TY - JOUR
T1 - Device-Free Activity Detection and Wireless Localization Based on CNN Using Channel State Information Measurement
AU - Yan, Jun
AU - Wan, Lingpeng
AU - Wei, Wu
AU - Wu, Xiaofu
AU - Zhu, Wei ping
AU - Lun, Daniel Pak Kong
N1 - Manuscript received August 1, 2021; accepted September 13, 2021. Date of publication September 20, 2021; date of current version October 29, 2021. This work was supported by the National Natural Science Foundation of China under Grant 61771256, Grant 61471205, Grant 61801242, Grant 61801245, Grant 61871235, and Grant 61801377. The associate editor coordinating the review of this article and approving it for publication was Prof. You Li. (Corresponding author: Jun Yan.)
Publisher Copyright:
IEEE
PY - 2021/11/1
Y1 - 2021/11/1
N2 - In this paper, a novel decoupled device-free activity detection and position estimation scheme is proposed using convolutional neural networks and channel state information (CSI) measurement as inputs. For the proposed scheme, the two processes of activity recognition and localization are realized in parallel but independently. Compared with the existing joint approaches, the proposed decoupled scheme is free of error propagation between two processes and achieves better performance especially for position estimation. We also propose a CSI based radio image construction using the amplitude measurement with temporal, spatial and frequency domain information. This has been proven very competitive for feature extraction, compared with the state-of-the-art methods. Extensive experimental and simulation results under a real test setup show the superiority of the proposed scheme.
AB - In this paper, a novel decoupled device-free activity detection and position estimation scheme is proposed using convolutional neural networks and channel state information (CSI) measurement as inputs. For the proposed scheme, the two processes of activity recognition and localization are realized in parallel but independently. Compared with the existing joint approaches, the proposed decoupled scheme is free of error propagation between two processes and achieves better performance especially for position estimation. We also propose a CSI based radio image construction using the amplitude measurement with temporal, spatial and frequency domain information. This has been proven very competitive for feature extraction, compared with the state-of-the-art methods. Extensive experimental and simulation results under a real test setup show the superiority of the proposed scheme.
KW - activity recognition
KW - channel state information
KW - convolutional neural network
KW - device-free
KW - localization
UR - http://www.scopus.com/inward/record.url?scp=85115680230&partnerID=8YFLogxK
U2 - 10.1109/JSEN.2021.3114206
DO - 10.1109/JSEN.2021.3114206
M3 - Journal article
AN - SCOPUS:85115680230
SN - 1530-437X
VL - 21
SP - 24482
EP - 24494
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 21
ER -