Deep learning in WiFi CSI-based human activity recognition
As one of the most common signals in people’s daily life, WiFi signal is widely used in human activity recognition tasks in recent years. Unlike visionbased human action recognition methods, WiFi-based methods are able to recognize occluded human actions due to the penetration and reflection nature...
| Hovedforfatter: | |
|---|---|
| Andre forfattere: | |
| Format: | Thesis-Master by Coursework |
| Sprog: | English |
| Udgivet: |
Nanyang Technological University
2022
|
| Fag: | |
| Online adgang: | https://hdl.handle.net/10356/155027 |
| _version_ | 1826123512110120960 |
|---|---|
| author | Li, Shuai |
| author2 | Alex Chichung Kot |
| author_facet | Alex Chichung Kot Li, Shuai |
| author_sort | Li, Shuai |
| collection | NTU |
| description | As one of the most common signals in people’s daily life, WiFi signal is widely used in human activity recognition tasks in recent years. Unlike visionbased human action recognition methods, WiFi-based methods are able to recognize occluded human actions due to the penetration and reflection nature of
WiFi signal. Despite of the advantage of WiFi signal, there is still a lack of public datasets which consider occlusion in human action comprehensively. Hence, we construct a WiFi-based CSI human activity recognition dataset with commodity WiFi devices. The dataset contains ten classes of actions and three
different occlusion scenarios. Based on the proposed dataset, we evaluate the accuracy and robustness of the state-of-the-art WiFi-based deep learning models. Furthermore, we examine the impact of occlusion on WiFi-based human activity recognition and find that the occlusion is a significant factor in improving the
diversity of the dataset. |
| first_indexed | 2024-10-01T06:05:53Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/155027 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:05:53Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1550272023-07-04T16:13:28Z Deep learning in WiFi CSI-based human activity recognition Li, Shuai Alex Chichung Kot School of Electrical and Electronic Engineering Rapid-Rich Object Search (ROSE) Lab EACKOT@ntu.edu.sg Engineering::Electrical and electronic engineering::Wireless communication systems Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence As one of the most common signals in people’s daily life, WiFi signal is widely used in human activity recognition tasks in recent years. Unlike visionbased human action recognition methods, WiFi-based methods are able to recognize occluded human actions due to the penetration and reflection nature of WiFi signal. Despite of the advantage of WiFi signal, there is still a lack of public datasets which consider occlusion in human action comprehensively. Hence, we construct a WiFi-based CSI human activity recognition dataset with commodity WiFi devices. The dataset contains ten classes of actions and three different occlusion scenarios. Based on the proposed dataset, we evaluate the accuracy and robustness of the state-of-the-art WiFi-based deep learning models. Furthermore, we examine the impact of occlusion on WiFi-based human activity recognition and find that the occlusion is a significant factor in improving the diversity of the dataset. Master of Science (Signal Processing) 2022-02-04T07:54:56Z 2022-02-04T07:54:56Z 2021 Thesis-Master by Coursework Li, S. (2021). Deep learning in WiFi CSI-based human activity recognition. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/155027 https://hdl.handle.net/10356/155027 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering::Wireless communication systems Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Li, Shuai Deep learning in WiFi CSI-based human activity recognition |
| title | Deep learning in WiFi CSI-based human activity recognition |
| title_full | Deep learning in WiFi CSI-based human activity recognition |
| title_fullStr | Deep learning in WiFi CSI-based human activity recognition |
| title_full_unstemmed | Deep learning in WiFi CSI-based human activity recognition |
| title_short | Deep learning in WiFi CSI-based human activity recognition |
| title_sort | deep learning in wifi csi based human activity recognition |
| topic | Engineering::Electrical and electronic engineering::Wireless communication systems Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/155027 |
| work_keys_str_mv | AT lishuai deeplearninginwificsibasedhumanactivityrecognition |