Blockchain-Based Smart Monitoring Framework for Defense Industry

• Published in: IEEE access Vol. 12; pp. 91316 - 91330
• Main Authors: Alqahtani, Abdullah, Alsubai, Shtwai, Alanazi, Abed, Bhatia, Munish
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Activity recognition; Artificial neural networks; Blockchain; Blockchains; Cloud computing; Cybersecurity; Data models; Data processing; Defense industry; digital twin; Digital twins; Effectiveness; Internet of Things; Military personnel; Monitoring; Network latency; Personnel; Real-time systems; Remote monitoring; Sensors; Smart cameras; smart surveillance; Surveillance; Technology assessment; US Department of Defense
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3421573

Internet of Things (IoT) technology has been widely adopted across various industries for remote decision-making, monitoring, and surveillance. The proliferation of IoT applications in sensitive sectors, such as national defense and security, has been driven by the ability to obtain in-depth information on ubiquitous occurrences. Conspicuously, the current research presents a comprehensive framework based on the IoT-empowered Digital Twin technology for assessing the national integrity of defense personnel. The primary objective is to identify the integral behavior of military personnel by securely tracking everyday activities. The proposed method demonstrated the ability to accurately analyze an individual's anomalous occurrences in activities using a hybrid Convolution Neural Network with Gated Recurrent Units. Moreover, each personnel is mapped using a secure blockchain platform for acquiring social interactions and activities to identify potential threats to national security. The proposed model has been validated using challenging date sets obtained from public repositories. The computed results indicate that the proposed solution is successful in facilitating the development of high-quality defense services. The effectiveness of the suggested solution is evaluated using statistical metrics including vulnerable activity recognition (Precision 95.24%), model training and testing (Precision 95.24%, Recall (95.00%), and F-Measure 94.11%), latency rate (7.45 seconds), and data processing cost(<inline-formula> <tex-math notation="LaTeX">\theta </tex-math></inline-formula>((n-1) logn)).