WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi
The past decade has demonstrated the potential of human activity recognition (HAR) with WiFi signals owing to non-invasiveness and ubiquity. Previous research has largely concentrated on enhancing precision through sophisticated models. However, the complexity of recognition tasks has been largely n...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2612 |
| _version_ | 1797614357054488576 |
|---|---|
| author | Mingze Yang Hai Zhu Runzhe Zhu Fei Wu Ling Yin Yuncheng Yang |
| author_facet | Mingze Yang Hai Zhu Runzhe Zhu Fei Wu Ling Yin Yuncheng Yang |
| author_sort | Mingze Yang |
| collection | DOAJ |
| description | The past decade has demonstrated the potential of human activity recognition (HAR) with WiFi signals owing to non-invasiveness and ubiquity. Previous research has largely concentrated on enhancing precision through sophisticated models. However, the complexity of recognition tasks has been largely neglected. Thus, the performance of the HAR system is markedly diminished when tasked with increasing complexities, such as a larger classification number, the confusion of similar actions, and signal distortion To address this issue, we eliminated conventional convolutional and recurrent backbones and proposed WiTransformer, a novel tactic based on pure Transformers. Nevertheless, Transformer-like models are typically suited to large-scale datasets as pretraining models, according to the experience of the Vision Transformer. Therefore, we adopted the Body-coordinate Velocity Profile, a cross-domain WiFi signal feature derived from the channel state information, to reduce the threshold of the Transformers. Based on this, we propose two modified transformer architectures, united spatiotemporal Transformer (UST) and separated spatiotemporal Transformer (SST) to realize WiFi-based human gesture recognition models with task robustness. SST intuitively extracts spatial and temporal data features using two encoders, respectively. By contrast, UST can extract the same three-dimensional features with only a one-dimensional encoder, owing to its well-designed structure. We evaluated SST and UST on four designed task datasets (TDSs) with varying task complexities. The experimental results demonstrate that UST has achieved recognition accuracy of 86.16% on the most complex task dataset TDSs-22, outperforming the other popular backbones. Simultaneously, the accuracy decreases by at most 3.18% when the task complexity increases from TDSs-6 to TDSs-22, which is 0.14–0.2 times that of others. However, as predicted and analyzed, SST fails because of excessive lack of inductive bias and the limited scale of the training data. |
| first_indexed | 2024-03-11T07:10:17Z |
| format | Article |
| id | doaj.art-4a525bcd2a6644b2890164584b7e1d4d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:17Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4a525bcd2a6644b2890164584b7e1d4d2023-11-17T08:37:11ZengMDPI AGSensors1424-82202023-02-01235261210.3390/s23052612WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFiMingze Yang0Hai Zhu1Runzhe Zhu2Fei Wu3Ling Yin4Yuncheng Yang5School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201602, ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201602, ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201602, ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201602, ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201602, ChinaSchool of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201602, ChinaThe past decade has demonstrated the potential of human activity recognition (HAR) with WiFi signals owing to non-invasiveness and ubiquity. Previous research has largely concentrated on enhancing precision through sophisticated models. However, the complexity of recognition tasks has been largely neglected. Thus, the performance of the HAR system is markedly diminished when tasked with increasing complexities, such as a larger classification number, the confusion of similar actions, and signal distortion To address this issue, we eliminated conventional convolutional and recurrent backbones and proposed WiTransformer, a novel tactic based on pure Transformers. Nevertheless, Transformer-like models are typically suited to large-scale datasets as pretraining models, according to the experience of the Vision Transformer. Therefore, we adopted the Body-coordinate Velocity Profile, a cross-domain WiFi signal feature derived from the channel state information, to reduce the threshold of the Transformers. Based on this, we propose two modified transformer architectures, united spatiotemporal Transformer (UST) and separated spatiotemporal Transformer (SST) to realize WiFi-based human gesture recognition models with task robustness. SST intuitively extracts spatial and temporal data features using two encoders, respectively. By contrast, UST can extract the same three-dimensional features with only a one-dimensional encoder, owing to its well-designed structure. We evaluated SST and UST on four designed task datasets (TDSs) with varying task complexities. The experimental results demonstrate that UST has achieved recognition accuracy of 86.16% on the most complex task dataset TDSs-22, outperforming the other popular backbones. Simultaneously, the accuracy decreases by at most 3.18% when the task complexity increases from TDSs-6 to TDSs-22, which is 0.14–0.2 times that of others. However, as predicted and analyzed, SST fails because of excessive lack of inductive bias and the limited scale of the training data.https://www.mdpi.com/1424-8220/23/5/2612body-coordinate velocity profilechannel state informationhuman activity recognitiontransformerWiFi signals |
| spellingShingle | Mingze Yang Hai Zhu Runzhe Zhu Fei Wu Ling Yin Yuncheng Yang WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi Sensors body-coordinate velocity profile channel state information human activity recognition transformer WiFi signals |
| title | WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi |
| title_full | WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi |
| title_fullStr | WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi |
| title_full_unstemmed | WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi |
| title_short | WiTransformer: A Novel Robust Gesture Recognition Sensing Model with WiFi |
| title_sort | witransformer a novel robust gesture recognition sensing model with wifi |
| topic | body-coordinate velocity profile channel state information human activity recognition transformer WiFi signals |
| url | https://www.mdpi.com/1424-8220/23/5/2612 |
| work_keys_str_mv | AT mingzeyang witransformeranovelrobustgesturerecognitionsensingmodelwithwifi AT haizhu witransformeranovelrobustgesturerecognitionsensingmodelwithwifi AT runzhezhu witransformeranovelrobustgesturerecognitionsensingmodelwithwifi AT feiwu witransformeranovelrobustgesturerecognitionsensingmodelwithwifi AT lingyin witransformeranovelrobustgesturerecognitionsensingmodelwithwifi AT yunchengyang witransformeranovelrobustgesturerecognitionsensingmodelwithwifi |