|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Perceiving human actions is viewed as exceptionally fundamental in interpersonal interaction and interpersonal relationships because of its inclination of giving data in regards to a group's nature, including members' personalities and psychological health. The comparison is conducted on any kind of remark against a predetermined pattern in machine vision, and the activity is recognized and labelled later on. The SVM is the classifier which is applied in the previously for recognizing the activities of individuals. The SVM classifier performs poorly at identifying human activities, necessitating the development of innovative models. The presented work suggests a hybrid approach in which Convolutional Neural Network is integrated with Long Short-Term Memory Network Model. The proposed approach achieves accuracy of up to 98 percent for the human activity recognition.
Keyword
HAR, Deep Learning, CNN, LSTM
PDF Download (click here)
|
|
|
|
|