遠端長期監控生命徵象已是未來生活中不可或缺的重要議題。但傳統的測量方式需要受測者穿戴裝置，造成不適感影響測量，抑或是部分病患無法碰觸這些穿戴式裝置。非接觸式的測量方式近年在新冠肺炎疫情之下更加受到矚目，且可以長時間監控病人狀況，然而量測距離的限制及訊號干擾都會影響測量的準確度。本論文選用FMCW雷達，藉電磁波訊號感測呼吸運動及心跳對身體造成的距離變化，來估計兩者的頻率，在現實情況中，人體上面有非常多反射點，且部分的訊號將散射開來，單一距離列會遺失部分訊息。本論文以資料融合的想法出發提出一個全新的觀點，利用深度學習(Deep Learning，簡稱DL)融合多條Range bin的頻率來提升估計準確度，我們將此演算法命名為DL-Aided Weighted Method (簡稱DA-WM)。
資料融合的方式以更多的資訊達到更好的準確度，並且穩定估計結果，而卷積神經網路(Convolutional neural network，簡稱CNN)對於圖片特徵具有強大的擷取能力，加上低時間複雜度的特性，使得應用在Range profile map上能以較短的處理時間達到高估計準確度。這些特點促成了DA-WM的優勢，讓我們的方法得以在更短的窗格時間內擁有相近的準確度，提供監控者呈現更即時的資訊，爭取救援時間。
最後實驗結果中，兩根天線下(一發送一接收)，使用我們提出的方法所估計的呼吸及心跳頻率和傳統方法相比有較高的正確率及穩定性，顯示DA-WM是有效提升效能的方法。

Remote vital sign monitoring is an extremely important issue for either patients or elderly people. However, conventional medical devices require attachments to patients which causes discomfort and is not suitable for some of the patients who can’t attach these devices. The outbreak of Covid-19 caused non-contact detection technology to gradually received attention. Besides avoid getting infected, it provided a way to long-term monitoring patients. In this paper, we used an FMCW radar to monitor vital signs by detecting chest vibration. In reality, there are lots of scatters spatially distributed on the thorax. These scatters extended over tens of centimeters of range depending on the incidence angle. Being inspired by the idea of data fusion, we proposed DL-Aided Weighted Method (DA-WM) to integrate frequencies from multiple range bin for better accuracy.
Data fusion attains high accuracy and increases stability while convolutional neural network (CNN) is capable of feature extraction with low time complexity. Undoubtedly, applying to range profile map is a good choice. Inheriting these characteristics, DA-WM provides high accuracy with less window time so that healthcare workers could have more time to rescue.
In our experiments, we use one antenna (one transmitter and one receiver) to show that DA-WM improves the accuracy and stability of respiration rate and heart rate, indicating that the method we proposed is completely effective.

[1] F. Khan, A. Ghaffar, N. Khan and S. H. Cho, "An overview of signal processing techniques for remote health monitoring using impulse radio UWB transceiver", Sensors, vol. 20, no. 9, 2020.
[2] L. Ren, Y. S. Koo, H. Wang, Y. Wang, Q. Liu and A. E. Fathy, "Noncontact Multiple Heartbeats Detection and Subject Localization Using UWB Impulse Doppler Radar," IEEE Microwave and Wireless Components Letters, vol. 25, no. 10, pp. 690-692, Oct. 2015.
[3] V. Nguyen, A. Q. Javaid and M. A. Weitnauer, "Harmonic Path (HAPA) algorithm for non-contact vital signs monitoring with IR-UWB radar," IEEE Biomedical Circuits and Systems Conference (BioCAS), pp. 146-149, 2013.
[4] D. R. Morgan and M. G. Zierdt, "Novel signal processing techniques for Doppler radar cardiopulmonary sensing", Signal Process., vol. 89, no. 1, pp. 45-66, Jan. 2009.
[5] M. Mercuri, Y. Liu, I. Lorato, T. Torfs, A. Bourdoux and C. Van Hoof, "Frequency-Tracking CW Doppler Radar Solving Small-Angle Approximation and Null Point Issues in Non-Contact Vital Signs Monitoring," IEEE Transactions on Biomedical Circuits and Systems, vol. 11, no. 3, pp. 671-680, June 2017.
[6] C. Li, V. M. Lubecke, O. Boric-Lubecke and J. Lin, "A Review on Recent Advances in Doppler Radar Sensors for Noncontact Healthcare Monitoring," IEEE Transactions on Microwave Theory and Techniques, vol. 61, no. 5, pp. 2046-2060, May 2013.
[7] J.M. Muñoz -Ferreras, G. Wang, C. Li, R. Gómez-García, Mitigation of stationary clutter in vital-sign-monitoring LFMCW radars, IET Radar Sonar Navig. 9 (2015) 138–144.
[8] J. -M. Muñoz-Ferreras, J. Wang, Z. Peng, C. Li and R. Gómez-García, "FMCW-Radar-Based Vital-Sign Monitoring of Multiple Patients," 2019 IEEE MTT-S International Microwave Biomedical Conference (IMBioC), pp. 1-3, 2019.
[9] A. Anghel, G. Vasile, R. Cacoveanu, C. Ioana and S. Ciochina, "Short-Range Wideband FMCW Radar for Millimetric Displacement Measurements," IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 9, pp. 5633-5642, Sept. 2014
[10] Y. Wang, W. Wang, M. Zhou, A. Ren and Z. Tian, "Remote Monitoring of Human Vital Signs Based on 77-GHz mm-Wave FMCW Radar", Sensors, vol. 20, no. 10, pp. 2999, 2020.
[11] M. Alizadeh, G. Shaker, J. C. M. D. Almeida, P. P. Morita and S. Safavi-Naeini, "Remote Monitoring of Human Vital Signs Using mm-Wave FMCW Radar," IEEE Access, vol. 7, pp. 54958-54968, 2019.
[12] E. Antide, M. Zarudniev, O. Michel and M. Pelissier, "Comparative Study of Radar Architectures for Human Vital Signs Measurement," 2020 IEEE Radar Conference (RadarConf20), pp. 1-6, 2020.
[13] 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.
[14] M. Mercuri, I. R. Lorato, Y.-H. Liu, F. Wieringa, C. Van Hoof and T. Torfs, "Vital-sign monitoring and spatial tracking of multiple people using a contactless radar-based sensor", Nature Electron., vol. 2, pp. 252-262, Jun. 2019.
[15] G. Wang, J. Muñoz-Ferreras, C. Gu, C. Li and R. Gómez-García, "Application of Linear-Frequency-Modulated Continuous-Wave (LFMCW) Radars for Tracking of Vital Signs," IEEE Transactions on Microwave Theory and Techniques, vol. 62, no. 6, pp. 1387-1399, June 2014.
[16] M. He, Y. Nian and Y. Gong, "Novel signal processing method for vital sign monitoring using FMCW radar", Biomed. Signal Process. Control, vol. 33, pp. 335-345, Mar. 2017.
[17] 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. 14, Jun. 2020.
[18] A. Ahmad, J. C. Roh, D. Wang and A. Dubey, "Vital signs monitoring of multiple people using a FMCW millimeter-wave sensor," 2018 IEEE Radar Conference (RadarConf18), pp. 1450-1455, 2018.
[19] B. Mamandipoor, D. Ramasamy and U. Madhow, "Newtonized Orthogonal Matching Pursuit: Frequency Estimation Over the Continuum," IEEE Transactions on Signal Processing, vol. 64, no. 19, pp. 5066-5081, 1 Oct.1, 2016.
[20] H. Wang, S. Li, L. Song, L. Cui and P. Wang, "An Enhanced Intelligent Diagnosis Method Based on Multi-Sensor Image Fusion via Improved Deep Learning Network," IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 6, pp. 2648-2657, June 2020.
[21] H. Chang, C. Lin, Y. Lin, W. Chung and T. Lee, "DL-Aided NOMP: a Deep Learning-Based Vital Sign Estimating Scheme Using FMCW Radar," IEEE 91st Vehicular Technology Conference (VTC2020-Spring), pp. 1-7, 2020.
[22] “Ti mmwave labs driver vital signs - developer’s guide,” 2017. [Online]. Available: https://dev.ti.com/tirex/explore/node?node=AAZ.3LdjgB9ICpyXqcY3zA__AocYeEd__LATEST
[23] AWR1642 Single-Chip 76-GHz to 81-GHz Automotive Radar Sensor Evaluation Module | TI.com. [Online]. Available: https://www.ti.com/tool/AWR1642BOOST
[24] DCA1000EVM Real-time data-capture adapter for radar sensing evaluation module Module | TI.com. [Online]. Available: https://www.ti.com/tool/DCA1000EVM?keyMatch=&tisearch=search-everything&usecase=hardware
[25] ACARE AE-XX Pulse Oximeter [Online]. Available: https://www.acaretech.com/product_872346.html
[26] Go Direct® Respiration Belt [Online]. Available: https://www.vernier.com/product/go-direct-respiration-belt/
[27] “Rossmax” Fingertip-Pulse-Oximeter
https://www.apexmedicalcorp.com/tw/Finger-Monitor-SB100-Fingertip-Pulse-Oximeter2.html
[28] Oxi – Q Finger Type Pulse Oximeter
https://www.acaretech.com/zh/product_872377.html
[29] Nissei Wrist Blood Pressure Monitor
https://www.nissei.tw/portal_c1_cnt_page.php?owner_num=c1_504337&button_num=c1&folder_id=66012&cnt_id=540931&search_field=&search_word=&search_field2=&search_word2=&search_field3=&search_word3=&bool1=&bool2=&search_type=1&up_page=1