Welcome to the InfoSci Platform
An Investigation Into the Use of Deep Learning to Recognize Human Activity

An Investigation Into the Use of Deep Learning to Recognize Human Activity

Tuhin Kumar Bera, Pinaki Pratim Acharjya
Copyright: © 2023 |Pages: 51
ISBN13: 9781668477021|ISBN10: 1668477025|ISBN13 Softcover: 9781668477069|EISBN13: 9781668477038
DOI: 10.4018/978-1-6684-7702-1.ch008
Cite Chapter Cite Chapter

MLA

Bera, Tuhin Kumar, and Pinaki Pratim Acharjya. "An Investigation Into the Use of Deep Learning to Recognize Human Activity." AI and Its Convergence With Communication Technologies, edited by Badar Muneer, et al., IGI Global, 2023, pp. 212-262. https://doi.org/10.4018/978-1-6684-7702-1.ch008

APA

Bera, T. K. & Acharjya, P. P. (2023). An Investigation Into the Use of Deep Learning to Recognize Human Activity. In B. Muneer, F. Shaikh, N. Mahoto, S. Talpur, & J. Garcia (Eds.), AI and Its Convergence With Communication Technologies (pp. 212-262). IGI Global. https://doi.org/10.4018/978-1-6684-7702-1.ch008

Chicago

Bera, Tuhin Kumar, and Pinaki Pratim Acharjya. "An Investigation Into the Use of Deep Learning to Recognize Human Activity." In AI and Its Convergence With Communication Technologies, edited by Badar Muneer, et al., 212-262. Hershey, PA: IGI Global, 2023. https://doi.org/10.4018/978-1-6684-7702-1.ch008

Export Reference

Mendeley
Favorite

Abstract

Human activity recognition (HAR) is a study area concerned with the voluntary detection of routine human activity using sensor-based time-series data. However, sensor-based HAR systems have higher misclassification rates for complex actions like running, jumping, wrestling, and swinging because of sensor reading errors. The HAR system's overall performance is decreased by these sensor errors, which produce the worst classification outcomes imaginable. For complex tasks, better accuracy can be attained using vision-based HAR systems. This technique builds a deep convolutional neural network, and then uses it to extract features from the input sequence in order to gather data. Then, the temporal connections between the images will be ascertained using LSTM. This model's accuracy was suggestively higher than that of other cutting-edge deep neural network models after it was effectively validated on the UCF50 dataset. The implementation of the models to maximize their efficacy has been covered in this chapter.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.