SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar
Current methods for daily human activity classification primarily rely on optical images from cameras or wearable sensors. Despite their high detection reliability, camera-based approaches suffer from several drawbacks, such as low-light conditions, limited range, and privacy concerns. To address th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Institute of Electromagnetic Engineering and Science
2024-07-01
|
| Series: | Journal of Electromagnetic Engineering and Science |
| Subjects: | |
| Online Access: | https://jees.kr/upload/pdf/jees-2024-4-r-235.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846164395814551552 |
|---|---|
| author | NgocBinh Nguyen Van-Sang Doan MinhNghia Pham VanNhu Le |
| author_facet | NgocBinh Nguyen Van-Sang Doan MinhNghia Pham VanNhu Le |
| author_sort | NgocBinh Nguyen |
| collection | DOAJ |
| description | Current methods for daily human activity classification primarily rely on optical images from cameras or wearable sensors. Despite their high detection reliability, camera-based approaches suffer from several drawbacks, such as low-light conditions, limited range, and privacy concerns. To address these limitations, this article proposes the use of a frequency-modulated continuous wave radar sensor for activity recognition. A stacked-residual convolutional neural network (SRCNN) is introduced to classify daily human activities based on the micro- Doppler features of returned radar signals. The model employs a two-layer stacked-residual structure to reuse former features, thereby improving the classification accuracy. The model is fine-tuned with different hyperparameters to find a trade-off between classification accuracy and inference time. Evaluations are conducted through training and testing on both simulated and measured datasets. As a result, the SRCNN model with six stacked-residual blocks and 64 filters achieves the best performance, with accuracies exceeding 95% and 99% at 0 dB and 10 dB, respectively. Remarkably, the proposed model outperforms several state-of-the-art CNN models in terms of classification accuracy and execution time on the same datasets. |
| format | Article |
| id | doaj-art-2e7dfc895d9e4748a88e2a43ffa1f24c |
| institution | Kabale University |
| issn | 2671-7255 2671-7263 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | The Korean Institute of Electromagnetic Engineering and Science |
| record_format | Article |
| series | Journal of Electromagnetic Engineering and Science |
| spelling | doaj-art-2e7dfc895d9e4748a88e2a43ffa1f24c2024-11-18T07:20:00ZengThe Korean Institute of Electromagnetic Engineering and ScienceJournal of Electromagnetic Engineering and Science2671-72552671-72632024-07-0124435836910.26866/jees.2024.4.r.2353674SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW RadarNgocBinh Nguyen0Van-Sang Doan1MinhNghia Pham2VanNhu Le3 Faculty of Radio Electronics Engineering, Le Quy Don Technical University, Hanoi, Vietnam Faculty of Communication and Radar, Vietnam Naval Academy, Nha Trang, Vietnam Faculty of Radio Electronics Engineering, Le Quy Don Technical University, Hanoi, Vietnam Faculty of Radio Electronics Engineering, Le Quy Don Technical University, Hanoi, VietnamCurrent methods for daily human activity classification primarily rely on optical images from cameras or wearable sensors. Despite their high detection reliability, camera-based approaches suffer from several drawbacks, such as low-light conditions, limited range, and privacy concerns. To address these limitations, this article proposes the use of a frequency-modulated continuous wave radar sensor for activity recognition. A stacked-residual convolutional neural network (SRCNN) is introduced to classify daily human activities based on the micro- Doppler features of returned radar signals. The model employs a two-layer stacked-residual structure to reuse former features, thereby improving the classification accuracy. The model is fine-tuned with different hyperparameters to find a trade-off between classification accuracy and inference time. Evaluations are conducted through training and testing on both simulated and measured datasets. As a result, the SRCNN model with six stacked-residual blocks and 64 filters achieves the best performance, with accuracies exceeding 95% and 99% at 0 dB and 10 dB, respectively. Remarkably, the proposed model outperforms several state-of-the-art CNN models in terms of classification accuracy and execution time on the same datasets.https://jees.kr/upload/pdf/jees-2024-4-r-235.pdfhuman activity classificationmicro-doppler signatureneural networkresidual block |
| spellingShingle | NgocBinh Nguyen Van-Sang Doan MinhNghia Pham VanNhu Le SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar Journal of Electromagnetic Engineering and Science human activity classification micro-doppler signature neural network residual block |
| title | SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar |
| title_full | SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar |
| title_fullStr | SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar |
| title_full_unstemmed | SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar |
| title_short | SRCNN: Stacked-Residual Convolutional Neural Network for Improving Human Activity Classification Based on Micro-Doppler Signatures of FMCW Radar |
| title_sort | srcnn stacked residual convolutional neural network for improving human activity classification based on micro doppler signatures of fmcw radar |
| topic | human activity classification micro-doppler signature neural network residual block |
| url | https://jees.kr/upload/pdf/jees-2024-4-r-235.pdf |
| work_keys_str_mv | AT ngocbinhnguyen srcnnstackedresidualconvolutionalneuralnetworkforimprovinghumanactivityclassificationbasedonmicrodopplersignaturesoffmcwradar AT vansangdoan srcnnstackedresidualconvolutionalneuralnetworkforimprovinghumanactivityclassificationbasedonmicrodopplersignaturesoffmcwradar AT minhnghiapham srcnnstackedresidualconvolutionalneuralnetworkforimprovinghumanactivityclassificationbasedonmicrodopplersignaturesoffmcwradar AT vannhule srcnnstackedresidualconvolutionalneuralnetworkforimprovinghumanactivityclassificationbasedonmicrodopplersignaturesoffmcwradar |