TY - GEN
T1 - Partially Observable Markov Decision Process Model for Dynamic Human Activity Recognition Using Radio Frequency Signals
AU - Wang, Feifan
AU - Jones, Derick
AU - Walker, Laura
AU - Borah, Bijan
AU - Salehinejad, Hojjat
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Human activity recognition (HAR) using radio frequency signals and machine learning is a novel approach for sensing and detection of human activities in a privacy preserving scheme. This is particularly important in healthcare systems, since privacy of patients and staff is a priority. Another advantage of this technology is the non-contact activity recognition with no need of line-of-sight (LoS). However, limited attention has been paid to human activity dynamics and their impact on HAR. In this paper, we propose a framework for dynamic human activity recognition (DHAR) based on a partially observable Markov Decision Process (POMDP) model, motivated by potential inaccuracy of current HAR models in real-world environments and human activity dynamics. The POMDP model dynamically uses historical data of observed human activities and model selections to select an HAR model from a set of given models. An approximate method is proposed to solve the POMDP model. The simulation experiments show that the DHAR method can deliver better performance over each single HAR model.
AB - Human activity recognition (HAR) using radio frequency signals and machine learning is a novel approach for sensing and detection of human activities in a privacy preserving scheme. This is particularly important in healthcare systems, since privacy of patients and staff is a priority. Another advantage of this technology is the non-contact activity recognition with no need of line-of-sight (LoS). However, limited attention has been paid to human activity dynamics and their impact on HAR. In this paper, we propose a framework for dynamic human activity recognition (DHAR) based on a partially observable Markov Decision Process (POMDP) model, motivated by potential inaccuracy of current HAR models in real-world environments and human activity dynamics. The POMDP model dynamically uses historical data of observed human activities and model selections to select an HAR model from a set of given models. An approximate method is proposed to solve the POMDP model. The simulation experiments show that the DHAR method can deliver better performance over each single HAR model.
UR - http://www.scopus.com/inward/record.url?scp=85174421325&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174421325&partnerID=8YFLogxK
U2 - 10.1109/CASE56687.2023.10260550
DO - 10.1109/CASE56687.2023.10260550
M3 - Conference contribution
AN - SCOPUS:85174421325
T3 - IEEE International Conference on Automation Science and Engineering
BT - 2023 IEEE 19th International Conference on Automation Science and Engineering, CASE 2023
PB - IEEE Computer Society
T2 - 19th IEEE International Conference on Automation Science and Engineering, CASE 2023
Y2 - 26 August 2023 through 30 August 2023
ER -