TY - JOUR
T1 - Environment-Robust WiFi-based Human Activity Recognition using Enhanced CSI and Deep Learning
AU - Shi, Zhenguo
AU - Cheng, Qingqing
AU - Zhang, J. Andrew
AU - Xu, Richard Yi Da
N1 - Publisher Copyright: IEEE
This work was supported in part by the Australian Government through the Australian Research Council’s Discovery Projects Funding Scheme under Project DP210101411
PY - 2022/12/15
Y1 - 2022/12/15
N2 - Deep learning has demonstrated its great potential in channel state information (CSI)-based human activity recognition (HAR), and hence has attracted increasing attention in both the industry and academic communities. While promising, most existing high-accuracy methodologies require to retrain their models when applying the previous-trained ones to a new/unseen environment. This issue has limited their practical usabilities. In order to overcome this challenge, this article proposes an innovative scheme, which combines an activity-related feature extraction and enhancement (AFEE) method and matching network (AFEE-MatNet). The proposed scheme is 'one-fits-all,' meaning that the trained model can be directly applied in new/unseen environments without any retraining. We introduce the AFEE method to enhance CSI quality by eliminating noise. Specifically, the approach mitigates environmental noises unrelated to activity while better compressing and preserving the behavior-related information. Moreover, the size of feature signals generated by AFEE are reduced, which in turn significantly shortens the training time. For effective feature extraction, we propose to use the MatNet architecture to learn transferable features shared among source environments. To further improve the recognition performance, we introduce a prediction checking and correction scheme to rectify some classification errors that do not abide by the state transition of human behaviors. Extensive experimental results demonstrate that our proposed AFEE-MatNet significantly outperforms existing state-of-the-art HAR methods, in terms of both recognition accuracy and training time.
AB - Deep learning has demonstrated its great potential in channel state information (CSI)-based human activity recognition (HAR), and hence has attracted increasing attention in both the industry and academic communities. While promising, most existing high-accuracy methodologies require to retrain their models when applying the previous-trained ones to a new/unseen environment. This issue has limited their practical usabilities. In order to overcome this challenge, this article proposes an innovative scheme, which combines an activity-related feature extraction and enhancement (AFEE) method and matching network (AFEE-MatNet). The proposed scheme is 'one-fits-all,' meaning that the trained model can be directly applied in new/unseen environments without any retraining. We introduce the AFEE method to enhance CSI quality by eliminating noise. Specifically, the approach mitigates environmental noises unrelated to activity while better compressing and preserving the behavior-related information. Moreover, the size of feature signals generated by AFEE are reduced, which in turn significantly shortens the training time. For effective feature extraction, we propose to use the MatNet architecture to learn transferable features shared among source environments. To further improve the recognition performance, we introduce a prediction checking and correction scheme to rectify some classification errors that do not abide by the state transition of human behaviors. Extensive experimental results demonstrate that our proposed AFEE-MatNet significantly outperforms existing state-of-the-art HAR methods, in terms of both recognition accuracy and training time.
KW - Channel state information (CSI)
KW - deep learning
KW - device-free sensing
KW - human activity recognition (HAR)
KW - WiFi
UR - http://www.scopus.com/inward/record.url?scp=85135216127&partnerID=8YFLogxK
U2 - 10.1109/JIOT.2022.3192973
DO - 10.1109/JIOT.2022.3192973
M3 - Journal article
AN - SCOPUS:85135216127
SN - 2327-4662
VL - 9
SP - 24643
EP - 24654
JO - IEEE Internet of Things Journal
JF - IEEE Internet of Things Journal
IS - 24
ER -