Learning gestures from WiFi: a Siamese recurrent convolutional architecture
We propose a gesture recognition system that leverages existing WiFi infrastructures and learns gestures from Channel State Information (CSI) measurements. Having developed an innovative OpenWrt-based platform for commercial WiFi devices to extract CSI data, we propose a novel deep Siamese represent...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162593 |
| _version_ | 1826125736611676160 |
|---|---|
| author | Yang, Jianfei Zou, Han Zhou, Yuxun Xie, Lihua |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Yang, Jianfei Zou, Han Zhou, Yuxun Xie, Lihua |
| author_sort | Yang, Jianfei |
| collection | NTU |
| description | We propose a gesture recognition system that leverages existing WiFi infrastructures and learns gestures from Channel State Information (CSI) measurements. Having developed an innovative OpenWrt-based platform for commercial WiFi devices to extract CSI data, we propose a novel deep Siamese representation learning architecture for one-shot gesture recognition. Technically, our model extends the capacity of spatio-temporal patterns learning for the standard Siamese structure by incorporating convolutional and bidirectional recurrent neural networks. More importantly, the representation learning is ameliorated by our Siamese framework and transferable pairwise loss which helps to remove structured noise such as individual heterogeneity and various measurement conditions during domain-different training. Meanwhile, our Siamese model also enables one-shot learning for higher availability in reality. We prototype our system on commercial WiFi routers. The experiments demonstrate that our model outperforms state-of-the-art solutions for temporal-spatial representation learning and achieves satisfactory results under one-shot conditions. |
| first_indexed | 2024-10-01T06:41:35Z |
| format | Journal Article |
| id | ntu-10356/162593 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:41:35Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1625932022-11-01T00:43:45Z Learning gestures from WiFi: a Siamese recurrent convolutional architecture Yang, Jianfei Zou, Han Zhou, Yuxun Xie, Lihua School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Channel State Information Gesture Recognition We propose a gesture recognition system that leverages existing WiFi infrastructures and learns gestures from Channel State Information (CSI) measurements. Having developed an innovative OpenWrt-based platform for commercial WiFi devices to extract CSI data, we propose a novel deep Siamese representation learning architecture for one-shot gesture recognition. Technically, our model extends the capacity of spatio-temporal patterns learning for the standard Siamese structure by incorporating convolutional and bidirectional recurrent neural networks. More importantly, the representation learning is ameliorated by our Siamese framework and transferable pairwise loss which helps to remove structured noise such as individual heterogeneity and various measurement conditions during domain-different training. Meanwhile, our Siamese model also enables one-shot learning for higher availability in reality. We prototype our system on commercial WiFi routers. The experiments demonstrate that our model outperforms state-of-the-art solutions for temporal-spatial representation learning and achieves satisfactory results under one-shot conditions. Ministry of Education (MOE) Submitted/Accepted version This work was supported by the Ministry of Education of Singapore MoE Tier 1 under Grant RG72/19. 2022-11-01T00:43:45Z 2022-11-01T00:43:45Z 2019 Journal Article Yang, J., Zou, H., Zhou, Y. & Xie, L. (2019). Learning gestures from WiFi: a Siamese recurrent convolutional architecture. IEEE Internet of Things Journal, 6(6), 10763-10772. https://dx.doi.org/10.1109/JIOT.2019.2941527 2327-4662 https://hdl.handle.net/10356/162593 10.1109/JIOT.2019.2941527 6 6 10763 10772 en RG72/19 IEEE Internet of Things Journal © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/JIOT.2019.2941527. application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering Channel State Information Gesture Recognition Yang, Jianfei Zou, Han Zhou, Yuxun Xie, Lihua Learning gestures from WiFi: a Siamese recurrent convolutional architecture |
| title | Learning gestures from WiFi: a Siamese recurrent convolutional architecture |
| title_full | Learning gestures from WiFi: a Siamese recurrent convolutional architecture |
| title_fullStr | Learning gestures from WiFi: a Siamese recurrent convolutional architecture |
| title_full_unstemmed | Learning gestures from WiFi: a Siamese recurrent convolutional architecture |
| title_short | Learning gestures from WiFi: a Siamese recurrent convolutional architecture |
| title_sort | learning gestures from wifi a siamese recurrent convolutional architecture |
| topic | Engineering::Electrical and electronic engineering Channel State Information Gesture Recognition |
| url | https://hdl.handle.net/10356/162593 |
| work_keys_str_mv | AT yangjianfei learninggesturesfromwifiasiameserecurrentconvolutionalarchitecture AT zouhan learninggesturesfromwifiasiameserecurrentconvolutionalarchitecture AT zhouyuxun learninggesturesfromwifiasiameserecurrentconvolutionalarchitecture AT xielihua learninggesturesfromwifiasiameserecurrentconvolutionalarchitecture |