IIRJET

Blockchain-Enabled Artificial Intelligence System for Real-Time Threat Detection in IoT Networks

Gofurjanov Ibrokhimjon Ilkhomjon ugli, Azizov Azizbek Sabitkhanovich — Wed, 04 Nov 2026 00:00:00 +0000

The attack surface for data manipulation, unauthorized access, and distributed denial of service (DDoS) is expanding due to the continuous expansion of connected Internet of Things (IoT) devices. The Centralized security solutions are hazards to privacy and single points of failure when managing the Internet of Things' size and variety. This article suggests a Blockchain-Enabled Artificial Intelligence System (BCAIS) for Real-time Threat Detection in IoT Networks to provide decentralized trust, improved data integrity, and transparent security event monitoring. To enable real-time anomaly detection and automated reaction, the suggested model combines machine learning-based threat identification with blockchain-based security event monitoring. The methodology is designed to ensure tamper-resistant security event records while identifying known and undiscovered dangers across heterogeneous IoT domains. The model's performance is evaluated using accuracy, precision, recall, F1-score, and detection latency. This technology enhances cyber resilience in critical sectors including manufacturing, energy, and infrastructure, where maintaining operational continuity and safety depends on timely and dependable attack responses by enabling quick, comprehensible, and low-latency intrusion detection directly on edge devices.

Intelligent Evidence-Aware Fake News Detection using NLP and Cybersecurity Analytics

Cheah Chee Xiang, Kang Harnyi — Wed, 04 Nov 2026 00:00:00 +0000

The tremendous growth of social media facilitated the rapid dissemination of information, but it has also accelerated the dissemination of fake news and misleading content. The trustworthiness of supporting evidence or cybersecurity-related signals connected to online content may not be sufficiently taken into account by traditional fake news detection techniques, which frequently concentrate exclusively on textual patterns. This study proposes IEFN-CS (Intelligent Evidence-Aware Fake News Detection) that makes use of cybersecurity analytics and natural language processing (NLP) framework for detecting potential false information in social media environments. The suggested framework is produced and evaluated using accessible to the public, the Kaggle fake-news dataset includes content that has been identified as either fake or real. The framework is designed to analyze social-media content and extract contextual and semantic information. The proposed technique employs Natural Language Processing (NLP) and semantic representation is to examine the meaning and credibility-related characteristics of the content. The framework also includes cybersecurity analytics to examine suspicious URLs, source-related traits, and unusual content-sharing habits, as well as evidence-aware analysis to find supporting or contradicting material. These heterogeneous signals are integrated through an evidence-aware decision to classify content as misleading or fake. The performance of the proposed framework is evaluated using accuracy, precision, recall, F1-score. The proposed IEFN-CS framework aims to provide reliable, evidence-supported, and security-aware fake news detection while improving the transparency and robustness of misinformation identification in dynamic social media environments.

Quantum Forensics in Cybercrime Investigation and Digital Forensics: From Digital Footprints to Strategic Decision-Making

Dr. Prabhu Rajasekar Kaliappan — Wed, 04 Nov 2026 00:00:00 +0000

This paper proposes Quantum Forensics as a novel theoretical and applied paradigm for cybercrime investigation and digital forensics. The central thesis is that proving evidence in cyber crimes demands a dual approach: a quantitative, reproducible STEM (Science, Technology, Engineering, and Mathematics) method that demonstrates evidence significance scientifically, and an inferential method that connects facts to law through evidentiary frameworks spanning national legislation, international conventions, UNCITRAL model laws, and established forensic standards. These two proof methods converge through the FIRREAC analytical framework (Facts, Issue, Rule, Rule Explanation, Analysis, Conclusion) to produce Substantial Conclusive Evidence that withstands judicial scrutiny.

Energy-efficient Solar-powered Wireless Sensor Network for Smart Agriculture

Balqis Nabilah Binti Ramanizan, Dr. Hishamuddin Bin M.Salleh — Wed, 04 Nov 2026 00:00:00 +0000

Agricultural Surveillance requires constant collection of environmental data, including temperature, humidity, and soil moisture. Traditional wireless sensor networks rely mainly on batteries, which can necessitate frequent maintenance and replacement. This study suggests a Solar-Powered Wireless Sensor Network (SP-WSN) for smart agriculture that uses energy-efficient clustering, solar energy harvesting, and LoRa communication techniques. Solar energy harvesting supplies renewable power to sensor nodes implemented across agricultural fields. The sensor nodes obtain crop and environmental parameters and transfer the information utilizing a wireless communication network. An energy-efficient clustering and routing technique is utilized to balance the energy usage between sensor nodes and reduce unnecessary communication. A LoRa- based communication technique can be used to transmit low-power data across long distances between sensor nodes and the gateway. The Solar-Powered Wireless Sensor Network (SP-WSN) has been proposed to enhance energy effectiveness, communication consistency, and lifespan of the network. The performance assessment will take into account various factors including energy usage, length of time the network can run, packet delivery rate (PDR), time taken for remote transmission, amount of data sent, and remaining power supply. Performance of this technology should be evaluated according to specific procedures either through experiments or simulations in order to come up with stable measures.

Design and FPGA Implementation of a Quantized YOLO Accelerator for Low-Latency Edge Object Detection

Dr. Sivachandiran Sivaraju, R.Anandbabu — Wed, 04 Nov 2026 00:00:00 +0000

Real-time object detection on edge devices is challenging because such platforms must deliver low inference latency and high throughput under tight hardware-resource and power budgets. This work presents the design and field-programmable gate array (FPGA) implementation of a quantized YOLO (You Only Look Once) accelerator for edge object detection. The proposed approach combines a YOLO-based detection model with reduced arithmetic precision, parallel processing, pipelining, and memory-efficient dataflow to improve inference efficiency. Model quantization lowers the memory footprint and computational demand of the detector while limiting accuracy loss, and the FPGA architecture is optimized to accelerate computationally intensive operations such as convolution. The accelerator is evaluated in terms of mean average precision (mAP), precision, recall, inference latency, throughput, FPGA resource utilization, power consumption, and energy per inference, and it is compared with the corresponding floating-point and quantized software models. In the measured comparison, the accelerator that is proposed achieves the highest across both latency, throughput and power and energy efficiency in technical data collected while maintaining a detection accuracy that reaches 91% instead of 93% that the floating point approach achieves. The results demonstrate that it is possible to utilize quantization with the parallel, pipelined architectural approach based on FPGA in order to significantly lower cost of YOLO inferences executed on edge devices with very little accuracy decrease.

An Explainable Machine Learning Framework for Fault Detection, Classification, and Localization in Smart Distribution Networks

Shurooq Ahmed Mohamme, Nada Amir Humaid Al Jassasi, Muna Ali Mohammed Al Shehhi — Wed, 04 Nov 2026 00:00:00 +0000

Smart distribution networks are more complicated due to the combination of distributed generation, renewable energy sources, and enhanced monitoring technologies. These developments describe difficulties in determining electrical defects, identifying different types of faults, and precisely finding fault locations under various operating circumstances. This study suggests an Explainable Artificial Intelligence-Based fault Detection, Classification, and Localization (XAI-FDCL) in smart distribution networks. The suggested structure uses three-phase voltage and current measurements to extract pertinent electrical information, such as sequence components, statistical traits, and root mean square values. For detecting fault conditions and categorizing common fault types, such as single-line-to-ground, line-to-line, double-line-to-ground, and three-phase faults, Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) algorithms are evaluated. To determine the fault's position within the distribution network, feeder-section classification and distance regression are used in fault localization. Furthermore, Shapley Additive explanations (SHAP) are integrated to determine the electrical characteristics that aid in defect diagnosis and to evaluate model forecasts. The framework is evaluated using accuracy, precision, recall, F1-score, mean absolute error, root mean square error, and computational latency. The suggested approach aims to model transparency, localization accuracy, and fault-diagnosis reliability in order to facilitate better decision-making and effective fault management in smart distribution networks.