Sequential image deep learning-based Wi-Fi human activity recognition method
For the problems existing in most of the researches,such as weak anti-noise ability,incompatible signal size and insufficient feature extraction of deep-learning-based Wi-Fi human activity recognition,a kind of sequential image deep learning-based recognition method was proposed.Based on the idea of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2020-08-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020141/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539302643728384 |
|---|---|
| author | Qizhen ZHOU Jianchun XING Qiliang YANG Deshuai HAN |
| author_facet | Qizhen ZHOU Jianchun XING Qiliang YANG Deshuai HAN |
| author_sort | Qizhen ZHOU |
| collection | DOAJ |
| description | For the problems existing in most of the researches,such as weak anti-noise ability,incompatible signal size and insufficient feature extraction of deep-learning-based Wi-Fi human activity recognition,a kind of sequential image deep learning-based recognition method was proposed.Based on the idea of sequential image deep learning,a series of image frames were reconstructed from time-varied Wi-Fi signal to ensure the consistency of input size.In addition,a low-rank decomposition method was innovatively designed to separate low-rank activity information merged in noises.Finally,a deep model combining temporal stream and spatial stream was proposed to automatically capture the spatiotemporal features from length-varied image sequences.The proposed method was extensively tested in WiAR dataset and self collected dataset.The experimental results show the proposed method could achieve the accuracy of 0.94 and 0.96,which indicate its high-accuracy performance and robustness in pervasive environments. |
| format | Article |
| id | doaj-art-b444e763a676404ca0e2bd9430d1ec63 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2020-08-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-b444e763a676404ca0e2bd9430d1ec632025-01-14T07:19:26ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2020-08-0141435459735867Sequential image deep learning-based Wi-Fi human activity recognition methodQizhen ZHOUJianchun XINGQiliang YANGDeshuai HANFor the problems existing in most of the researches,such as weak anti-noise ability,incompatible signal size and insufficient feature extraction of deep-learning-based Wi-Fi human activity recognition,a kind of sequential image deep learning-based recognition method was proposed.Based on the idea of sequential image deep learning,a series of image frames were reconstructed from time-varied Wi-Fi signal to ensure the consistency of input size.In addition,a low-rank decomposition method was innovatively designed to separate low-rank activity information merged in noises.Finally,a deep model combining temporal stream and spatial stream was proposed to automatically capture the spatiotemporal features from length-varied image sequences.The proposed method was extensively tested in WiAR dataset and self collected dataset.The experimental results show the proposed method could achieve the accuracy of 0.94 and 0.96,which indicate its high-accuracy performance and robustness in pervasive environments.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020141/activity recognitionWi-Fi signaldeep learningimage recognitionlow-rank decomposition |
| spellingShingle | Qizhen ZHOU Jianchun XING Qiliang YANG Deshuai HAN Sequential image deep learning-based Wi-Fi human activity recognition method Tongxin xuebao activity recognition Wi-Fi signal deep learning image recognition low-rank decomposition |
| title | Sequential image deep learning-based Wi-Fi human activity recognition method |
| title_full | Sequential image deep learning-based Wi-Fi human activity recognition method |
| title_fullStr | Sequential image deep learning-based Wi-Fi human activity recognition method |
| title_full_unstemmed | Sequential image deep learning-based Wi-Fi human activity recognition method |
| title_short | Sequential image deep learning-based Wi-Fi human activity recognition method |
| title_sort | sequential image deep learning based wi fi human activity recognition method |
| topic | activity recognition Wi-Fi signal deep learning image recognition low-rank decomposition |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2020141/ |
| work_keys_str_mv | AT qizhenzhou sequentialimagedeeplearningbasedwifihumanactivityrecognitionmethod AT jianchunxing sequentialimagedeeplearningbasedwifihumanactivityrecognitionmethod AT qiliangyang sequentialimagedeeplearningbasedwifihumanactivityrecognitionmethod AT deshuaihan sequentialimagedeeplearningbasedwifihumanactivityrecognitionmethod |