检索结果-内蒙古大学图书馆

Metaheuristic-Driven Abnormal Traffic Detection Model for SDN Based on Improved tyrannosaurus optimization algorithm

引用

Computers, Materials and Continua 2025年第3期83卷 4495-4513页

作者： Hui Xu Jiahui Chen Zhonghao Hu School of Computer Science Hubei University of Technology Wuhan 430068 China

Nowadays, abnormal traffic detection for Software-Defined Networking (SDN) faces the challenges of large data volume and high dimensionality. Since traditional machine learning-based detection methods have the problem of data redundancy, the Metaheuristic algorithm (MA) is introduced to select features before machine learning to reduce the dimensionality of data. Since a tyrannosaurus optimization algorithm (TROA) has the advantages of few parameters, simple implementation, and fast convergence, and it shows better results in feature selection, TROA can be applied to abnormal traffic detection for SDN. However, TROA suffers from insufficient global search capability, is easily trapped in local optimums, and has poor search accuracy. Then, this paper tries to improve TROA, namely the Improved tyrannosaurus optimization algorithm (ITROA). It proposes a metaheuristic-driven abnormal traffic detection model for SDN based on ITROA. Finally, the validity of the ITROA is verified by the benchmark function and the UCI dataset, and the feature selection optimization operation is performed on the InSDN dataset by ITROA and other MAs to obtain the optimized feature subset for SDN abnormal traffic detection. The experiment shows that the performance of the proposed ITROA outperforms compared MAs in terms of the metaheuristic-driven model for SDN, achieving an accuracy of 99.37% on binary classification and 96.73% on multiclassification.

关键词： Software-defined networking abnormal traffic detection feature selection metaheuristic algorithm tyrannosaurus optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing cybersecurity using optimized anti-interference dynamic integral neural network-based intrusion detection system

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2025年第6期67卷 5413-5435页

作者： Chaudhary, Deevesh Shekhawat, Deepika Gupta, Sunita Kalwar, Anju Mishra, Neha Nawal, Meenakshi Manipal Univ Jaipur Dept Data Sci & Engn Jaipur Ajmer Express HighwayDehmiKalanNear GVK T Jaipur 303007 Rajasthan India Amity Univ Maharastra Amity Sch Engn & Technol Dept Comp Sci & Engn Pune ExpresswayPanvel Mumbai 410206 Maharastra India Swami Keshvanand Inst Technol Management & Gramoth Informat Technol Dept Jaipur 302017 India JECRC Univ Sch Comp Sci & Applicat Jaipur Rajasthan India JECRC Univ Jaipur Dept Comp Sci & Engn Plot No IS-2036 IS-2039 Ramchandrapura Ind AreaSitapura Jaipur 303905 Rajasthan India Swami Keshvanand Inst Technol Management & Gramoth Comp Sci & Engn Dept Jaipur 302017 India

Cybersecurity has become a critical concern due to the exponential growth of the Internet of Things (IoT), computer networks, and associated applications, which have introduced new vulnerabilities and increased the risk of cyberattacks. Detecting such anomalies and designing an efficient intrusion detection system (IDS) is essential to secure interconnected systems. Therefore, this paper proposes an enhancing cybersecurity using optimized anti-interference dynamic integral neural network-based intrusion detection system (AIDINN-CSD). Here, the input data is collected through CIC IoT 2022 dataset. The input CIC IoT 2022 dataset is preprocessed using smoothing-sharpening filter (SSF) for handling missing values and data normalization. Synthetic minority oversampling technique (SMOTE) is used for data balancing. Then, the tyrannosaurus optimization algorithm (TOA) selects relevant features from the preprocessed data. The selected features are used by anti-interference dynamic integral neural network (AIDINN) for detecting normal and attack class from the data. Then, the weight parameters of AIDINN are optimized using Capuchin search optimization algorithm (CSOA) for improving accuracy and lowering computational time. The results show that the proposed technique attains 99.23% accuracy rate, 98.97% precision and 98.47% detection rate by outperforming existing techniques. These results show the effectiveness of the AIDINN-CSD in addressing the limitations of conventional IDS, particularly its ability to handle imbalanced datasets and reduce false positives thereby offering a promising solution for enhancing IoT network security and mitigating cyber threats.

关键词： Anti-interference dynamic integral neural network Capuchin search optimization algorithm Industrial control systems CIC IoT 2022 dataset Smoothing-sharpening filter tyrannosaurus optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing real-time health monitoring with hybrid recurrent long short-term tyrannosaurus search for menstrual cups

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 100卷

作者： Priyadharshini, S. Indra Irene, D. Shiny Beulah, J. Rene Ponnuviji, N. P. Vellore Inst Technol Sch Comp Sci & Engn Chennai India SRM Inst Sci & Technol Coll Engn & Technol Sch Comp Dept Comp Technol Kattankulathur Campus Chennai India Govt Polytech Coll Dept Comp Engn Aundipatti Tamilnadu India RMK Coll Engn & Technol Dept Comp Sci & Engn Puduvoyal India

Menstrual Hygiene Management is not only a health issue but also a crucial aspect of social and economic development. When women and girls have proper menstrual hygiene, it positively impacts their overall wellbeing, educational opportunities, and participation in the workforce. This study proposed the Hybrid Recurrent Long Short-term based tyrannosaurus Search (HRLS-TS) algorithm for real-time health monitoring during menstruation. The integration of these advanced techniques offers real-time data processing and analysis, especially when combined with IoT devices. In this work, a Recurrent Neural Network is employed to predict menstrual cycle-related historical data and analyze menstrual cycle patterns, also Long Short-term Memory (LSTM) is utilized to analyze menstrual flow data and capture rapid changes and fluctuations. To enhance accuracy, an initial search-based tyrannosaurus optimization technique is applied. Notably, the incorporation of tyrannosaurus optimization ensures efficient hyperparameter tuning, enhancing the overall performance of the developed method. Experiments were conducted based on performance evaluation measures such as recall, F1score, precision, Area Under the Curve-Receiver Operating Characteristic (AUC-ROC), accuracy and specificity, Mean Absolute Percentage error (MAPE), computational time, Mean Squared Error (MSE), Mean Absolute Error (MAE) and residual error, were used to assess the proposed and existing methods. The results are then compared with existing methods, demonstrating the efficiency of the HRLS-TS technique in real-time health monitoring.

关键词： Smart menstrual cup Recurrent neural network Long short-term memory tyrannosaurus optimization algorithm Initial search strategy Menstrual waste management

来源：评论

学校读者我要写书评

暂无评论

Wind Turbine Blade Fault Detection Method Based on TROA-SVM

引用

SENSORS 2025年第3期25卷 720-720页

作者： Lei, Zhuo Lin, Haijun Tang, Xudong Xiong, Yong Wen, He Hunan Normal Univ Coll Engn & Design Changsha 410081 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Hunan Lianzhi Technol Co Ltd Changsha 410200 Peoples R China Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China

Wind turbines are predominantly situated in remote, high-altitude regions, where they face a myriad of harsh environmental conditions. Factors such as high humidity, strong gusts, lightning strikes, and heavy snowfall significantly increase the vulnerability of turbine blades to fatigue damage. This susceptibility poses serious risks to the normal operation and longevity of the turbines, necessitating effective monitoring and maintenance strategies. In response to these challenges, this paper proposes a novel fault detection method specifically designed for analyzing wind turbine blade noise signals. This method integrates the tyrannosaurus optimization algorithm (TROA) with a support vector machine (SVM), aiming to enhance the accuracy and reliability of fault detection. The process begins with the careful preprocessing of raw noise signals collected from wind turbines during actual operational conditions. The method extracts vital features from three key perspectives: the time domain, frequency domain, and cepstral domain. By constructing a comprehensive feature matrix that encapsulates multi-dimensional characteristics, the approach ensures that all relevant information is captured. Rigorous analysis and feature selection are subsequently conducted to eliminate redundant data, thereby focusing on retaining the most significant features for classification. A TROA-SVM classification model is then developed to effectively identify the faults of the turbine blades. The performance of this method is validated through extensive experiments, which indicate that the recognition accuracy rate is 98.7%. This accuracy is higher than that of the traditional methods, such as SVM, K-Nearest Neighbors (KNN), and random forest, demonstrating the proposed method's superiority and effectiveness.

关键词： wind turbine blades feature extraction fault diagnosis tyrannosaurus optimization algorithm support vector machine

来源：评论

学校读者我要写书评

暂无评论

An Efficient Cyber Security Attack Detection With Encryption Using Capsule Convolutional Polymorphic Graph Attention

引用

TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES 2025年第3期36卷

作者： Kumar, P. J. Sathish Bapu, B. R. Tapas Sridhar, S. Nagaraju, V. Panimalar Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India SA Engn Coll Dept ECE Chennai Tamil Nadu India SVYASA Univ City campus Bengaluru India Saveetha Univ Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Biotechnol Chennai Tamil Nadu India

As digitalization permeates all aspects of life, the Internet has become a critical platform for communication across various domains. Workstations within organizations often handle sensitive and private data, underscoring the need for encryption to safeguard information and prevent unauthorized access. Despite advances in system security, challenges remain in the form of system vulnerabilities and evolving cyber threats. Intrusion detection using deep learning (DL), which serves as the second line of defense after firewalls, has progressed rapidly, yet still faces issues such as misclassification, false positives, and delayed or inadequate responses to attacks. These ongoing problems necessitate continuous improvement in system security screening and intrusion detection to protect networks effectively. Therefore, in this research, a novel DL framework called capsule convolutional polymorphic graph attention neural network with tyrannosaurus optimization algorithm (CCPGANN-TOA) is utilized for attack detection due to its advanced feature representation, graph attention for focusing on key data points, polymorphic graphs for adaptability, and TOA for performance optimization. Normal data are then encrypted using the digital signature algorithm based on elliptic curve cryptography (DSA-ECC) because it provides strong security with smaller key sizes, resulting in faster computations and efficient resource utilization. The proposed method outperforms traditional approaches in terms of 99.98% accuracy of data set I, 99.9% accuracy of data set II, and 900 Kbps higher throughput with low delay.

关键词： convolutional polymorphic graph attention neural network elliptic curve cryptography encryption intrusion detection tyrannosaurus optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

OPTIONS attack detection in WSN using Optimized Multitask Multi-Attention Residual Shrinkage Convolutional Neural Network

引用

KNOWLEDGE-BASED SYSTEMS 2024年 300卷

作者： Selvi, S. Tamil Visalakshi, P. Kumar, M. Senthil SRM Inst Sci & Technol Dept Networking & Commun Kattankulathur 603203 Tamilnadu India SRM Valliammai Engn Coll Dept Cyber Secur Kattankulathur 603203 Tamilnadu India

The rapid increase in Internet users has made web applications essential for daily services, rendering them targets for various cyber-attacks like path traversal, zero-day attacks, and injection attacks. While traditional security measures can prevent many familiar attacks, they are often ineffective against OPTIONS attacks, which involve injecting malicious code via hyperlinks to obstruct user access to legitimate webpage content. To address this novel challenge, we propose the OAD-WSN-MMRCNN technique, leveraging an Optimized Multitask MultiAttention Residual Shrinkage Convolutional Neural Network for OPTIONS attack detection in Wireless Sensor Networks (WSNs). This approach begins by selecting a CPU parameters dataset for attack detection, followed by pre-processing with a Variational Bayesian-Based Maximum Correntropy Cubature Kalman Filter to remove redundant data. Key features such as handles, threads, processor, context switch, deferred procedure call (DPC), interrupt delta, CPU socket, and core are extracted using a variable velocity strategy particle swarm optimization algorithm. The MMRCNN, optimized with the tyrannosaurus optimization algorithm, is then employed to detect normal and OPTIONS attacks. Implemented in Python, the efficacy of OAD-WSN-MMRCNN is evaluated using metrics such as energy consumption, target window, accuracy, precision, F-measure, recall, and CPU utilization. Experimental results demonstrate that OAD-WSN-MMRCNN outperforms existing techniques, achieving a 20 % improvement in detection accuracy and a 25 % reduction in energy consumption, highlighting its effectiveness and potential for enhancing web application cyber security.

关键词： OPTIONS attack tyrannosaurus optimization algorithm Variable velocity strategy particle swarm optimization algorithm VBMCCKF WSN

来源：评论

学校读者我要写书评

暂无评论

Quaternion generative adversarial -driven Soc estimation using tyrannosaurus optimizer for improving hybrid electric vehicles renewably powered energy management

引用

Scientific Reports 2025年第1期15卷 1-21页

作者： Sivaramkrishnan, M. Subramani, Jaganathan Alam, Mohammad Mukhtar Hui, Liew Tze Department of Electrical and Electronics Engineering Karpagam College of Engineering Coimbatore India Department of Industrial Engineering College of Engineering King Khalid University Abha 61421 Saudi Arabia Center for Engineering and Technology Innovations King Khalid University Abha 61421 Saudi Arabia Centre for Intelligent Cloud Computing (CICC) Faculty of Information Science & Technology Multimedia University Jln Ayer Keroh Lama Melaka 75450 Malaysia

The change in transportation efficiency in the last several years has seen several new engine technologies like EVs and HEVs being more prevalent. Integration of RES wind energy technique, solar photovoltaics, and bio-energies becomes a requirement during the transition from conventional houses to smart houses and from conventional cars for energy efficient electric or hybrid vehicles. The battery of an HEV can only be charged to a certain level and similarly it should not be discharged beyond a certain limit, hence the battery state of charge (SOC) in HEVs has to be supervised by a smart battery management system (BMS). However, the current method requires improvement of the performance of SOC estimate on HEVs. Therefore, development of new SOC estimation method with DL for safe renewable energy management (REM) framework for Hybrid EV (Electric vehicles) is the prime focus of this paper is developed as DLSOC-REM. For more accurate SOC estimate, the proposed approach employs a Quaternion Generative Adversarial Network (QGAN) model. When hyper parameter tuning, the prototype is invigorated employing the tyrannosaurus optimization algorithm (TOA) to fine-tune SOC estimate outcomes of the QGAN model. Using the QGAN model simplifies the modeling process and gives a correct representation of the battery model’s input–output relationship. The work’s originality is demonstrated by the design of the TOA-based QGAN model for SOC estimation. The suggested approach shows excellent accuracy with few errors for various drive cycles and temperatures: for US06, the RMSE stabilizes at about 0.05%, the MAE drops to 0.1%, and the MSE reaches 0.0025%. © The Author(s) 2025.

关键词： Battery management system Electric vehicles Quaternion generative adversarial network Renewable energy sources State of charge tyrannosaurus optimization algorithm

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：