Chronological Poor and Rich Tunicate Swarm Algorithm integrated Deep Maxout Network for human action and abnormality detection

Abstract

Human behavior has always been a significant parameter in social interaction and human activity recognition is a major clue that eases the analysis of human character. In recent decades, researchers have gained more attention towards human activity detection that plays a huge part in different domains, like intelligent video surveillance, and human computer communication in order to improve security level. In order to recognize the human action from videos, effective features are required. However, extraction of effective features is still resembles as a challenging process due to changes occurred in human action. In order to counterpart such limitations, this article proposes an effective strategy for human action recognition and abnormality detection using Chronological Poor and Rich Tunicate Swarm Algorithm (CPRTSA)-based Deep Maxout Network. However, the human action recognition and abnormality detection is performed using same Deep Maxout Network, where the network classifier is trained using proposed CPRTSA. The proposed approach provides better accuracy in terms of human action recognition with higher efficiency and the proposed CPRTSA achieved a maximum accuracy of 0.959, maximum sensitivity of 0.963, and a maximum specificity of 0.965.