Machine Learning Enabled e-Learner Non-Verbal Behavior Detection in IoT Environment

Internet of Things (IoT) with e-learning is widely employed to collect data from various smart devices and share it with other ones for efficient e-learning applications. At the same time, machine learning (ML) and data mining approaches are presented for accomplishing prediction and classification processes. With this motivation, this study focuses on the design of intelligent machine learning enabled e-learner non-verbal behaviour detection (IML-ELNVBD) in IoT environment. The proposed IML-ELNVBD technique allows the IoT devices such as audio sensors, cameras, etc. which are then connected to the cloud server for further processing. In addition, the modelling and extraction of behaviour take place. Moreover, extreme learning machine sparse autoencoder (ELM-SAE) model is employed for the detection and classification of non-verbal behaviour. Finally, the Ant Colony Optimization (ACO) algorithm is utilized to properly tune the weight and bias parameters involved in the ELM-SAE model. In order to ensure the improved performance of the IML-ELNVBD model, a comprehensive simulation analysis is carried out and the results highlighted the betterment compared to the recent models.