoming an important issue. This paper proposed a lightweight simple stream cipher which provides security and confidentiality of the data among resource-constrained devices. The proposed cipher comes in two variants: 128-bit and 64-bit based on the key size it used. The user can used any of these two variants as per application type and the features of the resources. Although the stream cipher design is simple but it delivers outstanding hardware performance compared to some well-known stream ciphers like Grain, Trivium, Mickey and two Grain-like stream ciphers Planet and Lizard. It proves its efficiency greater than all except Trivium. It also passed the 15 randomness tests of the National Institute of Standards and Technology (NIST). © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Embedded system FPGA Hardware metrics LFSR Lightweight cryptography Lightweight stream cipher NFSR NIST Nonce Randomness Throughput

来源：评论

学校读者我要写书评

暂无评论

PLD-Det: plant leaf disease detection in real time using an end-to-end neural network approach based on improved YOLOv7

引用

Neural Computing and Applications 2024年第34期36卷 21885-21898页

作者： Mehedi, Md Humaion Kabir Nawer, Nafisa Ahmed, Shafi Khan, Md Shakiful Islam Hasib, Khan Md Mridha, M.F. Alam, Md. Golam Rabiul Nguyen, Thanh Thi Department of Computer Science and Engineering BRAC University Dhaka Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Department of Computer Science American International University Dhaka Bangladesh Department of Data Science and AI Monash University Wellington Rd Clayton MelbourneVIC3800 Australia

In order to maintain sustainable agriculture, it is vital to monitor plant health. Since all species of plants are prone to characteristic diseases, it necessitates regular surveillance to search for any symptoms, which is utterly challenging and time-consuming. Besides, farmers may struggle to identify the type of plant disease and its potential symptoms. Hence, the interest in research like image-based computer-aided automated plant leaf disease detection by analyzing the early symptoms has increased enormously. However, limitations in the plant leaf image database, for instance, unfitting backgrounds, blurry images, and so on, sometimes cause underprivileged feature extraction, misclassification, and overfitting issues in existing models. As a result, we have proposed a real-time plant leaf disease detection architecture incorporating proposed PLD-Det model, which is based on improved YOLOv7 with the intention of assisting farmers while reducing the issues in existing models. The architecture has been trained on the widely used PlantVillage dataset, which resulted in an accuracy of 98.53%. Furthermore, SHapley Additive exPlanations (SHAP) values have been analyzed as a unified measure of feature significance. According to the experimental findings, the proposed PLD-Det model, which is an improved YOLOv7 architecture, outperformed the original YOLOv7 model in test accuracy by approximately 4%. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Seed

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient resource allocation in blockchain-based Cybertwin-driven 6G

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 103-114页

作者： Salim, Mikail Mohammed Pan, Yi Park, Jong Hyuk Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of Department of Computer Science Georgia State University Atlanta United States

Inefficient task scheduling schemes compromise network performance and increase latency for delay intolerant tasks. Cybertwin based 6G services support data logging of operational queries for appropriate resource allocation in Multi-Access Edge and Cloud Computing. In this paper, a Cybertwin assisted task scheduling scheme is proposed for energy-efficient job allocation to Edge-Cloud based on delay tolerance. Cybertwins using the Logger Function and the Digital Asset Function exchange Digital Assets with cloud operators using Smart Contracts to ensure maximum computational resources. The novelty of this study resides in using Communication Assistant Cybertwins to build profiles for all network entities and assign tasks based on their delay tolerance and the available resources of each Edge Datacenter and Cloud service provider. Compared with the Full Offloading scheme, experimental results demonstrate the higher energy efficiency of the task scheduling scheme. Offloading tasks to multiple data centers and smart contract-based selection of cloud operators result in reduced computation time. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

DisCovHAR: Contrastive Attention for Human Activity Recognition Under Distribution Shifts

引用

IEEE Internet of Things Journal 2025年第12期12卷 21973-21983页

作者： Chen, Luke Odema, Mohanad Al Faruque, Mohammad Abdullah University of California Department of Electrical Engineering and Computer Science IrvineCA92697 United States

Advances in Internet-of-Things (IoT) wearable sensors and Edge-Artificial Intelligence (Edge-AI) have enabled practical realizations of Machine Learning (ML)-enabled mobile sensing applications like Human Activity Recognition (HAR). The effective deployment of these data-driven models necessitates learning robust representations capable of handling prevalent Distribution Shifts (DS), including new users, device positions, rotations, and more. In that respect, Contrastive Learning (CL) has shown promise in learning transformation-invariant features, outperforming traditional HAR methods. However, recent findings reveal that the contrastive loss induces shrinkage and expansion of the feature space which may limit the generalization capacity of the model. To address this, we propose DisCovHAR, a contrastive attention method to selectively apply the contrastive loss to a subset of the feature space through the transformer encoder attention mechanism. Extensive experiments on three HAR datasets (DSADS, PAMAP2, USCHAD) demonstrate its superiority over state-of-the-art methods. Specifically, our approach yields up to 4.47% and 7.82% average accuracy improvements in subject-wise and position-wise generalization settings. Furthermore, DisCov-HAR demonstrates up to 5.07% increased robustness compared to prior methods under multivariate distribution shift scenarios. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Exploration of alzheimer disease using design of experiments

引用

Multimedia Tools and Applications 2025年第3期84卷 1079-1101页

作者： Gupta, Pranav Pandey, Kavita Gupta, Sanskar Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

This study examines the use of experimental designs, specifically full and fractional factorial designs, for predicting Alzheimer’s disease with fewer variables. The full factorial design systematically investigates the effects of selected factors, providing a comprehensive analysis of their individual and interactive impacts on Alzheimer’s prediction. On the other hand, the fractional factorial design simplifies the model by selecting key factors and removing non-significant ones. For Alzheimer’s, among all the factors examined, the MMSE (Mini-mental state Examination) score emerged as the most significant, which was further cross-validated using Minitab software Analysis. Importantly, the findings suggest that the fractional factorial design is a better alternative, particularly when time and cost constraints are present. The results highlight the effectiveness and efficiency of these experimental designs, demonstrating their potential for early detection, prevention, and treatment of Alzheimer’s disease. By contributing to the expanding knowledge base on experimental designs in medical research, this study emphasizes their crucial role in understanding and combating complex diseases like Alzheimer’s. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Human Detection-Enhanced YOLO Comparative Analysis 4

Deep Learning Model for Human Detection-Enhanced YOLO Compar...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Suresh, P. Aswathy, R.H. Soms, Nisha Niranjani, V. Saveetha School of Engineering Simats Department of Computer Science and Engineering Thandalam Chennai India Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Sri eshwar college of engineering Department of Computer science and engineering Coimbatore India

ISBN: (纸本)9798331540364

Video surveillance systems employing closed-circuit television (CCTV) are crucial for public safety. Accurately detecting humans within video frames is a core component of this technology. This knowledge is crucial for numerous uses, including detecting possible dangers, observing crowd dynamics, and examining patterns of human behavior. This research introduces a new method called YOLOv8, designed to enhance human detection capabilities within CCTV footage. The proposed algorithm, YOLOv8, is built upon the popular object recognition framework, YOLO, but with significant enhancements to improve its accuracy and efficiency in detecting humans. YOLOv8 utilizes deep convolutional neural networks (CNNs) and advanced object recognition techniques to achieve high accuracy in human detection, even in challenging environments such as low light conditions, occlusions, and varying scales of human poses. To assess the effectiveness of YOLOv8, various tests were performed using standard datasets and real-world CCTV surveillance footage. The results demonstrate that YOLOv8 outperforms existing human detection algorithms regarding accuracy, robustness, and real-time processing capability. YOLOv8 achieved an average precision of over 95% in human detection, making it highly suitable for everyday CCTV surveillance. The proposed YOLOv8 algorithm has the potential to significantly improve human detection in security camera footage and enhance public safety. This research contributes to advancing human detection technology and can benefit various domains, including law enforcement, public safety, and video analytics. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Fast Area Optimization Approach for Mixed Polarity Reed-Muller Logic Circuits

引用

Chinese Journal of Electronics 2024年第5期33卷 1165-1180页

作者： Yuhao ZHOU Zhenxue HE Jianhui JIANG Xiaojun ZHAO Fan ZHANG Limin XIAO Xiang WANG School of Software Engineering Tongji University Key Laboratory of Agricultural Big Data of Hebei Province Hebei Agricultural University School of Computer Science and Engineering Beihang University School of Electronic and Information Engineering Beihang University

Area has become one of the main bottlenecks restricting the development of integrated circuits. The area optimization approaches of existing XNOR/OR-based mixed polarity Reed-Muller(MPRM) circuits have poor optimization effect and efficiency. Given that the area optimization of MPRM logic circuits is a combinatorial optimization problem, we propose a whole annealing adaptive bacterial foraging algorithm(WAA-BFA), which includes individual evolution based on Markov chain and Metropolis acceptance criteria, and individual mutation based on adaptive probability. To address the issue of low conversion efficiency in existing polarity conversion approaches, we introduce a fast polarity conversion algorithm(FPCA). Moreover, we present an MPRM circuits area optimization approach that uses the FPCA and WAA-BFA to search for the best polarity corresponding to the minimum circuits area. Experimental results demonstrate that the proposed MPRM circuits area optimization approach is effective and can be used as a promising EDA tool.

关键词： Integrated circuits Microorganisms Annealing Logic circuits Circuits Benchmark testing Delays

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Writer Identification Based on Generating Clusterable Embeddings

引用

computer Systems science & engineering 2023年第8期46卷 2059-2073页

作者： M.F.Mridha Zabir Mohammad Muhammad Mohsin Kabir Aklima Akter Lima Sujoy Chandra Das Md Rashedul Islam Yutaka Watanobe Department of Computer Science and Engineering American International University BangladeshDhaka1229Bangladesh Department of Computer Science&Engineering Bangladesh University of Business&TechnologyDhaka1216Bangladesh Department of Computer Science and Engineering University of Asia PacificDhaka1216Bangladesh Department of Computer Science and Engineering University of AizuAizu-Wakamatsu965-8580Japan

The writer identification system identifies individuals based on their handwriting is a frequent topic in biometric authentication and verification *** to its importance,numerous studies have been conducted in various *** have established several learning methods for writer identification including supervised and unsupervised ***,supervised methods require a large amount of annotation data,which is impossible in most *** the other hand,unsupervised writer identification methods may be limited and dependent on feature extraction that cannot provide the proper objectives to the architecture and be *** paper introduces an unsupervised writer identification system that analyzes the data and recognizes the writer based on the inter-feature relations of the data to resolve the uncertainty of the features.A pairwise architecturebased Autoembedder was applied to generate clusterable embeddings for handwritten text ***,the trained baseline architecture generates the embedding of the data image,and the K-means algorithm is used to distinguish the embedding of individual *** proposed model utilized the IAM dataset for the experiment as it is inconsistent with contributions from the authors but is easily accessible for writer identification *** addition,traditional evaluation metrics are used in the proposed ***,the proposed model is compared with a few unsupervised models,and it outperformed the state-of-the-art deep convolutional architectures in recognizing writers based on unlabeled data.

关键词： Writer identification pairwise architecture clusterable embeddings convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Predictive Caching of File System for Database Workload Management 1

Predictive Caching of File System for Database Workload Mana...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Jadhav, Rohini Jadhav, Veena Pawar, Prajakta Kannaujia, Abhishek Kumar, Abhishek Gohil, Jayesh College of Engineering Department of Information Technology Pune India College of Engineering Department of Computer Engineering Pune India Bharati Vidyapeeth College of Engineering Department of Computer Engineering Lavale Pune India Veritas Principal Software Engineering India

ISBN: (纸本)9798350355611

The proactive caching technique known as 'predictive caching' attempts to improve file system performance by anticipating and pre-fetching data that is likely to be requested in the future. Conventional caching strategies, such LRU (Least Recently Used) and LFU (Least Frequently Used), base their decision on which material to keep in the cache on historical access patterns. Although these methods work well in many situations, they could not completely take advantage of the temporal and geographical proximity of file system access patterns, which could result in less-than-ideal cache use. Utilizing machine learning algorithms, statistical analysis, or heuristics, predictive caching makes predictions about future access patterns based on past data, system status, file properties, or user activity. So we propose a predictive caching technique which reduce access latency and boost system performance by pre-fetching and storing pertinent data ahead of time in anticipation of incoming data accesses. © 2025 IEEE.

关键词： Dynamic Data File Access Pattern Predictive Caching Random Forest Classifier

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：