Proceedings of the Conference on Social and Sustainable Innovation in Technology & Engineering (SASI-ITE 2025)

<Previous Article In Volume
Next Article In Volume>

Real-Time Human Activity Detection Using Wi-Fi CSI and LSTM on Edge Devices

Authors
R. Ravi Kumar1, *, A. Shravan Kumar1, N. Sri Harsha1, P. Aditya Sarma1, R. Sree Varsha2
1Department of ECE, VNRVJIET, Hyderabad, India
2School of Electronics Engineering (SENSE), VIT-AP, Amaravathi, India
*Corresponding author. Email: rayala.ravi2024@gmail.com
Corresponding Author
R. Ravi Kumar
Available Online 31 December 2025.
DOI
10.2991/978-94-6463-940-7_32How to use a DOI?
Keywords
Wi-Fi sensing; human activity detection; channel state information; LSTM; smart environments; edge computing; ESP32; Raspberry Pi
Abstract

Wi-Fi sensing for Human Activity Detection (HAD) provides a non-intrusive, privacy-preserving approach for monitoring human activity in indoor environments. This paper presents a real-time human activity detection framework based on Channel State Information (CSI) acquired from an ESP-32 embedded development board equipped with Wi-Fi. Human activities such as walking, sitting, standing, and falling are classified based on CSI data using a time series variant of deep learning algorithm called the Long Short-Term Memory (LSTM). 5-fold cross-validation indicates the system’s strong generalization and more than 93% accuracy. To demonstrate successful real-time classification, the built model is run on a Raspberry Pi 4 using a sliding window method. This system demonstrates the potential use of Wi-Fi sensing in smart homes, smart healthcare, and safety-critical applications.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial 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 license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the Conference on Social and Sustainable Innovation in Technology & Engineering (SASI-ITE 2025)
Series
Advances in Intelligent Systems Research
Publication Date
31 December 2025
ISBN
978-94-6463-940-7
ISSN
1951-6851
DOI
10.2991/978-94-6463-940-7_32How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial 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 license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - R. Ravi Kumar
AU  - A. Shravan Kumar
AU  - N. Sri Harsha
AU  - P. Aditya Sarma
AU  - R. Sree Varsha
PY  - 2025
DA  - 2025/12/31
TI  - Real-Time Human Activity Detection Using Wi-Fi CSI and LSTM on Edge Devices
BT  - Proceedings of the Conference on Social and Sustainable Innovation in Technology & Engineering (SASI-ITE 2025)
PB  - Atlantis Press
SP  - 433
EP  - 450
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-940-7_32
DO  - 10.2991/978-94-6463-940-7_32
ID  - Kumar2025
ER  -