Design and Implementation of Improved Ensemble Classification Algorithm for Human Activity Recognition (Har)

Abstract

To recognize the human activity is considered very essential in human-to-human interaction and interpersonal relations due to its nature of providing information regarding the identity of a people, their personality and psychological state. The extraction of this information is very challenging. The main operation occurred before the systematic fields of computer vision as well as ML is the potential for recognizing the activities of different person. The human activity recognition technique is executed in various stages such as to pre-process the data, extract the features and classifying the data. This work proposes a improved ensemble model in the human activity recognition which is the combination of K-mean clustering, PCA and of multiple classifiers which are merged through voting methodology. Python is executed to get evaluated the presented framework and various metrics such as accuracy, precision and recall are considered to analyse the results. The major subject of study of the scientific and research areas of computer vision and ML is the potential of human for identifying the activities of particular person. A sequence of human body movements in which different body parts (head, hands, legs etc.) are engaged in concurrent manner is known as action.