The blistering growth of the Internet of Things (IoT) networks has posed considerable issues of security because of the growing number of connected devices and the susceptibility of them to cyberattacks. Conventional anomaly detectors usually cannot reflect complicated communication association and dynamic behavioral trends that exist in the IoT context. This paper suggests a Probabilistic Graph Learning Based Anomaly Detection (PGL-AD) model on the CICIoT2023 data. The suggested method models IoT devices as the nodes of a probabilistic graph, with the communication relationships included as weighted edges with the probabilities of interactions. Learning through graph representation is used to learn probabilistic embeddings that incorporate structural and behavioral network traffic attributes. Probabilistic inference is carried out to calculate anomaly scores to determine abnormal communication patterns. Experimental performance shows that the proposed framework has reached $99.08 \%, 98.86 \%, 98.91 \%$, and $98.86\%$ detection accuracy, precision, recall, and F1-score respectively, and is superior to the traditional machine learning and deep learning models. The probabilistic graph learning algorithm is a good algorithm with the capability to learn network dependencies and uncertainty, to be able to detect anomalies accurately and at scale. The proposed framework is a dependable and effective measure of increasing the security of IoT and ensuring that connected devices are not affected by developing cyber threats.
T. H. Vidhya, K. Nithya, K. Alqawasmi et al.· International Conference on...· 0 citations
This paper presents a hardware-efficient object detection accelerator based on XNOR-driven variable-precision computation for real-time edge artificial intelligence. The proposed network combines DenseToRes and transition layers to preserve feature information under aggressive quantization. Binary convolution is executed through XNOR and population-count operations, replacing most multiplier-based multiply-accumulate units. To maintain detection accuracy, the architecture supports 1-bit, 2-bit, and 8-bit modes so that sensitive layers can use higher precision while deeper layers operate at reduced precision. A parallel array of 64 processing elements performs multiple output-channel computations concurrently using an output-stationary dataflow. The accelerator integrates on-chip feature and weight memories, data-fetch units, batch normalization, RPReLU activation, quantization, pooling, and lightweight control logic. AXI-based interfacing enables integration with an embedded processing system and external memory. The resulting architecture reduces arithmetic complexity, memory bandwidth, and power consumption while supporting scalable real-time object detection on FPGA-based edge platforms.
Javeed Md, Srinivasa Reddy Dumpa, K. Saisri et al.· Adolescência e Saúde· 0 citations
Energy networks are evolving into smart grids due to the expansion of the Internet of Things. Control is automated, monitored, and adjusted by intelligent network systems. While this method does enhance sustainability, efficiency, and reliability, it does so at the expense of cybersecurity. Critical infrastructure concerns have grown as a result of smart grids’ reliance on the Internet of Things. Smart meters, sensors, communication gateways, and controllers all fall under this category. Supply of electricity, confidentiality of data, and safety of the nation are all under risk from assaults on grid parts. To protect smart grid infrastructure from targeted attacks, this project employs an Internet of Things architecture driven by cybersecurity. Regions of the grid will be protected by multilayer security, advanced threat detection, and communication protocols. The most important things are ensuring the data is secure, authenticating devices, responding adaptively, and detecting anomalies in real-time. The smart grid’s visibility, resilience, and risk reduction are enhanced by a combination of centralized intelligence and decentralized security measures. Cybersecurity for smart grids is challenging because to the large amount of data, the number of devices involved, and the requirements for real-time operations. These concerns of cybersecurity based on the Internet of Things are addressed in this article. Scalability is ensured while infrastructure is protected. Sustainable, dependable, and environmentally friendly power systems are a result of secure IoT design.
Muruganantham Angamuthu, R. Alazaidah, Arumai Shiney et al.· International Conference on...· 0 citations
The high rate of Internet of Things (IoT) networks development has posed a serious problem of effective resource allocation because devices are heterogeneous, the traffic conditions are dynamic, and the energy and latency requirements are severe. Traditional resource allocation methods and classical reinforcement learning methods are not always the best methods to perform in a highly dynamic environment because they lack the adaptability and reduce convergence. The proposed paper introduces a Quantum Reinforcement Learning (QRL)-motivated adaptive resource allocation model which uses quantum-inspired state representation, as well as quantum-classical policy optimization, to optimize resource allocation. The proposed model is a dynamic distribution of bandwidth, transmission power, and computational resources the real-time state of network. Experimental assessment shows better performance than the traditional and classical reinforcement learning techniques. The proposed QRL framework attains the average accuracy of resource allocation 97.84%, lessens the communication latency by 43%, escalates the throughput by 64%, and lessens the energy usage by 37%. The system also has better convergence and stability exception when applied to different network load. Combination of quantum feature encoding improves efficacy in decision and learning. The findings affirm that the suggested framework offers a powerful and scalable system of smart resource management in the next-generation IoT systems.
A.Mohan Kumar, M. Al-Shalout, M. Elakiya et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
