检索结果-内蒙古大学图书馆

A QoS-aware adaptive cross-layer cyber-attack detection algorithm for vehicular networks

Vehicular Communications 2025年 54卷

作者： Kaur, Avneet Saiyed, Makhduma F. al-Anbagi, Irfan Shamim Hossain, M. Faculty of Engineering and Applied Science University of Regina Regina SK Canada Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh 12372 Saudi Arabia

Securing data transmission and detecting cyber-attacks in consumer Vehicular Ad hoc Networks (VANETs) pose significant challenges due to the highly dynamic topology of the network and frequent mobility of nodes. These characteristics enable attackers to exploit vulnerabilities and evade detection, making real-time attack detection complex while maintaining the Quality of Service (QoS). In this paper, we propose an Adaptive Cross-layer Cyber-attack Detection (ACCD) algorithm that dynamically detects and isolates malicious nodes while optimizing traffic routing based on application-specific requirements. The proposed algorithm uses a cross-layer traffic-aware approach to classify data flows into security-critical and delay-sensitive applications, ensuring optimal routing through the selection of Ant Colony Optimization (ACO) and Ad hoc On-Demand Multipath Distance Vector (AOMDV) protocols. The integration of pre-route authentication (PRA) enhances malicious node isolation, reducing the impact of selective forwarding and blocking attacks. Simulation results show that ACCD achieves lower end-to-end delay and higher Packet Delivery Ratio (PDR) while effectively balancing network security and performance. © 2025

关键词： ACO AOMDV Cross layer Cyber-attacks End-to-end delay Intelligent transportation system Reliability VANETs

来源：评论

学校读者我要写书评

暂无评论

A hybrid blockchain and AI-based approach for attack protection to secure internet of medical things networks

引用

alexandria engineering Journal 2025年 128卷 223-230页

作者： Hadeel alsolai Fahd N. al-Wesabi ali M. al-Sharafi Asma alshuhail Abdulbasit A. Darem Bandar M. alghamdi Fouad Shoie alallah Abdulrahman alzahrani Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information Technology University of Bisha Bisha 67714 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia Department of Computer Science and Engineering College of Computer Science and Engineering University of Hafr Al Batin Saudi Arabia

The Internet of Medical Things (IoMT) has revolutionized healthcare by enabling real-time monitoring, remote diagnosis, and seamless data exchange among medical devices and providers. However, the interconnected and distributed nature of IoMT systems exposes them to significant cybersecurity threats, including data breaches and unauthorized access. This study aims to develop a secure and scalable framework to safeguard IoMT environments using blockchain technology, federated learning, and dynamic consensus algorithms. The proposed approach integrates artificial intelligence to detect threats and employs federated learning to maintain patient privacy while training models collaboratively. Experimental evaluation of the framework shows improved data security, reduced response times, and enhanced system trustworthiness. The results suggest that the integration of blockchain and AI-driven mechanisms offers a robust solution to IoMT cybersecurity challenges, paving the way for more reliable and efficient healthcare systems.

关键词： Internet of medical things (IoMT) Blockchain security Federated learning AI-driven anomaly detection Cyber threat mitigation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Continual Learning for Domain-Knowledge Retention in Healthcare Federated Learning

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Iqbal, Saeed Zhong, Xiaopin Khan, Muhammad Attique Wu, Zongze alHammadi, Dina Abdulaziz Liu, Weixiang Choudhry, Imran Arshad Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Prince Mohammad Bin Fahd University Department of AI Alkhobar Saudi Arabia Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Systems Riyadh11671 Saudi Arabia University of Central Punjab Faculty of Information Technology and Computer Science Department of Software Engineering Lahore Pakistan

Internet of Medical Things (IoMT) applications encounter issues with data protection, continual adaptation, and domain-specific knowledge retention, especially in consumer-centric IoMT scenarios. We overcome these obstacles and facilitate effective knowledge retention and task adaptation in IoMT applications. This study attempts to create a unique privacy-preserving federated learning framework that combines a hierarchical learning structure with Continual Learning (CL). Despite the advancements in Federated Learning (FL), current models have trouble integrating changing datasets in real-time while protecting privacy, as well as catastrophic forgetting, which occurs when previously learned knowledge is lost when adjusting to new tasks. We present a hierarchical learning framework that makes use of three levels of models -Junior Model (JM), Consultant Model (CM), and Senior Consultant Model (SCM) -to overcome these drawbacks. Each level of the model aids in archived retention and domain-knowledge adaptation. To guarantee that the model maintains valuable information over time and adapts to new tasks with ease, our method blends domain adaptation strategies with ongoing learning approaches like knowledge distillation and elastic weight consolidation (EWC). We compare the suggested methodology with current state-of-the-art (SOTA) models on healthcare datasets for tasks like illness diagnosis and medical image categorization. According to our findings, the hierarchical continual learning model performs better than SOTA techniques in terms of accuracy, task adaptability, and privacy protection. In the healthcare industry, our study sets a new standard for privacy-preserving, continuously adaptable federated learning systems, allowing for real-time, scalable IoMT applications that can adapt dynamically to a variety of changing datasets. © 1975-2011 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Guava Health Monitoring Using Deep Vision: A VGG-16 Model Implementation

Guava Health Monitoring Using Deep Vision: A VGG-16 Model Im...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Jashanpreet Kaur Shalli Rani Nagendar Yamsani Hasssan Muhamedale Gaurav Sharma Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Punjab India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu India

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

The researchers in this study utilize VGG-16 deep model to classify guava with diseases in three classes - Anthracnose, Fruit Fly, and Healthy Guava. This approach will solve the issues when there are problems with recognition of the diseases affecting a number of crops, resulting in loss to the farmer from economic standpoint. The study used an annotated dataset which was taken under varied natural conditions so that it yields robust results. Over 24 epochs, the model reached a training accuracy of 99.95% and a validation accuracy of 98.86% with high precision of 0.9996, recall of 09996, and area under the curve (AUC) value of 1.0000. The results show that the model is able to extract important features such as dark lesions for Anthracnose, puncture marks for Fruit Fly, and smooth textures for healthy guavas, thus making the classification correct. However, some misclassifications were noted, and these mainly occurred in the Fruit Fly class, thus there is a need for more diversified datasets and pre processing techniques. This study points out the potential that the VGG-16 model may have in fully automating the identification of diseases for guava crops, towards precision agriculture and sustainable farming practices. Future work will include the integration of attention mechanisms and advanced augmentation techniques to enhance the performance of the model and overcome classification challenges.

关键词： Training Precision agriculture Accuracy Attention mechanisms Crops Feature extraction Data augmentation Lesions Diseases Farming

来源：评论

学校读者我要写书评

暂无评论

Optimizing vibratory energy harvesters with differentiable data-driven control

引用

Chaos, Solitons and Fractals 2025年 198卷

作者： al-zahrani, Mohammed S. alsaade, Fawaz W. alsaadi, Fuad E. Department of Computer Networks and Communications College of Computer Sciences and Information Technology King Faisal University Al-Ahsa31982 Saudi Arabia Department of Computer Science College of Computer Sciences and Information Technology King Faisal University Al-Ahsa31982 Saudi Arabia Communication Systems and Networks Research Group Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah Saudi Arabia

Nonlinear vibratory energy harvesters often exhibit multiple coexisting attractors, making their control challenging and energy-intensive. Ensuring an effective transition between these attractors while minimizing control effort is crucial for maximizing power generation and maintaining system stability. This paper introduces a differentiable data-driven control strategy that optimizes energy harvester performance by leveraging a neural network (NN)-based control framework. Unlike traditional fixed-gain or surrogate modeling approaches, the proposed method directly integrates system dynamics and control power consumption into the gain adaptation process, ensuring real-time adaptability. By exploiting the differentiability of neural networks, the controller employs gradient-based optimization to continuously refine control parameters in response to changes in operating conditions. The control framework consists of an offline training phase, where the neural network learns an energy-efficient control strategy through differentiable simulations. During this phase, the neural network is trained using a large dataset of system responses to different control inputs, allowing it to learn the most energy-efficient control strategy. This trained network is then used in the online deployment phase, where the trained controller dynamically adjusts control parameters in real-time. The proposed approach minimizes control energy consumption and efficiently guides the system toward the high-energy attractor, avoiding unnecessary control effort. Our approach significantly outperforms conventional PID-based sliding mode controllers. Simulation results confirm that the differentiable controller considerably enhances energy harvesting efficiency and reduces chattering, ensuring a smooth transition to the high-energy orbit while maintaining robust system stability. The study also highlights the necessity of an adaptive control strategy, stressing the urgency of its implementation for o

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Tactile-Driven Rule Configuration and Anomaly Detection in Industrial IoT Systems

引用

IEEE Internet of Things Journal 2025年

作者： Tan, Lizhuang Singh, Amritpal Zhang, Wei Pei, Hongjuan Zhang, Peiying Chahal, Prabhjot Kaur Singh, Maninderpal Ji'nan250014 China Pohang University of Science and Technology Department of Computer Science and Engineering Pohang37673 Korea Republic of Northumbria University Department of Computer and Information Sciences United Kingdom University of Chinese Academy of Sciences School of Engineering Science Beijing100049 China China University of Petroleum Qingdao Institute of Software College of Computer Science and Technology East China Qingdao266580 China Chandigarh Group of Colleges CEC Punjab Mohali India Southern Methodist University Electrical and Computer Engineering Department Dallas United States

The Industrial Internet of Things (IIoT) enables communication among automation systems, machinery, and sensors in an industrial setting. To optimize critical industrial operations, a substantial volume of data concerning diverse in-factory activities and automation services is generated by IoT devices and sensors. This data is subsequently transferred to distant processing systems for analysis and decision-making. Nevertheless, a substantial latency in data transmission or any abnormality in the generated data may result in delayed or erroneous decisions, consequently impacting the efficacy of essential industrial systems. To address these challenges, we established an intelligent network architecture utilizing software-defined networking that achieves tactile latencies efficiently while handling industrial data traffic in an energy-efficient manner. To address the initial challenge, the suggested architecture utilizes the Self-Organized Maps approach to distinguish between industrial traffic requiring tactile latencies and non-tactile traffic. We utilize a binary tree-based flow table mapping method to enhance flow table matching and decrease lookup times. To address the second challenge, we employ the Support Vector Machine technique to identify anomalies in real-time industrial data traffic. The Hadoop system and Mininet emulator are utilized to evaluate the proposed architecture using the UNSW dataset. The results demonstrate the effectiveness of the suggested solution in providing energy-efficient tactile assurances and identifying anomalies in traffic. © 2014 IEEE.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

AI in Credit Scoring: Developing Fair and Transparent Models for Assessing Loan Eligibility

AI in Credit Scoring: Developing Fair and Transparent Models...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： K. Raghuveer Malik Bader alazzam Rozhgar Khorsheed Mahmud ali ali Saber Mohammed Omar Mohsen Hussein I Infant Raj School of Management V.R. Siddhartha Engineering College (Deemed to be University) Kanuru A.P. India Faculty of Information Technology Jadara University Irbid Jordan Department of Accounting College of Administrative and Financial Sciences Knowledge University Erbil Iraq Department of Computer Engineering Al Kitab University Kirkuk Iraq Department of Biomedical Engineering Al-Farahidi University Baghdad Iraq Department of CSE K.Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

Credit scoring is employed by the financial institutions to compute the credit rating of the people and the eligibility for the loans and credit dangers. However, credit scoring models includes challenges like biases, lack of interpretability, and inadequate accuracy, which becomes clear in dealing with unbalanced or missing records. They can cause biased credit decisions. Based on these challenges, we introduce Auto encoder-GAN Hybrid Model which helps to create a transparent and non-discriminatory credit scoring and loan eligibility model. The problem of data imbalance is solved using auto encoder-based feature learning and data augmentation using an advanced Generative Adversarial Network (GAN). Thus, the accuracy observed in Autoencoder-GAN was 99.3%. The use of GAN is to generate synthetic data in the model increases its capability to mean fair across samples, thereby providing a good balance of samples for every demographic group. Finally, this paper aims to demonstrate that the integration of auto encoder and GANs is an effective solution for credit scoring and also address fairness and interpretability issues with high accuracy. The proposed model is applicable to real-world financial systems by enhancing capacities of risk assessment and loan eligibility fairness as compared to the existing methods and models it can play a part in enhancing the smarter and more efficient decision making in banking and financial sector.

关键词： Representation learning Deep learning Accuracy Autoencoders Decision making Generative adversarial networks Smart systems Data models Risk management Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Over time analysis of the codon usage of SARS-CoV-2 and its variants

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2034-2050页

作者： alma Davidson Marina Parr Franziska Totzeck alexander Churkin Danny Barash Dmitrij Frishman Tamir Tuller Department of Biomedical Engineering Tel Aviv University Tel Aviv 6997801 Israel Department of Bioinformatics School of Life Sciences Technical University of Munich Freising Germany Department of Software Engineering Sami Shamoon College of Engineering Beer-Sheva 84100 Israel Department of Computer Science Ben-Gurion University Beer-Sheva 8410501 Israel Sagol School of Neuroscience Tel Aviv University Tel Aviv 6997801 Israel

As viruses evolve over time with their host, they adapt to multiple cellular functions to ensure efficient long-term transmission. Their ability to survive and function efficiently depends on optimizing their genetic code to effectively recruit the host’s gene expression machinery, particularly the translation machinery. Codon usage bias (CUB) measures the level of adaptation at the codon level, considering multiple factors such as the host’s tRNA *** estimating the adaptation scores of viruses to their host, we can gain insight into the changes that occur on the genomic level throughout their evolution. In our study, we propose tracking the viral evolution of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) using CUB to estimate adaptation. By comparing different strains and analyzing changes over time, we demonstrate an increased adaptation of the Omicron SARS-COV-2 variant. In addition, we observe fluctuations in CUB scores, with periods of decreased and then increased adaptation over time, offering detailed insights at a fine temporal resolution. This analysis further contributes to understanding how different mutations influence viral adaptation, as well as the evolution of other human-infecting viruses.

关键词： SARS-CoV-2 Comparative Analysis Over Time Analysis Codon usage Omicron

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Cloud-Edge Collaborative Intelligence Inference Framework with Runtime Dynamic Optimization for Resource-Constrained Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Wang, Chenlu Peng, Yuhuai Zhang, Dawei alturki, Ryan alshawi, Bandar alotaibi, Majid Northeastern University College of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Xihu District Hangzhou China Zhengzhou University School of Computer and Artificial Intelligence Henan Zhengzhou450001 China Umm Al-Qura University College of Computing Department of Software Engineering Makkah24382 Saudi Arabia Umm Al-Qura University College of Computing Department of Computer and Network Engineering Makkah24382 Saudi Arabia

The proliferation of Internet of Things (IoT) and embedded computing has led to widespread deployment of smart consumer electronics requiring edge-based Artificial Intelligence (AI) capabilities. However, the heterogeneous nature of sensing data and dynamic edge environments poses significant challenges for efficient model inference on resource-constrained devices. To address these challenges, this paper presents a lightweight collaborative inference framework designed for consumer electronics. First, we formulate the inference optimization problem as a Mixed-Integer Nonlinear Programming (MINLP) problem, considering channel pruning, early exit and cloud offloading decisions to optimize the trade-off between accuracy and computational cost. Second, we propose a selective model activation mechanism based on Markov Decision Process (MDP), which employs a recursive self-attention mechanism to dynamically track inference budgets and guide decision-making through encoder-decoder architectures. The mechanism integrates entropy regularization during training to ensure robust and diverse execution paths. Comprehensive experiments demonstrate that our framework achieves 65.50% reduction in model parameters and 80.68% reduction in inference Floating Point Operations (FLOPs) while maintaining accuracy loss within 0.81% of the original model, making it suitable for real-time AI applications on resource-constrained consumer electronics. © 1975-2011 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fire Detection for Industrial and Environmental Safety Using IoT-Integrated Vision Sensors and Residual Clutch Attention Network and Depthwise Distinguishable Convolutional Neural Networks

Enhanced Fire Detection for Industrial and Environmental Saf...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： D.Christy Sujatha Priyanshu Singh C. Vallikannu Ravi Varman Skanda M G T. Gavaskar Department of Software Engineering Periyar Maniammai Institute of Science & Technology Thanjavur Tamil Nadu India Department of Computer Science and Engineering R.V college of engineering Bangalore Karnataka India Department of Humanities and Sciences Rajalakshmi Engineering College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Karpagam academy of Higher Education Coimbatore Tamil Nadu India Department of Industrial and Production Engineering SJCE JSS Science and Technology University Mysore Karnataka India Department of Mechanical Engineering St. Joseph's College of Engineering Chennai Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Fire detection is an important factor in improved safety in industrial and environmental conditions. The conventional flame detectors, largely relying on heat and smoke detectors, have drawbacks of time lag, low sensitivity, and low coverage when compared with our requirement in large industrial scenes and vast natural terrains vulnerable to fire occurrence. These systems are highly unsuitable for dynamic and high-risk situations as they require a higher accuracy and a faster reaction time for the alarms to be efficient as is now the case due to the aforementioned reasons. In an attempt to remedy these limitations, this research introduces a fire detection system using IoT and vision sensors that combines a RCAN with DDCNN. This architecture is tuned using the Crayfish Optimization algorithm (COA), which seeks to improve model parameter to improve response time and accuracy. By incorporating feedbacks from sensors placed at its different parts and reading from the environment, the RCAN-DDCNN model can quickly identify the fire patterns and respond by activating the sprinkler systems as well as setting off alarms. The proposed system presents a superior option for fire detecting because it is scalable and adaptive and it provides high degree of precision, making it an optimal development in fire detection technology for industry and environment. The introduced approach attains higher accuracy as 99%.

关键词： Support vector machines Accuracy Vision sensors Sensor systems Stability analysis Safety Convolutional neural networks Time factors Optimization Smoke detectors

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：