CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal
Hand gesture is a visual input of human-computer interaction for providing different applications in smart homes, healthcare, and eldercare. Most deep learning-based techniques adopt standard convolution neural networks (CNNs) which require a large number of model parameters with high computational...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9931675/ |
| _version_ | 1817976584042184704 |
|---|---|
| author | M. Humayun Kabir Md. Ali Hasan Wonjae Shin |
| author_facet | M. Humayun Kabir Md. Ali Hasan Wonjae Shin |
| author_sort | M. Humayun Kabir |
| collection | DOAJ |
| description | Hand gesture is a visual input of human-computer interaction for providing different applications in smart homes, healthcare, and eldercare. Most deep learning-based techniques adopt standard convolution neural networks (CNNs) which require a large number of model parameters with high computational complexity; thus, it is not suitable for application in devices with limited computational resources. However, fewer model parameters can reduce the system accuracy. To address this challenge, we propose a lightweight heterogeneous deep learning-based gesture recognition system, coined CSI-DeepNet. The CSI-DeepNet comprises four steps: i) data collection, ii) data processing, iii) feature extraction, and iv) classification. We utilize a low-power system-on-chip (SoC), ESP-32, for the first time to collect alphanumeric hand gesture datasets using channel state information (CSI) with 1,800 trials of 20 gestures, including the steady-state data of ten people. A Butterworth low-pass filter with Gaussian smoothing is applied to remove noise; subsequently, the data is split into windows with sufficient dimensions in the data processing step before feeding to the model. The feature extraction section utilizes a depthwise separable convolutional neural network (DS-Conv) with a feature attention (FA) block and residual block (RB) to extract fine-grained features while reducing the complexity using fewer model parameters. Finally, the extracted refined features are classified in the classification section. The proposed system achieves an average accuracy of 96.31% with much less computational complexity, which is better than the results obtained using state-of-the-art pre-trained CNNs and two deep learning models using CSI data. |
| first_indexed | 2024-04-13T22:05:31Z |
| format | Article |
| id | doaj.art-afdd4e2453a64116b65c5ad9895a7dc3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T22:05:31Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-afdd4e2453a64116b65c5ad9895a7dc32022-12-22T02:27:58ZengIEEEIEEE Access2169-35362022-01-011011478711480110.1109/ACCESS.2022.32179109931675CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI SignalM. Humayun Kabir0Md. Ali Hasan1Wonjae Shin2https://orcid.org/0000-0001-6513-1237Department of Electrical and Computer Engineering, Ajou University, Suwon, Republic of KoreaDepartment of Electrical and Computer Engineering, Ajou University, Suwon, Republic of KoreaDepartment of Electrical and Computer Engineering, Ajou University, Suwon, Republic of KoreaHand gesture is a visual input of human-computer interaction for providing different applications in smart homes, healthcare, and eldercare. Most deep learning-based techniques adopt standard convolution neural networks (CNNs) which require a large number of model parameters with high computational complexity; thus, it is not suitable for application in devices with limited computational resources. However, fewer model parameters can reduce the system accuracy. To address this challenge, we propose a lightweight heterogeneous deep learning-based gesture recognition system, coined CSI-DeepNet. The CSI-DeepNet comprises four steps: i) data collection, ii) data processing, iii) feature extraction, and iv) classification. We utilize a low-power system-on-chip (SoC), ESP-32, for the first time to collect alphanumeric hand gesture datasets using channel state information (CSI) with 1,800 trials of 20 gestures, including the steady-state data of ten people. A Butterworth low-pass filter with Gaussian smoothing is applied to remove noise; subsequently, the data is split into windows with sufficient dimensions in the data processing step before feeding to the model. The feature extraction section utilizes a depthwise separable convolutional neural network (DS-Conv) with a feature attention (FA) block and residual block (RB) to extract fine-grained features while reducing the complexity using fewer model parameters. Finally, the extracted refined features are classified in the classification section. The proposed system achieves an average accuracy of 96.31% with much less computational complexity, which is better than the results obtained using state-of-the-art pre-trained CNNs and two deep learning models using CSI data.https://ieeexplore.ieee.org/document/9931675/Hand gesture recognitionchannel state information (CSI)deep learningdepthwise separable convolutional neural network (DS-Conv)feature attentionresidual block |
| spellingShingle | M. Humayun Kabir Md. Ali Hasan Wonjae Shin CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal IEEE Access Hand gesture recognition channel state information (CSI) deep learning depthwise separable convolutional neural network (DS-Conv) feature attention residual block |
| title | CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal |
| title_full | CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal |
| title_fullStr | CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal |
| title_full_unstemmed | CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal |
| title_short | CSI-DeepNet: A Lightweight Deep Convolutional Neural Network Based Hand Gesture Recognition System Using Wi-Fi CSI Signal |
| title_sort | csi deepnet a lightweight deep convolutional neural network based hand gesture recognition system using wi fi csi signal |
| topic | Hand gesture recognition channel state information (CSI) deep learning depthwise separable convolutional neural network (DS-Conv) feature attention residual block |
| url | https://ieeexplore.ieee.org/document/9931675/ |
| work_keys_str_mv | AT mhumayunkabir csideepnetalightweightdeepconvolutionalneuralnetworkbasedhandgesturerecognitionsystemusingwificsisignal AT mdalihasan csideepnetalightweightdeepconvolutionalneuralnetworkbasedhandgesturerecognitionsystemusingwificsisignal AT wonjaeshin csideepnetalightweightdeepconvolutionalneuralnetworkbasedhandgesturerecognitionsystemusingwificsisignal |