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

Brain Tumor Detection: A Comprehensive Review 5

Brain Tumor Detection: A Comprehensive Review

引用

5th International Conference on Electrical, communication and computer engineering, ICECCE 2024

作者： Bhagat, Poonam Pandian, R. Sathyabama Institute of Science and Technology Computer Science and Engineering Chennai India Sathyabama Institute of Science and Technology Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331529437

Brain tumor classification and segmentation are crucial medical imaging procedures that aid in diagnosis and treatment planning. This study provides a detailed analysis of the methodologies and techniques used in this subject, which includes conventional machine learning (ML), convolutional neural networks (CNNs), capsule networks (CapsNets), and vision transformers (ViTs). This survey identifies key challenges and opportunities in brain tumor analysis and delineates future research directions. Extant literature predominantly focuses on individual tasks such as tumor detection, segmentation, or grade estimation, indicating the necessity for integrated frameworks capable of simultaneous multi-tasking, particularly with multi-grade classification. While CNNs have been extensively utilized, alternative architectures such as CapsNets and ViTs offer promising avenues for enhancing diagnostic accuracy and efficiency. © 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

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

引用

computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

来源：评论

学校读者我要写书评

暂无评论

Development of LiFi System for communication and Control in Hilly Regions 6

Development of LiFi System for Communication and Control in ...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Dabral, Adarsh Gusain, Raj Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics and Communication Engineering Dehradun India Department of Electronics and Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350306613

In hilly regions where cable distribution is challenging and costly traditional communication systems often face difficulties. LiFi technology emerges as a promising solution in such contexts, leveraging communication through visible light. It uses light as a medium to provide data speeds that surpass those of Wi-Fi, This research paper presents an approach for a communication system specifically designed for hilly terrains using Light Fidelity (LiFi) technology. The proposed paper start with an introduction of LiFi technology and advantages of it over conventional communication methods in these regions. However, it also acknowledges the inherent limitations of Li-Fi, such as its low range, which is especially relevant in hilly topographies. The main body of the paper details the system's architecture, comprising a transmitter for sending data, a receiver to receive data, and dual operation: text for sending massage and operate devices, and audio for communication. To underscore its practicality, the system is showcased through two applications: an SOS emergency feature for hilly terrains and a device activation/deactivation application. In conclusion, the paper provides an in-depth examination of how this tailored system functions and its potential benefits for communities and operations in hilly landscapes. © 2024 IEEE.

关键词： Arduino Hilly region communication methods Laser LiFi Microcontroller Remote Station communication

来源：评论

学校读者我要写书评

暂无评论

Analytical Performance Comparison of IoT communication Protocols MQTT and CoAP from Security Perspective 3

Analytical Performance Comparison of IoT Communication Proto...

引用

3rd Odisha International Conference on Electrical Power engineering, communication and Computing Technology, ODICON 2024

作者： Swain, Satyaprakash Pattanayak, Binod Kumar Mohanty, Mihir Narayan Senapati, Chinmayee Department of Computer Science and Engineering Bhubaneswar India Department of Electronics and Communication Engineering Bhubaneswar India Department of Civil Engineering Bhubaneswar India

ISBN: (纸本)9798350354379

In this present scenario, world Internet is maximum based on H2H communication only. But in the principle of IoT, it reduces direct Human-Human and Human-Machine communication. IoT provides support to work 24 X 7 over the year without affecting the accuracy of result. IoT environment is fully based on sensors and actuators. Sensor is responsible for data collection as well as for the route of transmission and actuator is responsible for security of data, communication of data and for accuracy of data. From application point of view, now days all critical sectors like: health care sectors, defense sectors, Aviation sectors, Space sectors are strictly working on the application of IoT. Most of the work is there performed by their automated systems. If any error occurs at the time of data transmission, then that may cause a serious loss for the society. So, security mechanism is most vital part for all IoT systems. Though IoT is based on machine-to-machine communications without human intervention, we need to emphasize both on device structures and their protocols. Generally, IoT devices are very small in size and its embedded applications are less complexity. We need maximum attention if any modification is carried out in its structure. There are various types of IoT protocols available, out of them two most common protocols are CoAP and MQTT. Different security algorithms are used by these protocols for encryption and decryption of these data. Two most security algorithms are AES and ECC algorithm. The algorithm which takes low time for key generation is most suitable for IoT protocols. In this research, we are going to find out different Lou points of these two protocols. Then we will analyze two most common security algorithms i.e. AES and ECC key generation time using python codes and we will compare these times to its hybrid model key generation time. At last we have proposed a new security algorithm i.e. AES-ECC hybrid algorithm for IoT communication protocols.

关键词： Data communication systems

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction Using Levy Distribution-Based Salp Swarm Algorithm 4th

Feature Extraction Using Levy Distribution-Based Salp Swarm ...

引用

4th International Conference on Data, engineering, and Applications, IDEA 2022

作者： Jayachitra, S. Devi, S. Nandhini Hariprasath, S. Khan, Javed Akhtar Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Tamilnadu India Department of Computer Science Engineering VSB Engineering College Tamilnadu India Department of Electronics and Communication Engineering Saranathan College of Engineering Tamilnadu India Department of Computer Science and Engineering Gyan Ganga College of Technology Madhya Pradesh Jabalpur India

ISBN: (纸本)9789819700363

Feature selection is a major pre-processing stage in machine learning to identify the optimal features through diminishing the redundant features to enhance the classification accuracy. The swarm intelligence algorithm provides superior optimal solution through distributive search over complete search in the feature space. Nevertheless, the SSA algorithm falls with local optima and poor convergence rate. In this paper, the levy distribution-based Salp Swarm Algorithm (LDSSA) framework is proposed to strengthen the balance among explorative and exploitative samples. The goal of this work is to minimize the higher dimensionality for larger datasets by feature extraction. The experimental results were examined on 10 Benchmark datasets from UCI repository to legitimize the supremacy of proposed algorithm with other existing methodologies. The comparative outcome shows the distribution improves the performance of SSA method and surpasses over other optimization algorithm. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Pollutants and Heavy Metal Detection in Water Samples Employing Artificial Intelligence 2

Pollutants and Heavy Metal Detection in Water Samples Employ...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and communications Systems, ICMACC 2024

作者： Barusu, Madhusudhana Reddy Kothuri, Rahul Ravindra College of Engineering For Women Electronics and Communication Engineering Kurnool India Mohan Babu University Computer Science and Engineering Tirupathi India

ISBN: (纸本)9798350366570

The increasing prevalence of water contamination by heavy metals and other pollutants poses a serious threat to public health. This study presents an innovative approach to detecting pollutants and heavy metals in water samples using Artificial Intelligence (AI). Utilizing a comprehensive dataset containing concentrations of various contaminants such as aluminium, ammonia, arsenic, and lead, we trained and evaluated multiple machine learning models. The models assessed included Decision Trees, Logistic Regression, Support Vector Machines (SVM), Gradient Boosting and Random Forest, with performance metrics such as accuracy, precision, recall, and F1-score used for evaluation. Gradient Boosting achieved the highest performance, demonstrating superior accuracy and reliability in predicting water safety. The methods detects the pollutants with accuracy of 95.6%, 90.93%, 94.15%, 95.75% and 95.8% respectively. The results highlight the potential of AI to significantly enhance the efficiency and accuracy of water quality monitoring systems. By providing real-time assessments of water safety, this AI-enabled approach offers a robust solution for early detection and management of water contamination. This study underscores the critical role of AI in ensuring safe drinking water, thereby contributing to public health protection and environmental sustainability. The integration of AI into water monitoring frameworks can revolutionize the approach to maintaining water quality standards. © 2024 IEEE.

关键词： Heavy metals

来源：评论

学校读者我要写书评

暂无评论

DeepFakeGuard: Safeguarding Digital Platforms Against Fake Profiles Using AI 4

DeepFakeGuard: Safeguarding Digital Platforms Against Fake P...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Swarna Sudha, M. Manjula, S. Bharathi, Indira Krishnasamy, Valarmathi Vijayalakshmi, K. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India School of Computer Science and Engineering Vellore Institute of Technology Chennai India PSR Engineering College Department of Electronics and Communication Engineering Sivakasi India

ISBN: (纸本)9798331523923

This research introduces DeepFakeGuard, a hybrid deep learning framework designed to detect fake profiles on social media platforms, addressing the growing threat of fraudulent accounts online. DeepFakeGuard integrates multiple data modalities, including textual, visual, behavioral, and network features, to accurately classify profiles as real or fake. Leveraging advanced deep learning models such as BERT for textual analysis, ResNet for image processing, and LSTM for modeling behavioral patterns, DeepFakeGuard provides a comprehensive and robust solution for identifying fake profiles across diverse platforms. The framework processes a rich set of profile characteristics, including account information, posting behavior, post sentiment, and network relationships, ensuring a multi-dimensional analysis of social media accounts. The hybrid architecture of DeepFakeGuard merges outputs from individual sub-models, which are then processed through dense layers for final classification using a sigmoid activation function. This multi-faceted approach significantly enhances detection accuracy, precision, and recall compared to traditional methods. The framework is highly scalable and adaptable to various social media platforms, offering a versatile tool for strengthening online security. With strong performance metrics, including high classification accuracy, DeepFakeGuard demonstrates its potential for real-world applications in mitigating the risks associated with fake profiles. By fostering secure and trustworthy social media environments, this research contributes to the ongoing fight against fraudulent accounts, paving the way for safer online interactions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Flexible Ring Slot Antenna for Optimized 5G Performance in N77 and N78 Frequency Bands for Wearable Applications

引用

Progress in Electromagnetics Research C 2024年 150卷 47-55页

作者： Soni, Gaurav Kumar Yadav, Dinesh Kumar, Ashok Sharma, Chanchal Yadav, Manish Varun Department of Electronics and Communication Engineering Manipal University Jaipur Rajasthan Jaipur India Department of Electronics and Communication Engineering Government Mahila Engineering College Rajasthan Ajmer India Department of Computer Science Engineering in Artificial Intelligence and Machine Learning Saraswati College of Engineering Maharashtra Navi Mumbai India Department of Aeronautical and Automobile Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India

The growth of 5G communications has created a demand for advanced wearable and flexible antennas due to supporting the high speeds, low latency, and capability of mechanical deformation conditions such as bending and conformability. In this paper, the design and analysis of a defected ground structure (DGS)-based ring slot antenna for N77 (3.3–4.2 GHz) and N78 (3.3–3.8 GHz) frequency bands is demonstrated. The antenna is made of an RT/Duroid 5880 substrate and has a loss tangent (tan δ) of 0.0009 and dielectric constant (Εr) of 2.2. A DGS-based ring slot microstrip antenna is simulated, tested, and experimentally characterized on different body locations (leg, chest, and hand) along with bending, and their results are presented accordingly. The magnitude of S11 (|S11|) of the proposed antenna is −26.81 dB at resonant frequency of 3.45 GHz, with the impedance bandwidth of 22 MHz (3.486 GHz to 3.508 GHz), peak gain of 6.27 dBi, and radiation efficiency of 85.02%. The simulated specific absorption rate (SAR) for 1 g and 10 g human body tissues is 0.263 W/Kg and 0.076 W/Kg, respectively. The total volume of the antenna is 0.58λ0 × 0.58λ0 × 0.00595λ0 (at 3.5 GHz). The proposed antenna is suitable for 5G wearable devices. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Detection of Distributed Denial of Service in The Application Layer of IoT Using Machine Learning 15

Detection of Distributed Denial of Service in The Applicatio...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Nanthiya, D. Gopal, S.B. Manjula Devi, R. Praveenkumar, R. Vijayakumar, S.D. Raja, T. Dharanish Sriram, L. Kongu Engineering college Department of Computer Technology -UG Perundurai India Kongu Engineering College Department of Electronics and Communication Engineering Perundurai India Kpr institute of Engineering and Technology Department of Computer science and Engineering Coimbatore India Builders Engineering College Department of Electronics and Communication Engineering Kangeyam India Vivekanandha college of Technology for women Department of Electronics and Communication Engineering Tiruchengode India

ISBN: (纸本)9798350370249

Cybersecurity prevents harmful assaults on computers, networks, and mobile devices. Included in the category of cyber-attacks are threats like as malware, distributed denial of service assaults, phishing, spoofing, code injection, and supply chain attacks. Massive denial-of-service assaults are destructive. As part of a Distributed Denial-of-Service (DDoS) assault, hackers bypass botnets and go straight for the server. In order to temporarily block or suspend a website, these botnets send a flood of requests to the server. The server typically takes requests and returns responses. There will be a brief outage if the server gets more requests than it can handle. While this attack makes the service inaccessible, it prevents data theft. A machine-learning approach is used to detect server-side DDoS assaults. The term 'machine learning' refers to software that can learn new tasks and solve old ones without any input from a human. Learning Vector Quantization, Support Vector Machine, Naive Bayes, K-Nearest Neighbour, Random Forest, and Decision Tree are the six ML classification models used since these ML procedures enhance accuracy. The main goal of this research is to use the CIDAD dataset to find ways to protect the application layer of the Internet of Things (IoT) against Distributed Denial of Service (DDoS) attacks. The lower layers of the IoT network architecture are disregarded by this dataset, which comprises information at the COAP level. © 2024 IEEE.

关键词： CIDAD Cyber security Cyber-attacks DDoS attacks

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：