Human Action Recognition Based on a Sequential Deep Learning Model

Abstract

Human Action Recognition (HAR) is an application-oriented field that utilizes numerous Machine Learning methods to identify diverse human actions or movements to provide an appropriate or suitable response. A HAR method's success largely depends on the performance of the algorithms for data processing and activity prediction working in the background. This article inscribes an easy action recognition method based on a sequential Deep Learning model. Instead of using intricated signal processing, feature extraction, and feature selection techniques, we used a special type of matrix formulated directly from raw data. The described method has been tested on three different HAR datasets — namely UCI HAR, WISDM, and KU-HAR — and the maximum classification accuracies achieved on them were 98.99%, 96.53%, and 96.67%, respectively. Other evaluation metrics yield similar outcomes, which asserts the method's reliability. Detailed descriptions and discussions of each step of the methodology, reported results, and limitations have been provided with necessary illustrations.