Home|Journals|Articles by Year|Audio Abstracts

Original Article

JJCIT. 2021; 7(4): 363-372


Yee Leong Tan, Yan Chiew Wong, Syafeeza Ahmad Radzi.


Human activities can be recognised through reflections of wireless signals which solve the problem of privacy concerns and restriction of the application environment in vision-based recognition. Spiking Neural Networks (SNNs) for human activity recognition (HAR) using Wi-Fi signals has been proposed in this work. SNNs are inspired by information processing in biology and processed in a massively parallel fashion. The proposed method reduces processing resources while still maintaining accuracy through using frail but robust to noise spiking signals for information transfer. The performance of HAR by SNNs is compared with other machine learning (ML) networks such as LSTM, Bi-LSTM and GRU models. Significant reduction in memory usage while still having accuracy that is on a par with other ML networks has been observed. More than 70% saving in memory usage has been achieved in SNNs compared with the other existing ML networks, making SNNs potential solutions for edge computing in industrial revolution 4.0.

Key words: Human Activity recognition, Wi-Fi signals, Spiking Neural Network

Full-text options

Share this Article

Online Article Submission
• ejmanager.com

ejPort - eJManager.com
Refer & Earn
About BiblioMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Bibliomed are open access articles licensed under Creative Commons Attribution 4.0 International License (CC BY), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.