Secure Sensor-Based Learning Analytics for Students with Disabilities Using Blockchain and Hybrid Artificial Intelligence

Abstract

The educational needs of students with disabilities may be ongoing and require individualized support, monitoring, and intervention to maximize learning experience and educational results. With the recent developments of Internet of Things (IoT) technologies and learning analytics, educational data can be gathered from wearable technologies, classroom sensors and assistive learning systems in real-time. But the transmission of secure data, privacy protection and efficient communication between resource constrained devices is still a challenge. This study introduces a secure sensor-based learning analytics framework that combines blockchain technology and hybrid artificial intelligence methods, facilitating students with disabilities in smart learning environments. The blockchain layer offers a decentralized and tamper-proof solution for secure data aggregation and storage in the context of learning, thereby ensuring transparency, traceability and data integrity. For the efficient communication, a hybrid Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) algorithm is used in intelligent routing and resource management. The ANN checks network conditions and device statuses, and the PSO determines communication paths that are energy efficient, minimizing overhead in the communication process and extending network lifetime. Experimental evaluation proves that it is more reliable, energy efficient, packet delivered performance and better secured data management, than the traditional approaches. The proposed framework is scalable, privacy preserving and intelligent learning analytics for learning applications that can support students with disabilities and good educational support.