Open AccessAN ADVANCED APPROACH TO RECOGNIZE HUMAN ACTIVITIES VIA DEEP LEARNING
Author(s) -
Aryan Karn,
Dharm Raj Maurya
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v06i01.036
Subject(s) - computer science , activity recognition , deep learning , artificial intelligence , raw data , machine learning , wearable computer , set (abstract data type) , data set , deep belief network , human–computer interaction , embedded system , programming language
The study of wearable and handheldsensors recognizing human activity improved ourunderstanding of human behaviours and human objectives.Many academics seek to identify the activities of a user fromraw data using the fewest necessary resources. In this article,we propose a network of profound beliefs, a full-servicearchitecture for the recognition of activities (DBN-LSTM).This DBN-LSTM method improves the humanpredictability of raw data and reduces the complexity of themodel as well as the requirement for comprehensiveworkmanship. A geographically and temporally richnetwork is CNN-LSTM. Our proposed model for the UCIHAR Public Data Set can achieve 99% accuracy and 92%precision.