TY - GEN
T1 - An Unsupervised Approach to Motion Detection Using WiFi Signals
AU - Tahir, Naveed
AU - Liu, Yang
AU - Wang, Tiexing
AU - Katz, Garrett E.
AU - Chen, Biao
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - WiFi signals have been demonstrated to facilitate non-intrusive detection of a range of activities and behaviors in the physical environments they permeate. Different activities affect both phase and magnitude of channel state information (CSI) in WiFi networks in a complex yet predictable way, and machine learning models can be trained to classify activities from such information. While constructing such WiFi-sensing systems is generally convenient and cost-effective, acquiring labeled data for a particular task can be time and labor-intensive. In this paper, we seek to remedy this issue in the context of human motion detection using deep unsupervised learning. Our proposed method uses a deep clustering model trained on appropriately-preprocessed CSI magnitude-only data to detect human motion with over 99 % accuracy in the absence of any ground labels. Removing the need for labeled samples significantly reduces the training overhead, making it a promising alternative to existing methods for motion detection.
AB - WiFi signals have been demonstrated to facilitate non-intrusive detection of a range of activities and behaviors in the physical environments they permeate. Different activities affect both phase and magnitude of channel state information (CSI) in WiFi networks in a complex yet predictable way, and machine learning models can be trained to classify activities from such information. While constructing such WiFi-sensing systems is generally convenient and cost-effective, acquiring labeled data for a particular task can be time and labor-intensive. In this paper, we seek to remedy this issue in the context of human motion detection using deep unsupervised learning. Our proposed method uses a deep clustering model trained on appropriately-preprocessed CSI magnitude-only data to detect human motion with over 99 % accuracy in the absence of any ground labels. Removing the need for labeled samples significantly reduces the training overhead, making it a promising alternative to existing methods for motion detection.
KW - RF sensing
KW - WiFi sensing
KW - channel state information
KW - deep unsupervised learning
KW - human activity recognition
UR - http://www.scopus.com/inward/record.url?scp=85190153486&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85190153486&partnerID=8YFLogxK
U2 - 10.1109/ICMLA58977.2023.00143
DO - 10.1109/ICMLA58977.2023.00143
M3 - Conference contribution
AN - SCOPUS:85190153486
T3 - Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
SP - 966
EP - 972
BT - Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
A2 - Arif Wani, M.
A2 - Boicu, Mihai
A2 - Sayed-Mouchaweh, Moamar
A2 - Abreu, Pedro Henriques
A2 - Gama, Joao
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
Y2 - 15 December 2023 through 17 December 2023
ER -