检索结果-内蒙古大学图书馆

IoT botnet detection from software defined network using American zebra optimization algorithm with SSRNN-ElM

International Journal of Information Technology (Singapore) 2025年第2期17卷 959-967页

作者： Bindu, Nalluri Venkata Madhu Nassa, Vinay Kumar Vasuki, P. Manikandan, G. Jeena, R. Mahaveerakannan, R. Department of CSE-AIML Malla Reddy Engineering College (Autonomous) Medchal Secunderabad Malkajgiri (Dist) India Ellenki College of Engineering and Technology (ECET) Patelguda (v) Ameenpur (m) Sangareddy (D) Hyderabad Telangana India Department of Information Technology Sri Sivasubramaniya Nadar College of Engineering Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

Software-defined networking (SdN) offers centralized control over large-scale networks, enhancing flexibility and enabling tailored network applications. However, SdN introduces new security vulnerabilities, including the risk of botnet attacks, which can compromise systems and steal data. This paper proposes a novel approach for detecting botnet attacks in SdN environments by leveraging a hybrid model that integrates recurrent neural networks (RNNs) and extreme learning machines (ElMs). The proposed method utilizes RNNs for feature learning and ElMs for classification, with the American zebra optimization algorithm (AZOA) optimizing ElM weights. This hybrid SSRNN-ElM (supervised subset recurrent neural network—extreme learning machine) approach is evaluated using N-BaIoT dataset and performance metrics, demonstrating effective detection of complex botnet attacks with high accuracy. The results demonstrate that the hybrid model effectively identifies complex botnet attacks, achieving a detection accuracy of 96.60%. The integration of recurrent neural networks (RNNs) for feature learning and extreme learning machines (ElMs) for classification, along with optimization by the American zebra optimization algorithm (AZOA), significantly improves detection performance as compared to the recent existing studies. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： American zebra optimization algorithm (AZOA) BotNet attack detection Extreme learning machine (ElM) Recurrent neural network (RNN) Software-defined network (SdN)

来源：评论

学校读者我要写书评

暂无评论

A Simplified Policy Modification Framework By External provider For Human Medical Record Sharing

A Simplified Policy Modification Framework By External provi...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Pandi, C. Siva Rama lingham, N. Anish, T.P. Aruna, R. Computer Science and Engineering Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Avadi India Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi India Computer Science and Engineering R.M.K College of Engineering and Technology India

ISBN: (纸本)9798350305708

The great flexibility and accessibility of cloud computing make it a good fit for storing and managing Personal Health Records (PHR), which are often large and complex datasets. Personal health data, on the other hand, include incredibly sensitive and private information, which raises serious security and privacy concerns. There should also be a flexible and secure access plan for PHR owners' outsourced data. Although Some business cloud platforms offer symmetric or public key encryption as an add-on feature, these conventional encryption techniques are not well-suited for data outsourcing due to the high overhead of key management and maintenance. We create and put into practise a secure, granular access control system with minimal policy modifications for outsourced PHRs. On top of AES and Cypher Text encryption, our suggested method is constructed. In order to provide comprehensive policy change tracing, a policy versioning system is also presented. In the conclusion, we evaluated the effectiveness of the suggested scheme by analysing its performance. © 2023 IEEE.

关键词： access control AES performance evaluation PHR policy update policy versioning proxy re-encryption

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement by Various Segmentation Techniques Using Machine learning 6th

Image Enhancement by Various Segmentation Techniques Using M...

引用

6th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2021

作者： Chanchlani, Akshita Thakare, Vilas M. Wadhai, Vijay M. Department of Computer Science and Engineering SGBA University Amravati India Department of Electronics and Telecommunications Engineering D. Y. Patil College of Engineering Akurdi Pune India

ISBN: (纸本)9789811935701

Brain Cancer is a disease where abnormal cells grow without control and can invade other tissues, if it is identified at the early stage and treated appropriately then it can save human life. In developing countries cause of disease like brain cancer is effecting many people. Brain Cancer Medical image processing is most important and challenging field now a days. Image preprocessing and its segmentation on brain cancer Magnetic Resonance Imaging (MRI) and its analysis is process of finding the objects and understanding their significance. Image segmentation have become most popular due to its usage into various applications. The objective of this paper is exploring and implementation of various algorithms of image segmentation on medical image specifically on brain cancer MRI. Image segmentation is very important step of understanding the images for further processing and analysis. This paper represents implementation of various image segmentation techniques that includes Image Thresholding, Applying Various Morphological Operations, edge and region-based segmentation for enhancement of brain cancer images and detection of contours from brain cancer MRI. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte ltd.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

ElephantGuardNet: A Comprehensive Solution for Elephant Conservation and Human-Elephant Conflict Reduction 4

ElephantGuardNet: A Comprehensive Solution for Elephant Cons...

引用

4th International Conference on Sentiment Analysis and deep learning, ICSAdl 2025

作者： Naveen, S. dhamotharan, R. Sahebzathi, S. Krishnan, R. Santhana Kumar, V. Vinoth Sundaravadivel, P. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Mechanical Engineering Chennai India Kalasalingam Academy of Research and Education Department of Computer Science and Information Technology Krishnankoil India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798331523923

The ElephantGuardNet system is an advanced technological framework designed to monitor and protect elephants while minimizing human-elephant conflict. The system leverages a combination of real-time data collection, AI-driven analysis, and IoT sensors to track elephant movements across vast territories. By integrating wildlife camera traps, drones, satellite imagery, and IoT sensors such as infrared motion detectors and seismic sensors, the system provides continuous monitoring of elephant activity, enabling proactive management of potential risks. A custom dataset, ElephantMovementTracker, compiled from diverse data sources, forms the foundation for the model's training. Preprocessing techniques such as data normalization, augmentation, and noise filtering enhance the dataset's quality and ensure its suitability for deep learning applications. EfficientNet B7 and YOlO are employed for image and real-time detection tasks, respectively, while 3d CNNs are used for video analytics, enabling accurate tracking of dynamic movement patterns. GRU-based models predict future elephant movements, helping assess the likelihood of conflict. XGBoost is utilized for classification tasks, evaluating the risk of human-elephant conflict. The system is deployed on AWS and incorporates NVIdIA Jetson Nano for real-time detection and automated alerting via SMS and email. IoT sensors and automated deterrent systems, including sound emitters and drones, further mitigate conflict risk. The system's effectiveness in reducing human-elephant conflicts and providing a scalable solution for elephant conservation demonstrates the potential of AI and IoT integration in wildlife protection efforts, offering a comprehensive approach to both conservation and human-elephant coexistence. © 2025 IEEE.

关键词： drones

来源：评论

学校读者我要写书评

暂无评论

Overhead-Aware Resource Allocation with Cluster-Based Network Construction in VANETs 1

Overhead-Aware Resource Allocation with Cluster-Based Networ...

引用

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Hariz, Hussein Muhi Hashim, Mohammed I. Manikandan, M. Kurdi, Waleed Hadi Madhloom Jaber, Zahraa Hameed Abbas, F.H. Mazaya University College Department of Computer Techniques Engineering DhiQar Iraq The Islamic University College of Technical Engineering Department of Computer Technical Engineering Najaf Iraq Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai India Altoosi University College Department of Computer Science Najaf Iraq National University of Science and Technology Dhi Qar Iraq Al-Mustaqbal University Medical Laboratories Techniques Department Hillah Iraq

ISBN: (纸本)9798350367003

The feasibility in communication among the source to the destination is disturbed at the time of high-speed data transmission it increases the delay, overhead, and power utilization. Mainly to overcome such drawbacks in the network in this article overhead-aware resource allocation with clusterbased network construction is created. The core modules which are present in this article are vehicular network model creation and overhead-based resource allocation (ORACNC). With the presence of this process the efficiency and the reliability of the network is improved and that increases the lifespan of the vehicles. This network model is constructed in the software NS3 and the parameters which are taken into consideration for the result analysis are the packet delivery ratio, network throughput, average delay, energy efficiency, and routing overhead. The simulation result shows that the ORACNC increases the delivery ratio and it reduces the delay when compared with the previous works. © 2024 IEEE.

关键词： cluster-based network construction overhead-aware resource allocation VANETs

来源：评论

学校读者我要写书评

暂无评论

deep learning for MANET Routing

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine learning in Communications and Networking 2023年 1卷 412-424页

作者： danilchenko, Kiril Azoulay, Rina Reches, Shulamit Haddad, Yoram University of Waterloo Department of Electrical and Computer Engineering WaterlooN2L 3G1 Canada Jerusalem College of Technology Department of Computer Science Jerusalem91160 Israel

Power control and scheduling are among the most well-known resource allocation challenges in wireless networks, and are often solved as optimization problems with constraints. However, solving these optimization challenges by using optimal algorithms often incurs a significant time complexity, which creates considerable discrepancies between the theoretical results and real-time processing required. In this study, we propose a novel machine learning-based perspective to address this issue. We propose a scheduling and power control deep neural network SPCdNet method and its modification SPCdNetR. SPCdNet solves the scheduling problem for point-to-point transmission requests while SPCdNetR solves the more complex problem, where the input transmission list is composed of ordered routes which should be satisfied. Both SPCdNet and SPCdNetR are trained in a supervised manner and show near-optimal performance on the test set. Our results demonstrate that SPCdNet and SPCdNetR can serve as a computationally inexpensive solution (regarding time complexity), compared with state-of-the-art schemes, while showing to be near-optimal approximation solutions to the time scheduling and power control challenges. Moreover, we found that both SPCdNet and SPCdNetR reach efficient solutions for large problem instances, even though they were trained on small problems. © 2023 CCBY.

关键词： Time division multiple access

来源：评论

学校读者我要写书评

暂无评论

AN EARlY dIABETES dISEASES PREdICTION USING MACHINE lEARNING WITH OPTIMAl FEATURES SElECTION

AN EARLY DIABETES DISEASES PREDICTION USING MACHINE LEARNING...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Kasinathan, Prabakaran Balamurugan, M. Rao, B. dean Beema Sangeetha, M. Aminabee, Shaik Reddy, Pundru Chandra Shaker Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Tehnology Tamilnadu Chennai India Computer Science and Engineering Sri Sairam Engineering College Tamilnadu Chennai India Computer Science and Engineering Panimalar Engineering College Tamilnadu Chennai India Computer Science and Engineering SRM Madurai College for Engineering and Technology Tamilnadu India Department of Pharmacology V. V. Institute of Pharmaceutical Sciences AP Gudlavalleru India School of Computer Science and Engineering Lovely Professional University Punjab India

ISBN: (纸本)9798350305708

diabetics have elevated blood glucose levels for a lengthy period of time, either due to insufficient insulin synthesis or a lack of effective insulin response by the body's cells. long-term harm, breakdown, and collapse of diverse organs, including the eyes, kidneys, nerves, heart, and veins, are associated with the persistent hyperglycemia of diabetes. The focus of this study is on utilizing important features, developing a prediction algorithm by means of Machine-learning(Ml), and identifying the best classifier in order to obtain the most accurate results when compared to clinical outcomes. The proposed approach utilizes Predictive analysis with the goal of zeroing in on the variables that are crucial for early diagnosis of diabetes Miletus. There were a variety of methods used, including random-forest(RF), extreme-gradient-boost(EdB), logistic-regression(lR), and weighted-ensemble-models(WSM). When compared to severe gradient boost (0.93), logistic regression (0.92), and weighted ensemble model (0.87), the RF performed admirably in anticipating uncontrolled diabetes. The study also generalizes the process of picking the best features from the dataset to boost classification precision. These clinical features can be utilized in conjunction with machine learning methods for diabetes control prediction. © 2023 IEEE.

关键词： diabetes feature selection Machine learning prediction Random Forest

来源：评论

学校读者我要写书评

暂无评论

Cyber-Physical Attack detection in Additive Manufacturing: An lSTM-Based Autoencoder Approach Using Reconstruction Error Analysis from Side-Channel Monitoring

Cyber-Physical Attack Detection in Additive Manufacturing: A...

引用

2024 IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2024

作者： Chithras, T. Brijesh, K.J. Paul, M. Mano Raja Karthick, S. Bhuvanesh, A. Keerthanadevi, R. Veltech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electrical and Electronics Engineering Chennai India Gregorian Institute of Technology Department of Automobile Engineering Kottayam India Nehru Institute of Engineering and Technology Department of Electrical and Electronics Engineering Coimbatore India Sri Eshwar College of Engineering Department of English Coimbatore India Psn College of Engineering and Technology Department of Electrical and Electronics Engineering Tirunelveli India Psn College of Engineering and Technology Department of Computer Science and Engineering Tirunelveli India

ISBN: (纸本)9798331535476

In order to identify cyber-physical threats in additive manufacturing systems, this study suggests a sophisticated technique that uses data from side-channel monitoring. Strong attack detection capabilities are guaranteed by the method's integration of many important approaches for pre-processing, analyzing, and classifying time-series data. In order to make the continuous time-series data more understandable and efficient to analyze, a pre-processing method based on defined Window Sliding (FWS) is used to divide the data into manageable windows of defined size. After that, we use discrete Wavelet Transform (dWT) to get all the features out of each window, collecting important data from all the different frequency bands. Using Particle Swarm Optimization (PSO) to sift through the dWT coefficients and extract the most useful features improves classification performance by making sure that only the most informative characteristics are used. In order to train a deep learning (dl) approach that can identify anomalies via reconstruction errors, the optimal feature set is used. This technique is an lSTM-A autoencoder. We show that the suggested approach can differentiate between normal and attack cases with a 99% accuracy rate by applying it to the problem of side-channel attack detection in additive manufacturing. To protect cyber-physical systems from advanced cyberattacks, this method offers a scalable and adaptable solution while simultaneously increasing detection accuracy. © 2024 IEEE.

关键词： discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cybersecurity in the digital Age with Machine learning for Threat detection and Prevention

Enhancing Cybersecurity in the Digital Age with Machine Lear...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering Technology, ICRASET 2024

作者： Jayarin, P.Jesu david, d. Beulah Jenifa Kumari, V. Sheeja Pillai, N. Muthuvairavan Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Information Technology Thandalam Tamil Nadu Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Thandalam Tamil Nadu Chennai India R.M.D Engineering College Department of Computer Science and Business Systems Tamil Nadu Thiruvallur India

ISBN: (纸本)9798350388602

Information security cannot be underemphasized today especially with the increased use of Information Communication Technology which requires improved threat identification techniques. In this study, we propose a novel methodology comprising four variants - CyberShield, SentinelGuard, ThreatHunter, and SecureNet - and evaluate their performance against existing approaches in terms of key performance metrics: which are efficiency, precision, recall, F1-score and AUC. In all variants above experiments that we had demonstrated, there is rather more distinctive feature towards threat identifiers guaranteed other than what is presently offered. Interestingly, CyberShield with +3.8% and ThreatHunter with +3.8%, both the highest, are more accurate in terms of classifications of cyper-attacks than other algorithms. Finally, all proposed variants are ranked higher than the current approaches in terms of recall with possible variation between 4.2% and 2.2 for TP rates, meaning these approaches have the potential to minimize false negatives. In addition, the advance variants actually cause slight increase in Precision and F1-Score but with aids to make Precision equivalent to Recall, the achieved performance is relatively higher. What this would do is expose the advantages of the new proposed variants in terms of the degree of influence human behavior and the rate of risk of cyber threats. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Optimized Hybrid deep learning Framework for Monitoring Botnet Attacks in IoT Networks 5

An Optimized Hybrid Deep Learning Framework for Monitoring B...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Manimaran, A. Sathish Kumar, P.J. Kartheesan, l. Kumutha, d. Surendran, R. Karpaga Vinayaga College of Engineering and Technology Technical Sciences Department of Electronics and Communication Engg Chengalpattu India Panimalar Engineering College Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr.Sangunthala R&D Department of Computer Science and Engineering Institute of Science and Technology Chennai India Jeppiaar Institute of Technology Department of Electronics and Communication Engg Sriperumudur India Saveetha School of Engineering Department of Computer Science and Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518097

The serious threat of botnet attacks in the IOT world today can be effectively addressed with deep learning (dl). However, to train the model, large and complex data sets are required, which adds cost and necessitates expensive hardware to perform intricate mathematical operations. The IoT plays a significant challenge in memory constrained by implementing the dl. The hybrid Principal Component Analysis (PCA) and Autoencoder is proposed to measures the performance to lower the IoT network traffic data and consumes bulky information. Following that, reduced datasets are examined and trained using hybrid long Short Term Memory (lSTM) and Convolutional Neural Network (CNN) algorithms. The hybrid deep learning algorithms attain the feature to enhance the precision, accuracy, recall, and F1 scores 96.51%, 100%, 96.51%, and 98.22%, which were higher than the conventional methods. The model's performance is analyzed using extensive experiments. © 2024 IEEE.

关键词： Bot (Internet)

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：