Feature Detection and Extraction Techniques for Real‐Time Student Monitoring in Sensor Data Environments

The research mainly focuses on the potential of student motion behavior analysis. This study is conducted for the learning of repeated motion behavior with respect to the students (i.e., the frequently visited places and the paths taken between the places) and thereafter to show that it is possible to detect unusual behavior using the knowledge of frequent behavior. This chapter presents a novel framework using deep support vector machines for the detection and extraction of features from real‐time sensor data obtained through the wireless sensor networks placed inside an academic campus. It discusses the existing techniques used for human motion detection. The chapter presents the proposed methodology and discusses the experimental setup and the results obtained. The results obtained through the experiments prove that the proposed technique outperforms the other methods in terms of performance and accuracy.