WiFi-based human activity recognition through wall using deep learning
Wireless sensing is a promising method that integrates wireless mechanisms with strong sensing capabilities. The current focus of using WiFi Channel State Information (CSI) for human activity recognition (HAR) is the line-ofsight (LoS) path, which is mainly affected by human activities and is very s...
Saved in:
id |
my.utem.eprints.27352 |
---|---|
record_format |
eprints |
institution |
Universiti Teknikal Malaysia Melaka |
building |
UTEM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknikal Malaysia Melaka |
content_source |
UTEM Institutional Repository |
url_provider |
http://eprints.utem.edu.my/ |
language |
English |
description |
Wireless sensing is a promising method that integrates wireless mechanisms with strong sensing capabilities. The current focus of using WiFi Channel State Information (CSI) for human activity recognition (HAR) is the line-ofsight (LoS) path, which is mainly affected by human activities and is very sensitive to environmental changes. However, the signal on non-line-of-sight (nLoS) paths, particularly those passing through walls, is unpredictable due to the weak reflected signals destroyed by the wall. This work proposes a method to achieve high-accuracy wireless sensing based on CSI behavior recognition with low-cost resources by showing through-wall and widerangle predictions using WiFi signals. The technique utilizes MIMO to exploit multipath propagation and increase
the capability of signal transmission and receiving antennas. The signals captured by the multi-antenna are delivered into parallel channels with different spatial signatures. An RPi 4 B is attached to an ALFA AWUS 1900 adapter utilizing Nexmon firmware monitors and extracts CSI data with flexible C-based firmware for Broadcom/
Cypress WiFi chips. Preprocessing techniques based on CSI are applied to improve the feature extraction from the amplitude data in an indoor environment. Furthermore, a deep learning algorithm based on RNN with an LSTM algorithm is used to classify the activity instances indoors, achieving up to 97.5% accuracy in classifying seven activities. The experiment shows CSI can achieve accurate wireless sensing in nLoS scenarios with extended antennas and a deep learning approach. |
format |
Article |
author |
Wong, Yan Chiew Ahmed Abuhoureyah, Fahd Saad Mohd Isira, Ahmad Sadhiqin |
spellingShingle |
Wong, Yan Chiew Ahmed Abuhoureyah, Fahd Saad Mohd Isira, Ahmad Sadhiqin WiFi-based human activity recognition through wall using deep learning |
author_facet |
Wong, Yan Chiew Ahmed Abuhoureyah, Fahd Saad Mohd Isira, Ahmad Sadhiqin |
author_sort |
Wong, Yan Chiew |
title |
WiFi-based human activity recognition through wall using deep learning |
title_short |
WiFi-based human activity recognition through wall using deep learning |
title_full |
WiFi-based human activity recognition through wall using deep learning |
title_fullStr |
WiFi-based human activity recognition through wall using deep learning |
title_full_unstemmed |
WiFi-based human activity recognition through wall using deep learning |
title_sort |
wifi-based human activity recognition through wall using deep learning |
publisher |
Elsevier Ltd |
publishDate |
2023 |
url |
http://eprints.utem.edu.my/id/eprint/27352/2/0129821122023563.PDF http://eprints.utem.edu.my/id/eprint/27352/ https://pdf.sciencedirectassets.com/271095/1-s2.0-S0952197623X00141/1-s2.0-S0952197623013556/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjELz%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJHMEUCIFMFCAt6c6bFptik7HhFyQByTpcMFEcyfemwzfwt9h2iAiEAloaIFuiOvWhX8BLmtnLdnP3ijV885PSYXYBMs56vcbcqswUIJRAFGgwwNTkwMDM1NDY4NjUiDOTr3CrkovPqEx3NPCqQBWwASmUDJsYXpilpy05oL64qcJLG%2B%2FHqhZ7o4gr8JJVsy7jTtADNJagWiGgARgpn5G%2FlVOiUBtJQ9rha6TjdAG3uQV9P74mubclKPYuehCcfWlA0BSAdg3f%2BQZ8T6GZUq8o8U1DVBKjDWOtUE%2FAZnce13ryNt7r%2FzvaI8GpHtuSkOdNKz6aPGQir4ThEtVVQhOGFiM4chMRsecx8MJbmBritBedYQlJNSrsS2QTIOh2C7xSIrMkrRWfCkTElS%2FiyY26Q4mxYWbt3PBsmLGZAHaelZ0bKSQ%2FDNxoej0kZ27zqH2F%2FFA%2FCsyFhuVEWH4DT%2B2Rft0lc6SBWugHBzO3B61Oeo%2BrGuk9liEf5XpCjqyVThqJkMNl2MAyW7wbHCOz%2F%2FU7e69mrKEQxS7gzh7%2FI9%2FtnivdAndOjAowwmih9jNkyjXVxXuAj%2FU3lKJuqBkVdJIlHRaeCjvGilaRtLUVQESm15ov5Oqx4uQwxnwGpqPfmBvF%2FUMquTZRi0IHQbLSM5%2FShOnGV2IisQGhWQiY0NAb0K7wEyC4On4a9mHTrNfd8SCoO5G%2BJcyBSPfw5aCeFmhN622ATO4S%2FvPRr97m0uCPDG99yhDPSNuJpzQvzBKWp0gTImPqGwXmzKESE1gLeIzgyLK%2BSNGVl%2B52%2F0jFwv9c0TIsO46o%2FeNeGgPWRjdEWI%2B3ddeWHUb9271QOq5P0XiJ3q95KEDqS1RLV96i8dO9BRZJ1v%2FERev9LFBYyh4RDpW8WRqw6hYHI%2F1oHfsnyezkhvTqulaiBjgo4l6VzFmLIP1wr%2FuNzCjMlUtvygzv%2B000KEnWFyHOR067efXwMw2E%2BbICZO%2BiTrvtX%2BnEongkvECR%2B4gyOclk9yQQs20oGMI6r9rEGOrEBwghPKkAO1lVh0CWGvKh3UVxQniTsHdvMWO%2B0g7NW%2FlyrOe3hkGVnwOB9b95ImHoL%2FW89UqT2J02%2FPzzVaSYpByuYlQRec7LILf6OKCCDb19s69JxaHoKG%2B%2Fiog1A5kHU%2BwO%2F2TELdmNhEy%2BQjDnqHHUiHSEvjdcE%2FVRT%2BzuP5fMv1YUtM4WIFt9iEheFCx31puNp%2BmXaOoiPhnH4n9rBbZZIWuo4S%2B7%2FnHX7TpARBkH9&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Date=20240510T043456Z&X-Amz-SignedHeaders=host&X-Amz-Expires=300&X-Amz-Credential=ASIAQ3PHCVTY3HAYB75A%2F20240510%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Signature=d3f4218ce244e41138e9bc355d7ca1f2d2d2f789238a10228ec9081c8bc769f2&hash=8de1ff04330b496b400ecb08d5f227e3697189a5ab5b75676bbea8a345d04857&host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&pii=S0952197623013556&tid=spdf-9e548a73-d7f4-4551-8444-28ac824b392f&sid=6f77f43140e41843e4881ae5a9c13bede762gxrqb&type=client&tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t&ua=031c575e5f595c5d57&rr=88173839f87513e0&cc=my https://doi.org/10.1016/j.engappai.2023.107171 |
_version_ |
1804070314508812288 |
spelling |
my.utem.eprints.273522024-07-04T11:16:56Z http://eprints.utem.edu.my/id/eprint/27352/ WiFi-based human activity recognition through wall using deep learning Wong, Yan Chiew Ahmed Abuhoureyah, Fahd Saad Mohd Isira, Ahmad Sadhiqin Wireless sensing is a promising method that integrates wireless mechanisms with strong sensing capabilities. The current focus of using WiFi Channel State Information (CSI) for human activity recognition (HAR) is the line-ofsight (LoS) path, which is mainly affected by human activities and is very sensitive to environmental changes. However, the signal on non-line-of-sight (nLoS) paths, particularly those passing through walls, is unpredictable due to the weak reflected signals destroyed by the wall. This work proposes a method to achieve high-accuracy wireless sensing based on CSI behavior recognition with low-cost resources by showing through-wall and widerangle predictions using WiFi signals. The technique utilizes MIMO to exploit multipath propagation and increase the capability of signal transmission and receiving antennas. The signals captured by the multi-antenna are delivered into parallel channels with different spatial signatures. An RPi 4 B is attached to an ALFA AWUS 1900 adapter utilizing Nexmon firmware monitors and extracts CSI data with flexible C-based firmware for Broadcom/ Cypress WiFi chips. Preprocessing techniques based on CSI are applied to improve the feature extraction from the amplitude data in an indoor environment. Furthermore, a deep learning algorithm based on RNN with an LSTM algorithm is used to classify the activity instances indoors, achieving up to 97.5% accuracy in classifying seven activities. The experiment shows CSI can achieve accurate wireless sensing in nLoS scenarios with extended antennas and a deep learning approach. Elsevier Ltd 2023 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/27352/2/0129821122023563.PDF Wong, Yan Chiew and Ahmed Abuhoureyah, Fahd Saad and Mohd Isira, Ahmad Sadhiqin (2023) WiFi-based human activity recognition through wall using deep learning. Engineering Applications of Artificial Intelligence, 127. pp. 1-16. ISSN 0952-1976 https://pdf.sciencedirectassets.com/271095/1-s2.0-S0952197623X00141/1-s2.0-S0952197623013556/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjELz%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJHMEUCIFMFCAt6c6bFptik7HhFyQByTpcMFEcyfemwzfwt9h2iAiEAloaIFuiOvWhX8BLmtnLdnP3ijV885PSYXYBMs56vcbcqswUIJRAFGgwwNTkwMDM1NDY4NjUiDOTr3CrkovPqEx3NPCqQBWwASmUDJsYXpilpy05oL64qcJLG%2B%2FHqhZ7o4gr8JJVsy7jTtADNJagWiGgARgpn5G%2FlVOiUBtJQ9rha6TjdAG3uQV9P74mubclKPYuehCcfWlA0BSAdg3f%2BQZ8T6GZUq8o8U1DVBKjDWOtUE%2FAZnce13ryNt7r%2FzvaI8GpHtuSkOdNKz6aPGQir4ThEtVVQhOGFiM4chMRsecx8MJbmBritBedYQlJNSrsS2QTIOh2C7xSIrMkrRWfCkTElS%2FiyY26Q4mxYWbt3PBsmLGZAHaelZ0bKSQ%2FDNxoej0kZ27zqH2F%2FFA%2FCsyFhuVEWH4DT%2B2Rft0lc6SBWugHBzO3B61Oeo%2BrGuk9liEf5XpCjqyVThqJkMNl2MAyW7wbHCOz%2F%2FU7e69mrKEQxS7gzh7%2FI9%2FtnivdAndOjAowwmih9jNkyjXVxXuAj%2FU3lKJuqBkVdJIlHRaeCjvGilaRtLUVQESm15ov5Oqx4uQwxnwGpqPfmBvF%2FUMquTZRi0IHQbLSM5%2FShOnGV2IisQGhWQiY0NAb0K7wEyC4On4a9mHTrNfd8SCoO5G%2BJcyBSPfw5aCeFmhN622ATO4S%2FvPRr97m0uCPDG99yhDPSNuJpzQvzBKWp0gTImPqGwXmzKESE1gLeIzgyLK%2BSNGVl%2B52%2F0jFwv9c0TIsO46o%2FeNeGgPWRjdEWI%2B3ddeWHUb9271QOq5P0XiJ3q95KEDqS1RLV96i8dO9BRZJ1v%2FERev9LFBYyh4RDpW8WRqw6hYHI%2F1oHfsnyezkhvTqulaiBjgo4l6VzFmLIP1wr%2FuNzCjMlUtvygzv%2B000KEnWFyHOR067efXwMw2E%2BbICZO%2BiTrvtX%2BnEongkvECR%2B4gyOclk9yQQs20oGMI6r9rEGOrEBwghPKkAO1lVh0CWGvKh3UVxQniTsHdvMWO%2B0g7NW%2FlyrOe3hkGVnwOB9b95ImHoL%2FW89UqT2J02%2FPzzVaSYpByuYlQRec7LILf6OKCCDb19s69JxaHoKG%2B%2Fiog1A5kHU%2BwO%2F2TELdmNhEy%2BQjDnqHHUiHSEvjdcE%2FVRT%2BzuP5fMv1YUtM4WIFt9iEheFCx31puNp%2BmXaOoiPhnH4n9rBbZZIWuo4S%2B7%2FnHX7TpARBkH9&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Date=20240510T043456Z&X-Amz-SignedHeaders=host&X-Amz-Expires=300&X-Amz-Credential=ASIAQ3PHCVTY3HAYB75A%2F20240510%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Signature=d3f4218ce244e41138e9bc355d7ca1f2d2d2f789238a10228ec9081c8bc769f2&hash=8de1ff04330b496b400ecb08d5f227e3697189a5ab5b75676bbea8a345d04857&host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&pii=S0952197623013556&tid=spdf-9e548a73-d7f4-4551-8444-28ac824b392f&sid=6f77f43140e41843e4881ae5a9c13bede762gxrqb&type=client&tsoh=d3d3LnNjaWVuY2VkaXJlY3QuY29t&ua=031c575e5f595c5d57&rr=88173839f87513e0&cc=my https://doi.org/10.1016/j.engappai.2023.107171 |
score |
13.1944895 |