IOT based wearable sensor system architecture for classifying human activity
Measurement Sensors · vol. 39 · 101871-101871 · 2025
Abstract
Human Activity Recognition (HAR) has applications in diverse fields, including sports management and behavior classification. Existing HAR methods can be categorized into three main approaches: camera-based, wearable sensor-based, and Wi-Fi sensing-based. Camera-based methods suffer from privacy concerns, while wearable sensor-based methods face limitations in battery longevity and continuous monitoring. Wi-Fi sensing methods mitigate privacy and battery issues but rely on costly Intel 5300 network cards or software-defined radio (SDR) platforms, limiting scalability. This paper presents a cost-effective IoT-based human activity recognition system using ESP32, leveraging its Wi-Fi sensing capabilities. The proposed system follows a structured workflow: (i) channel state information (CSI) is extracted from ESP32 modules, (ii) data preprocessing is performed using Hampel and Gaussian filters for noise and outlier removal, (iii) dimensionality reduction is achieved through Principal Component Analysis (PCA) and Discrete Wavelet Transform (DWT), and (iv) activity classification is conducted using Dynamic Time Warping (DTW) and the K-Nearest Neighbors (KNN) algorithm. Experimental evaluations demonstrate that the proposed system achieves an average recognition accuracy of 98.6 % across six human activities, comparable to high-end Intel 5300-based HAR systems, while significantly reducing hardware costs and improving ease of deployment.
Details
- Journal
- Measurement Sensors
- Publisher
- Elsevier BV
- Volume
- 39
- Issue
- —
- Pages
- 101871-101871
- ISSN
- 2665-9174
- Year
- 2025
- Language
- en
- License
- cc-by-nc
- Open access
- gold
- Citations
- 1
- Source
- scopus
Keywords
Topics
Context-Aware Activity Recognition Systems (Computer Science) · Indoor and Outdoor Localization Technologies (Engineering) · Gait Recognition and Analysis (Engineering)
Cite this
Mahalakshmi, V., Kumar, P., Bhende, M. S., Keshta, I. M., Rathod, S. Y., Ramesh, J. V. N. (2025). IOT based wearable sensor system architecture for classifying human activity. Measurement Sensors, 39, 101871-101871. https://doi.org/10.1016/j.measen.2025.101871
Mahalakshmi, V., Kumar, P., Bhende, M. S., Keshta, I. M., Rathod, S. Y., Ramesh, J. V. N. 2025, 'IOT based wearable sensor system architecture for classifying human activity', Measurement Sensors, vol. 39, 101871-101871. Available at: https://doi.org/10.1016/j.measen.2025.101871
Mahalakshmi V, Kumar P, Bhende MS, Keshta IM, Rathod SY, Ramesh JVN. IOT based wearable sensor system architecture for classifying human activity. Measurement Sensors. 2025;39, 101871-101871.
@article{mahalakshmi2025815,
title = {IOT based wearable sensor system architecture for classifying human activity},
author = {V.J. Mahalakshmi and Pramod Kumar and Manisha Sunil Bhende and Ismail Mohamed Keshta and Swatiben Yashvantbhai Rathod and Janjhyam Venkata Naga Ramesh},
year = {2025},
journal = {Measurement Sensors},
volume = {39},
pages = {101871-101871},
publisher = {Elsevier BV},
doi = {10.1016/j.measen.2025.101871},
url = {https://doi.org/10.1016/j.measen.2025.101871}
}TY - JOUR AU - V.J. Mahalakshmi AU - Pramod Kumar AU - Manisha Sunil Bhende AU - Ismail Mohamed Keshta AU - Swatiben Yashvantbhai Rathod AU - Janjhyam Venkata Naga Ramesh TI - IOT based wearable sensor system architecture for classifying human activity PY - 2025 JO - Measurement Sensors VL - 39 SP - 101871-101871 DO - 10.1016/j.measen.2025.101871 UR - https://doi.org/10.1016/j.measen.2025.101871 ER -
