A Review on Human Activity Recognition

Abstract

Human activity recognition(HAR) and the forecast is nowadays among the few advance application of AI and machine learning. HAR is used in Healthcare assistance systems, Security surveillance, gaming industries etc. In this paper, we look into challenges in this field and also try to get thorough knowledge of HAR architecture. We also compared different machine learning techniques like Support Vector Machine, Naïve Bayes, Random Forest, Hidden Markov model, Convolution neural network, etc. different Datasets have been taken from various sensors, camera, gyroscope, accelerometer etc.