Human Activity Recognition using Machine Learning

Authors

  • Puneeth Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • Sowmya Assistant Professor, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • Salith Ziyan Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India
  • M. R. Manu Student, Department of Information Science and Engineering, Srinivas Institute of Technology, Mangalore, India

Keywords:

CNN, Human activity recognition, 3D

Abstract

The subject of Human Activity recognition (HAR) could also be a prominent research area topic within the sector of computer vision and image processing area. It has privileged state-of-art application in various sectors, surveillance, digital entertainment and medical healthcare. It is interesting to watch and intriguing to predict such quite movements. Several sensor-based approaches have also been introduced to review and predict human activities such accelerometer, gyroscope, etc., it's its own advantages and drawbacks. Convolutional neural networks (CNN) with spatiotemporal 3 dimensional (3D) kernels are trained using data set which has Three classes that depicts activities of humans in their everyday life and work. The trained model show satisfactory performance altogether stages of coaching, testing. The ability to acknowledge various human activities enables the developing of intelligent system. Usually the task of act recognition is mapped to the classification task of images representing person’s actions. This system provides the comparison study on these methods applied for human activity recognition task using the set of images representing five different categories of daily life activities.

Downloads

Download data is not yet available.

Downloads

Published

22-07-2021

Issue

Section

Articles

How to Cite

[1]
Puneeth, Sowmya, S. Ziyan, and M. R. Manu, “Human Activity Recognition using Machine Learning”, IJRESM, vol. 4, no. 7, pp. 253–255, Jul. 2021, Accessed: Nov. 03, 2024. [Online]. Available: https://journal.ijresm.com/index.php/ijresm/article/view/1051