利用毫米波（mmWave）頻率調變連續波（FMCW）雷達準確估測生命徵象，能夠在未來提供方便可靠的健康監測。非接觸式的生命徵象測量系統無需連接任何感測器到身體，不僅更加舒適、便利，還能避免感染病透過接觸式儀器傳播的風險。本文提出完整的非接觸式生命徵象估測方案，使用毫米波FMCW雷達來估計人體呼吸與心跳頻率。所提出之zDAWS（Zoom FFT-Enhanced Deep Learning-Aided Weighted Scheme）基於資料融合的概念結合多條 range bin的頻率結果來提高估計準確度，並利用卷積神經網路（CNN）模型提取隱藏資訊以產生合適的權重來進行資料融合，同時引入ZFFT將可用的range bin數量大幅提升，增強了資料融合的效果與模型的訓練資料。此外，提出輕量化的CNN模型架構來避免資料量提升所帶來的參數量過高的問題。實驗結果顯示，相較於傳統方法及其他方案，zDAWS在呼吸與心跳頻率的估測方面具有最好的準確度，且所提出的CNN模型有效解決了引入ZFFT後所造成之計算複雜度與訓練時間過高的問題，證實了所提出方案的價值與潛力。

The accurate estimation of vital signs using millimeter-wave (mmWave) frequency-modulated continuous wave (FMCW) radar promises a future of enhanced health monitoring with superior convenience and reliability. The non-contact vital sign measurement system elim-inates the need for connecting any sensors to the body, offering not only increased comfort and convenience but also mitigating the risk of infection transmission associated with contact-based devices. This paper proposes a vital signs monitoring scheme utilizing millimeter-wave FMCW radar to estimate breathing and heartbeat rates. The introduced scheme, named Zoom FFT-Enhanced Deep Learning-Aided Weighted Scheme (zDAWS), employs the concept of data fusion, combining estimated frequencies from multiple range bins to enhance estimation accu-racy. It extracts hidden information and generates appropriate weights for data fusion using a Convolutional Neural Network (CNN) model. We use Zoom FFT to significantly increase the number of available range bins, thereby enhancing the effectiveness of data fusion. Further-more, a lightweight CNN model architecture is proposed to address the issue of excessive pa-rameterization resulting from increased data size. Experimental results show that the proposed scheme achieves satisfactory performance. Compared to conventional methods and alternative approaches, zDAWS achieves superior accuracy in estimating breathing and heartbeat rates.

[1] S. B. Baker, W. Xiang, and I. Atkinson, “Internet of Things for smart healthcare: Tech-nologies, challenges, and opportunities,” IEEE Access, vol. 5, pp. 26521–26544, 2017.
[2] M. A. Cretikos, R. Bellomo, K. Hillman, J. Chen, S. Finfer, and A. Flabouris, “Respirato-ry rate: The neglected vital sign,” Med. J. Austral., vol. 188, no. 11, pp. 657–659, 2008.
[3] A. Zaza, C. Ronchi, and G. Malfatto, “Arrhythmias and heart rate: Mechanisms and sig-nificance of a relationship,” Arrhythmia Electrophysiol Rev., vol. 7, no. 4, pp. 232–237, Dec. 2018.
[4] Q. -V. Nguyen, R. Le Page, J. -M. Goujon, P. Guyader and M. Billon, “Pulse rate analysis in case of central sleep apnea: A new algorithm for cardiac rate estimation,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., 2009, pp. 5490-5493.
[5] G. Cinel, E. A. Tarim, and H. C. Tekin, “Wearable respiratory rate sensor technology for diagnosis of sleep apnea,” in Proc. Med. Technol. Congr. (TIPTEKNO), 2020, pp. 1–4.
[6] P. H. Charlton, D. A. Birrenkott, T. Bonnici, and M. A. F. Pimentel, “Breathing rate esti-mation from the electrocardiogram and photoplethysmogram: A review,” IEEE Rev. Bio-med. Eng., vol. 11, pp. 2–20, 2018.
[7] C. Orphanidou, “Derivation of respiration rate from ambulatory ECG and PPG using en-semble empirical mode decomposition: Comparison and fusion,” Comput. Biol. Med., vol. 81, pp. 45–54, Feb. 2017.
[8] H. Liu, J. Allen, D. Zheng, and F. Chen, “Recent development of respiratory rate meas-urement technologies,” Physiolog. Meas., vol. 40, no. 7, 2019, Art. no. 07TR01.
[9] J. Parák and J. Havlík, “ECG signal processing and heart rate frequency detection meth-ods,” Proc. Tech. Comput. Prague, vol. 8, Mar. 2011.
[10] Q. Zhang, X. Zeng, W. Hu, and D. Zhou, “A machine learning-empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with Ear-ECG/PPG,” IEEE Access, vol. 5, pp. 10547–10561, 2017.
[11] Y. Yang, H. Wang, R. Jiang, X. Guo, J. Cheng, and Y. Chen, “A review of IoT-enabled mobile healthcare: Technologies, challenges, and future trends,” IEEE Internet Things J., vol. 9, no. 12, pp. 9478–9502, Jun. 2022.
[12] M. Nouman, S. Y. Khoo, M. A. P. Mahmud, and A. Z. Kouzani, ‘‘Recent advances in contactless sensing technologies for mental health monitoring,’’ IEEE Internet Things J., vol. 9, no. 1, pp. 274–297, Jan. 2022.
[13] G. Paterniani, D. Sgreccia, A. Davoli, G. Guerzoni, P. Di Viesti, A. C. Valenti, M. Vitolo, G. M. Vitetta, and G. Boriani, “Radar-based monitoring of vital signs: A tutorial over-view,” Proceedings of the IEEE, vol. 111, no. 3, pp. 277–317, 2023.
[14] F. Wang, X. Zeng, C. Wu, B. Wang, and K. J. R. Liu, “Driver vital signs monitoring us-ing millimeter wave radio,” IEEE Internet Things J., vol. 9, no. 13, pp. 11283–11298, Jul. 2022.
[15] D. Zhang, Y. Hu, and Y. Chen, “MTrack: Tracking multiperson moving trajectories and vital signs with radio signals,” IEEE Internet Things J., vol. 8, no. 5, pp. 3904–3914, Mar. 2021.
[16] J. Qiu, P. Zheng, K. Chi, R. Xu, and J. Liu, “Respiration monitoring in high-dynamic en-vironments via combining multiple WiFi channels based on wire direct connection be-tween RX/TX,” IEEE Internet Things J., vol. 10, no. 2, pp. 1558–1573, Jan. 2023.
[17] . N. Bao, J. Du, C. Wu, D. Hong, J. Chen, R. Nowak, and Z. Lv, “Wi-breath: A WiFi-based contactless and real-time respiration monitoring scheme for remote healthcare,” IEEE J. Biomed. Health Informat., vol. 27, no. 5, pp. 2276–2285, May 2023.
[18] S. Shi, Y. Xie, M. Li, A. X. Liu, and J. Zhao, “Synthesizing wider WiFi bandwidth for respiration rate monitoring in dynamic environments,” in Proc. IEEE Conf. Comput. Commun. (INFOCOM), 2019, pp. 181–189.
[19] C. Chen, Y. Han, Y. Chen, and K. J. R. Liu, “Multi-person breathing rate estimation using time-reversal on WiFi platforms,” in Proc. IEEE Global Conf. Signal Inf. Process. (Glob-alSIP), 2016, pp. 1059–1063.
[20] Q. Gao, J. Tong, J. Wang, Z. Ran, and M. Pan, “Device-free multiperson respiration mon-itoring using WiFi,” IEEE Trans. Veh. Technol., vol. 69, no. 11, pp. 14083–14087, Nov. 2020.
[21] X. Liu, J. Cao, S. Tang, J. Wen, and P. Guo, “Contactless respiration monitoring via off-the-shelf WiFi devices,” IEEE Trans. Mobile Comput., vol. 15, no. 10, pp. 2466–2479, Oct. 2016.
[22] T. Kanda, T. Sato, H. Awano, S. Kondo, and K. Yamamoto, ‘‘Respiratory rate estimation based on WiFi frame capture,’’ in Proc. IEEE 19th Annu. Consum. Commun. Netw. Conf. (CCNC), Jan. 2022, pp. 881–884.
[23] C. He, J. Tan, X. Jian, G. Zhong, L. Cheng, and J. Lin, “A smart flexible vital signs and sleep monitoring belt based on MEMS triaxial accelerometer and pressure sensor,” IEEE Internet Things J., vol. 9, no. 15, pp. 14126–14136, Aug. 2022.
[24] F. Wang, F. Zhang, C. Wu, B. Wang, and K. J. R. Liu, “ViMo: Multiperson vital sign monitoring using commodity millimeter-wave radio,” IEEE Internet Things J., vol. 8, no. 3, pp. 1294–1307, Feb. 2021.
[25] A. Bin Obadi, P. J. Soh, O. Aldayel, M. H. Al-Doori, M. Mercuri, and D. Schreurs, “A survey on vital signs detection using radar techniques and processing with FPGA imple-mentation,” IEEE Circuits Syst. Mag., vol. 21, no. 1, pp. 41–74, 1st Quart., 2021.
[26] A. Ahmad, J. C. Roh, D. Wang, and A. Dubey, “Vital signs monitoring of multiple people using a FMCW millimeter-wave sensor,” in Proc. IEEE Radar Conf., Apr. 2018, pp. 1450–1455.
[27] E. Antide, M. Zarudniev, O. Michel, and M. Pelissier, “Comparative study of radar archi-tectures for human vital signs measurement,” in Proc. IEEE Radar Conf. (RadarConf), Sep. 2020, pp. 1–6.
[28] G. Wang, J.-M. Munoz-Ferreras, C. Gu, C. Li, and R. Gomez-Garcia, “Application of linear-frequency-modulated continuous-wave (LFMCW) radars for tracking of vital signs,” IEEE Trans. Microw. Theory Techn., vol. 62, no. 6, pp. 1387–1399, Jun. 2014.
[29] G. Sacco, E. Piuzzi, E. Pittella, and S. Pisa, “An FMCW radar for localization and vital signs measurement for different chest orientations,” Sensors, vol. 20, no. 12, pp. 1–4, Jun. 2020.
[30] H.-I. Choi, H. Song, and H.-C. Shin, “Target range selection of FMCW radar for accurate vital information extraction,” IEEE Access, vol. 9, pp. 1261–1270, 2021.
[31] Y. Hu and T. Toda, “Remote vital signs measurement of indoor walking persons using mm-Wave FMCW radar,” IEEE Access, vol. 10, pp. 78219–78230, 2022.
[32] Q. Wu, Z. Mei, Z. Lai, D. Li, and D. Zhao, “A non-contact vital signs detection in a multi-channel 77 GHz LFMCW radar system,” IEEE Access, vol. 9, pp. 49614–49628, 2021.
[33] L. Qu, C. Liu, T. Yang and Y. Sun, “Vital sign detection of FMCW radar based on im-proved adaptive parameter variational mode decomposition,” in IEEE Sensors Journal, vol. 23, no. 20, pp. 25048–25060, Oct. 2023.
[34] H. -Y. Chang, C. -H. Hsu and W. -H. Chung, “Fast acquisition and accurate vital sign es-timation with deep learning-aided weighted scheme using FMCW radar,” in Proc. IEEE 95th Veh. Technol. Conf. (VTC-Spring), Jun. 2022, pp. 1–6.
[35] S. Salman and X. Liu, “Overfitting mechanism and avoidance in deep neural networks,” 2019, arXiv:1901.06566.
[36] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014.
[37] A. Shrestha and A. Mahmood, “Review of deep learning algorithms and architectures,” IEEE Access, vol. 7, pp. 53040–53065, 2019.
[38] M Mercuri et al., “Enabling robust radar-based localization and vital signs monitoring in multipath propagation environments,” IEEE Trans. Biomed. Eng., vol. 68, no. 11, pp. 3228–3240, Nov. 2021.
[39] B. Mamandipoor, D. Ramasamy, and U. Madhow, “Newtonized orthogonal matching pursuit: Frequency estimation over the continuum,” IEEE Trans. Signal Process., vol. 64, no. 19, pp. 5066–5081, Oct. 2016.
[40] P. C. Y. Yip, “Some aspects of the zoom transform,” IEEE Trans. Comput., vol. C–25, no. 3, pp. 287–296, 1976.
[41] E. Hoyer and R. Stork, “The zoom FFT using complex modulation,” in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), vol. 2, May 1977, pp. 78–81.
[42] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
[43] M. M. Najafabadi, F. Villanustre, T. M. Khoshgoftaar, N. Seliya, R. Wald, and E. Mu-haremagic, “Deep learning applications and challenges in big data analytics,” J. Big Data, vol. 2, no. 1, pp. 1–21, 2015.
[44] A. Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, ‘‘Deep learning for computer vision: A brief review,’’ Comput. Intell. Neurosci., vol. 2018, pp. 1–13, Feb. 2018.
[45] Z.-Q. Zhao, P. Zheng, S.-T. Xu, and X. Wu, ‘‘Object detection with deep learning: A re-view,’’ IEEE Trans. Neural Netw. Learn. Syst., vol. 30, no. 11, pp. 3212–3232, Nov. 2019.
[46] M. D. Zeiler, D. Krishnan, G. W. Taylor, and R. Fergus, “Deconvolutional networks,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., Jun. 2010, pp. 2528–2535.
[47] D. W. Otter, J. R. Medina, and J. K. Kalita, “A survey of the usages of deep learning for natural language processing,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 2, pp. 604–624, Feb. 2021.
[48] S. V. Balkus, H. Wang, B. D. Cornet, C. Mahabal, H. Ngo, and H. Fang, ‘‘A survey of collaborative machine learning using 5G vehicular communications,’’ IEEE Commun. Surveys Tuts., vol. 24, no. 2, pp. 1280–1303, 2022.
[49] N. C. Luong et al., “Applications of Deep Reinforcement Learning in Communications and Networking: A Survey,” IEEE Commun. Surveys Tuts., vol. 21, no. 4, pp. 3133–3174, Oct. 2019.
[50] C. Zhang, P. Patras and H. Haddadi, “Deep learning in mobile and wireless networking: A survey,” IEEE Commun. Surveys Tuts., vol. 21, no. 3, pp. 2224-2287, Mar. 2019.
[51] S. Sun, Z. Cao, H. Zhu, and J. Zhao, “A survey of optimization methods from a machine learning perspective,” IEEE Trans. Cybern., vol. 50, no. 8, pp. 3668–3681, Aug. 2020.
[52] AWR1642 Single-Chip 76-GHz to 81-GHz Automotive Radar Sensor Evaluation Module | TI.com. [Online]. Available: https://www.ti.com/tool/AWR1642BOOST
[53] DCA1000EVM Real-time data-capture adapter for radar sensing evaluation module Mod-ule | TI.com. [Online]. Available: https://www.ti.com/tool/DCA1000EVM?keyMatch=&-tisearch=searcheverything&usecase=hardware
[54] Go Direct® Respiration Belt [Online]. Available: https://www.vernier.com/product/go-direct-respiration-belt/
[55] ACARE AE-XX Pulse Oximeter [Online]. Available: https://www.acaretech.com/product_872346.html
[56] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. Int. Conf. Learn. Representations, 2015, pp. 1–15.
[57] S. Ruder, “An overview of gradient descent optimization algorithms,” 2016. arXiv: 1609.04747.