Fall Detection Based on Continuous Wave Radar Sensor Using Binarized Neural Networks
Source abstract
Abstract
Accidents caused by falls among the elderly have become a significant social issue, making fall detection systems increasingly needed. Fall detection systems such as internet of things (IoT) devices must be affordable and compact because they must be installed in various locations around the house, such as bedrooms, living rooms, and bathrooms. In this study, we propose a lightweight fall detection method using a continuous-wave (CW) radar sensor and a binarized neural network (BNN) to meet these requirements. We used a CW radar sensor, which is more affordable than other types of radar sensors, and employed a BNN with binarized features and parameters to reduce memory usage and make the system lighter. The proposed method distinguishes movements using micro-Doppler signatures, and spectrogram is binarized as an input to the BNN. The proposed method achieved 93.1% accuracy in binary classification of five fall actions and six non-fall actions. The memory requirements for storing parameters were reduced to 11.9 KB, representing a reduction of up to 99.9% compared with previous studies.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Non-Invasive Vital Sign Monitoring · Gait Recognition and Analysis · Advanced SAR Imaging Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronics and Information Engineering, Korea Aerospace University, Goyang 10540, Republic of Korea
Department of Smart Air Mobility, Korea Aerospace University, Goyang 10540, Republic of Korea
Department of Electrical Engineering, Sejong University, Seoul 05006, Republic of Korea
Department of Convergence Engineering of Intelligent Drone, Sejong University, Seoul 05006, Republic of Korea
Funding
MSIT (Ministry of Science and ICT) · MOTIE (Ministry of Trade, Industry, and Energy) · IDEC
References (23)
Show source-provided references
1. Low-power fall detector using triaxial accelerometry and barometric pressure sensing10.1109/TII.2016.2587761 ↗
2. A Patient-Specific Single Sensor IoT-Based Wearable Fall Prediction and Detection System10.1109/TNSRE.2019.2911602 ↗
3. Development of an enhanced threshold-based fall detection system using smartphones with built-in accelerometers10.1109/JSEN.2019.2918690 ↗
4. An integrated vision-based approach for efficient human fall detection in a home environment10.1109/ACCESS.2019.2936320 ↗
5. Deep convolutional neural networks for human action recognition using depth maps and postures10.1109/TSMC.2018.2850149 ↗
6. A posture recognition-based fall detection system for monitoring an elderly person in a smart home environment10.1109/TITB.2012.2214786 ↗
7. A Machine Learning Approach for Fall Detection Based on the Instantaneous Doppler Frequency10.1109/ACCESS.2019.2947739 ↗
8. Fall detection utilizing frequency distribution trajectory by microwave Doppler sensor10.1109/JSEN.2017.2760911 ↗
9. Effective fall detection and post-fall breath rate tracking using a low-cost CW Doppler radar sensor
10. Tewari, R.C., Routray, A., and Maiti, J. (2023, January 14–17). Enhanced Robustness in Low-Cost Doppler Radar Based Fall Detection System via Kalman Filter Tracking and Transition Activity Analysis. Proceedings of the 2023 IEEE 20th India Council International Conference (INDICON), Hyderabad, India.10.1109/INDICON59947.2023.10440756 ↗
11. Design of a Multistage Radar-Based Human Fall Detection System10.1109/JSEN.2022.3177173 ↗
12. Yoshino, H., Moshnyaga, V.G., and Hashimoto, K.J.I. (2019, January 6–9). Fall Detection on a single Doppler Radar Sensor by using Convolutional Neural Networks. Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy.10.1109/SMC.2019.8914303 ↗
13. Li, Z., Du, J., Zhu, B., Greenwald, S.E., Xu, L., Yao, Y., and Bao, N. (2024). Doppler Radar Sensor-Based Fall Detection Using a Convolutional Bidirectional Long Short-Term Memory Model. Sensors, 24.10.3390/s24165365 ↗
14. Ding, C., Zou, Y., Sun, L., Hong, H., Zhu, X., and Li, C. (2019, January 19–22). Fall detection with multi-domain features by a portable FMCW radar. Proceedings of the 2019 IEEE MTT-S International Wireless Symposium (IWS), Guangzhou, China.10.1109/IEEE-IWS.2019.8804036 ↗
15. Unobtrusive Human Fall Detection System Using mmWave Radar and Data Driven Methods10.1109/JSEN.2023.3245063 ↗
16. A Millimetre-Wave Radar-Based Fall Detection Method Using Line Kernel Convolutional Neural Network10.1109/JSEN.2020.3006918 ↗
17. Sun, Y., Hang, R., Li, Z., Jin, M., and Xu, K. (2019, January 1–4). Privacy-Preserving Fall Detection with Deep Learning on mmWave Radar Signal. Proceedings of the 2019 IEEE Visual Communications and Image Processing (VCIP), Sydney, Australia.10.1109/VCIP47243.2019.8965661 ↗
18. Fall detection using standoff radar-based sensing and deep convolutional neural network
19. Contactless Fall Detection Using Time-Frequency Analysis and Convolutional Neural Networks10.1109/TII.2021.3049342 ↗
20. CapsFall: Fall detection using ultra-wideband radar and capsule network10.1109/ACCESS.2019.2907925 ↗
21. A convolution neural network approach for fall detection based on adaptive channel selection of UWB radar signals10.1007/s00521-021-06795-w ↗
22. Ma, L., Liu, M., Wang, N., Wang, L., Yang, Y., and Wang, H. (2020). Room-level fall detection based on ultra-wideband (UWB) monostatic radar and convolutional long short-term memory (LSTM). Sensors, 20.10.3390/s20041105 ↗
23. (2024, September 12). Infineon: DEMO SENSE2GOL. Available online: https://www.infineon.com/cms/en/product/evaluation-boards/demo-sense2gol/.