An Improved Human Activity Recognition Technique Based On Convolutional Neural Network

This paper provides a comprehensive study of the application of convolutional neural networks (CNNs) in the classification of human activity recognition (HAR) tasks. It describes the enhancement of CNNs from their antecedents up to the current state-of-the-art systems of deep learning (DL). A two-dimensional CNN approach is proposed to make a model for the classification of different human activities, using the publicly available WISDM dataset for HAR. The rate of accuracy for HAR through the proposed model in this experiment is 97.20%, which is better than the previously estimated state-of-the-art technique.