Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models
Abstract
:1. Introduction
2. Materials and Methods
2.1. Radar Data Acquisition System
2.2. Signal Processing
2.3. Classification Model
3. Experimental Design
4. Results and Discussion
4.1. Developed Doppler Radar System Performance
4.2. Comparative Analysis of T–F Representation Methods
4.3. Comparative Analysis of Classification Models
5. Conclusions
Author Contributions
Funding
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Elharrouss, O.; Almaadeed, N.; Al-Maadeed, S. A Review of Video Surveillance Systems. J. Vis. Commun. Image Represent. 2021, 77, 103116. [Google Scholar] [CrossRef]
- Perra, C.; Kumar, A.; Losito, M.; Pirino, P.; Moradpour, M.; Gatto, G. Monitoring Indoor People Presence in Buildings Using Low-Cost Infrared Sensor Array in Doorways. Sensors 2021, 21, 4062. [Google Scholar] [CrossRef] [PubMed]
- Bai, Y.-W.; Shen, L.-S.; Li, Z.-H. Design and Implementation of an Embedded Home Surveillance System by Use of Multiple Ultrasonic Sensors. IEEE Trans. Consum. Electron. 2010, 56, 119–124. [Google Scholar] [CrossRef]
- van Berlo, B.; Elkelany, A.; Ozcelebi, T.; Meratnia, N. Millimeter Wave Sensing: A Review of Application Pipelines and Building Blocks. IEEE Sens. J. 2021, 21, 10332–10368. [Google Scholar] [CrossRef]
- Yin, X.; Zhu, Y.; Hu, J. A Comprehensive Survey of Privacy-Preserving Federated Learning: A Taxonomy, Review, and Future Directions. ACM Comput. Surv. 2021, 54, 131:1–131:36. [Google Scholar] [CrossRef]
- Hong, S. Reduction of False Alarm Signals for PIR Sensor in Realistic Outdoor Surveillance. ETRI J. 2013, 35, 80–88. [Google Scholar] [CrossRef]
- Chuma, E.L.; Iano, Y. A Movement Detection System Using Continuous-Wave Doppler Radar Sensor and Convolutional Neural Network to Detect Cough and Other Gestures. IEEE Sens. J. 2021, 21, 2921–2928. [Google Scholar] [CrossRef]
- Ma, X.; Zhao, R.; Liu, X.; Kuang, H.; Al-qaness, M.A.A. Classification of Human Motions Using Micro-Doppler Radar in the Environments with Micro-Motion Interference. Sensors 2019, 19, 2598. [Google Scholar] [CrossRef]
- Gurbuz, S.Z.; Amin, M.G. Radar-Based Human-Motion Recognition With Deep Learning: Promising Applications for Indoor Monitoring. IEEE Signal Process. Mag. 2019, 36, 16–28. [Google Scholar] [CrossRef]
- Othman, K.A.; Rashid, N.E.A.; Abdullah, R.S.A.R.; Alnaeb, A.A. CWT Algorithm for Forward-Scatter Radar Micro-Doppler Signals Analysis. In Proceedings of the 2020 IEEE International RF and Microwave Conference (RFM), Kuala Lumpur, Malaysia, 14–16 December 2020; pp. 1–4. [Google Scholar]
- Le, H.T.; Phung, S.L.; Bouzerdoum, A. A Fast and Compact Deep Gabor Network for Micro-Doppler Signal Processing and Human Motion Classification. IEEE Sens. J. 2021, 21, 23085–23097. [Google Scholar] [CrossRef]
- Chen, V.C.; Li, F.; Ho, S.-S.; Wechsler, H. Micro-Doppler Effect in Radar: Phenomenon, Model, and Simulation Study. IEEE Trans. Aerosp. Electron. Syst. 2006, 42, 2–21. [Google Scholar] [CrossRef]
- Singh, A.K.; Kim, Y.H. Analysis of Human Kinetics Using Millimeter-Wave Micro-Doppler Radar. Procedia Comput. Sci. 2016, 84, 36–40. [Google Scholar] [CrossRef]
- Narayanan, R.M.; Zenaldin, M. Radar Micro-Doppler Signatures of Various Human Activities. IET Radar Sonar Navig. 2015, 9, 1205–1215. [Google Scholar] [CrossRef]
- Dura-Bernal, S.; Garreau, G.; Andreou, C.; Andreou, A.; Georgiou, J.; Wennekers, T.; Denham, S. Human Action Categorization Using Ultrasound Micro-Doppler Signatures. In International Workshop on Human Behavior Understanding; Salah, A.A., Lepri, B., Eds.; Springer: Berlin/Heidelberg, Germany, 2011; pp. 18–28. [Google Scholar]
- Bilik, I.; Tabrikian, J. Radar Target Classification Using Doppler Signatures of Human Locomotion Models. IEEE Trans. Aerosp. Electron. Syst. 2007, 43, 1510–1522. [Google Scholar] [CrossRef]
- Chen, V.C. The Micro-Doppler Effect in Radar, 2nd ed.; Artech House: Norwood, MA, USA, 2019; ISBN 978-1-63081-546-2. [Google Scholar]
- Belgiovane, D.; Chen, C.-C. Micro-Doppler Characteristics of Pedestrians and Bicycles for Automotive Radar Sensors at 77 GHz. In Proceedings of the 2017 11th European Conference on Antennas and Propagation (EUCAP), Paris, France, 19–24 March 2017; pp. 2912–2916. [Google Scholar]
- Balal, Y.; Balal, N.; Richter, Y.; Pinhasi, Y. Time-Frequency Spectral Signature of Limb Movements and Height Estimation Using Micro-Doppler Millimeter-Wave Radar. Sensors 2020, 20, 4660. [Google Scholar] [CrossRef]
- Buchman, D.; Drozdov, M.; Krilavičius, T.; Maskeliūnas, R.; Damaševičius, R. Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning. Sensors 2022, 22, 3456. [Google Scholar] [CrossRef]
- Ye, L.; Lan, S.; Zhang, K.; Zhang, G. EM-Sign: A Non-Contact Recognition Method Based on 24 GHz Doppler Radar for Continuous Signs and Dialogues. Electronics 2020, 9, 1577. [Google Scholar] [CrossRef]
- Kwon, J.; Kwak, N. Radar Application: Stacking Multiple Classifiers for Human Walking Detection Using Micro-Doppler Signals. Appl. Sci. 2019, 9, 3534. [Google Scholar] [CrossRef]
- Gurbuz, S.Z.; Clemente, C.; Balleri, A.; Soraghan, J.J. Micro-Doppler-Based in-Home Aided and Unaided Walking Recognition with Multiple Radar and Sonar Systems. IET Radar Sonar Navig. 2017, 11, 107–115. [Google Scholar] [CrossRef]
- Stowell, D.; Plumbley, M.D. Automatic Large-Scale Classification of Bird Sounds Is Strongly Improved by Unsupervised Feature Learning. PeerJ 2014, 2, e488. [Google Scholar] [CrossRef]
- Salamon, J.; Bello, J.P. Unsupervised Feature Learning for Urban Sound Classification. In Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia, 19–24 April 2015; pp. 171–175. [Google Scholar]
- Renuka Devi, S.M.; Sudeepini, D. Road Surface Detection Using FMCW 77GHz Automotive RADAR Using MFCC. In Proceedings of the 2021 6th International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 20–22 January 2021; pp. 794–799. [Google Scholar]
- Liu, L.; Popescu, M.; Rantz, M.; Skubic, M. Fall Detection Using Doppler Radar and Classifier Fusion. In Proceedings of the 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics, Hong Kong, 5–7 January 2012; pp. 180–183. [Google Scholar]
- IEEE Xplore. Using Doppler Radar Classify Respiration by MFCC|IEEE Conference Publication. Available online: https://ieeexplore.ieee.org/document/8955162 (accessed on 8 October 2023).
- Abdel-Hamid, O.; Mohamed, A.; Jiang, H.; Deng, L.; Penn, G.; Yu, D. Convolutional Neural Networks for Speech Recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 2014, 22, 1533–1545. [Google Scholar] [CrossRef]
- Chipengo, U.; Sligar, A.P.; Canta, S.M.; Goldgruber, M.; Leibovich, H.; Carpenter, S. High Fidelity Physics Simulation-Based Convolutional Neural Network for Automotive Radar Target Classification Using Micro-Doppler. IEEE Access 2021, 9, 82597–82617. [Google Scholar] [CrossRef]
- Jordan, T. Using Convolutional Neural Networks for Human Activity Classification on Micro-Doppler Radar Spectrograms. In Proceedings of the SPIE Defense + Security, Baltimore, MD, USA, 12 May 2016; p. 982509. [Google Scholar]
- Sadeghi Adl, Z.; Ahmad, F. Whitening-Aided Learning from Radar Micro-Doppler Signatures for Human Activity Recognition. Sensors 2023, 23, 7486. [Google Scholar] [CrossRef] [PubMed]
- Czerkawski, M.; Clemente, C.; Michie, C.; Andonovic, I.; Tachtatzis, C. Robustness of Deep Neural Networks for Micro-Doppler Radar Classification. In Proceedings of the 2022 23rd International Radar Symposium (IRS), Gdansk, Poland, 12 September 2022; pp. 480–485. [Google Scholar]
- Lai, G.; Lou, X.; Ye, W. Radar-Based Human Activity Recognition With 1-D Dense Attention Network. IEEE Geosci. Remote Sens. Lett. 2022, 19, 1–5. [Google Scholar] [CrossRef]
- Rabiner, L.; Schafer, R. Theory and Applications of Digital Speech Processing, 1st ed.; Pearson: Upper Saddle River, NJ, USA, 2010; ISBN 978-0-13-603428-5. [Google Scholar]
- McFee, B.; McVicar, M.; Faronbi, D.; Roman, I.; Gover, M.; Balke, S.; Seyfarth, S.; Malek, A.; Raffel, C.; Lostanlen, V.; et al. Librosa: Audio and Music Signal Analysis in Python. In Proceedings of the 14th Python in Science Conference, Austin, TX, USA, 6–12 July 2015; pp. 18–25. [Google Scholar] [CrossRef]
- Fu, J.; Rui, Y. Advances in Deep Learning Approaches for Image Tagging. APSIPA Trans. Signal Inf. Process. 2017, 6, e11. [Google Scholar] [CrossRef]
- Shrestha, A.; Le Kernec, J.; Fioranelli, F.; Cippitelli, E.; Gambi, E.; Spinsante, S. Feature Diversity for Fall Detection and Human Indoor Activities Classification Using Radar Systems. In Proceedings of the International Conference on Radar Systems (Radar 2017), Belfast, UK, 23–26 October 2017; pp. 1–6. [Google Scholar]
- Seyfioglu, M.S.; Erol, B.; Gurbuz, S.Z.; Amin, M.G. DNN Transfer Learning from Diversified Micro-Doppler for Motion Classification. IEEE Trans. Aerosp. Electron. Syst. 2018, 55, 2164–2180. [Google Scholar] [CrossRef]
- Tian, H.; Dong, C.; Yuan, L.; Yin, H. Motion State Classification for Micro-Drones via Modified Mel Frequency Cepstral Coefficient and Hidden Markov Mode. Electron. Lett. 2022, 58, 164–166. [Google Scholar] [CrossRef]
- Purnomo, A.T.; Lin, D.-B.; Adiprabowo, T.; Hendria, W.F. Non-Contact Monitoring and Classification of Breathing Pattern for the Supervision of People Infected by COVID-19. Sensors 2021, 21, 3172. [Google Scholar] [CrossRef]
Training Parameters | Value |
---|---|
Training set | 72% |
Validation set | 8% |
Test set | 20% |
Random shuffle | Yes |
Number of Epoch | 200 |
Batch size | 32 |
Initial learning rate | 1 × 10−4 |
Optimizer | Adam |
No. | Method | Accuracy | Precision | F1-Score | Recall | AUC |
---|---|---|---|---|---|---|
1 | ann_model_mel | 88.29 | 0.8903 | 0.8903 | 0.8904 | 0.9429 |
2 | cnn2d_model_mel | 89.27 | 0.9006 | 0.8991 | 0.8987 | 0.9567 |
3 | cnn1d_model_mel | 90.61 | 0.9129 | 0.9121 | 0.9128 | 0.9566 |
4 | ann_model_stft | 94.88 | 0.9514 | 0.9516 | 0.9519 | 0.9884 |
5 | ann_model_mfcc | 95.12 | 0.9598 | 0.9539 | 0.9526 | 0.9971 |
6 | cnn1d_model_stft | 96.22 | 0.9650 | 0.9641 | 0.9634 | 0.9931 |
7 | cnn2d_model_stft | 97.20 | 0.9750 | 0.9736 | 0.9731 | 0.9964 |
8 | cnn1d_model_mfcc | 97.44 | 0.9760 | 0.9760 | 0.9764 | 0.9979 |
9 | cnn2d_model_mfcc | 97.93 | 0.9807 | 0.9805 | 0.9802 | 0.9979 |
Classification Method | Signal Representation Method | Accuracy | Categories | |
---|---|---|---|---|
[8] | Bagged Trees | S-method | 97.30% | Walking motions |
[38] | SVM | STFT | 94.00% | Human activities |
[21] | CNN | CEMD | 96.32% | Hand sign language |
[39] | DivNet | STFT | 97.00% | Human activities |
[40] | Hidden Markov | MFCC | 97.00% | UAV detection |
[41] | XGBoost | MFCC | 87.38% | Breathing pattern |
Proposed system | 2DCNN | MFCC | 97.93% | Walking motions |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ha, M.-K.; Phan, T.-L.; Nguyen, D.H.H.; Quan, N.H.; Ha-Phan, N.-Q.; Ching, C.T.S.; Hieu, N.V. Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models. Sensors 2023, 23, 8743. https://doi.org/10.3390/s23218743
Ha M-K, Phan T-L, Nguyen DHH, Quan NH, Ha-Phan N-Q, Ching CTS, Hieu NV. Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models. Sensors. 2023; 23(21):8743. https://doi.org/10.3390/s23218743
Chicago/Turabian StyleHa, Minh-Khue, Thien-Luan Phan, Duc Hoang Ha Nguyen, Nguyen Hoang Quan, Ngoc-Quan Ha-Phan, Congo Tak Shing Ching, and Nguyen Van Hieu. 2023. "Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models" Sensors 23, no. 21: 8743. https://doi.org/10.3390/s23218743
APA StyleHa, M.-K., Phan, T.-L., Nguyen, D. H. H., Quan, N. H., Ha-Phan, N.-Q., Ching, C. T. S., & Hieu, N. V. (2023). Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models. Sensors, 23(21), 8743. https://doi.org/10.3390/s23218743