調頻連續波雷達 (FMCW) 可以實現對人體生理資訊 (心率及呼吸率) 的非 接觸式檢測。但是生命體徵訊號容易受到其他身體軀幹的訊號干擾，特別 在身體運動時。所以本研究旨在研究運動期間人體心率的預測。基於現 有的基於毫米波雷達計算人體運動功率方法，我們分析運動期間心率升 高和恢復的特徵模式。並基於上下文學習的 LSTM 模型學習目標物體運 動強度與心率的相依性，預測個體在運動期間的心率。考慮到健康狀況 和心率波動的個體差異，採用國際身體活動問卷得分、健康狀況分類和 靜態校準機制來微調心率預測曲線。我們收集了 75 個參與者在運動期間 的 FMCW 雷達資料集，包含兩種每日活動類型，心率範圍為 58 BPM 到 189 BPM。在提出的數據集上，我們的方法對運動心率進行預測平均絕對 誤差(MAE)為 6.95。

Frequency Modulated Continuous Wave (FMCW) radar enables non-contact detection of human physiological information. However, vital signals are susceptible to interference from other body artifacts, especially during body movements. Therefore, this study aims to research the prediction of human heart rate during exercise. Based on existing methods of radar-based de- tection of human movement power, we analyze characteristic patterns of heart rate elevation and recovery during exercise. By combining an LSTM model with target object movement intensity, we predict the heart rate of individuals during exercise. Considering individual differences in fitness and heart rate fluctuations, we adopt International Physical Activity Ques- tionnaire scores, fitness categorization, and a static calibration mechanism to fine-tune the heart rate prediction curve. We collect a dataset of RF signals from 75 individuals during exercise, involving two types of daily activities with a heart rate range of 58 BPM to 189 BPM. On the proposed dataset, our method predicts exercise heart rate with an Mean Absolute Er- ror (MAE) error of 6.95.

[1] Y.-X. Lin, D. S. Tan, W.-H. Cheng, Y.-Y. Chen, and K.-L. Hua, “Spatially-aware domain adaptation for semantic segmentation of urban scenes,” in 2019 IEEE International Conference on Image Processing (ICIP), pp. 1870–1874, IEEE, 2019.
[2] D. D. Thang, S. C. Hidayati, Y.-Y. Chen, W.-H. Cheng, S.-W. Sun, and K.-L. Hua, “A spatial-pyramid scene categorization algorithm based on locality-aware sparse coding,” in 2016 IEEE Second Inter- national Conference on Multimedia Big Data (BigMM), pp. 342–345, 2016.
[3] M. Shahid, J. J. Virtusio, Y.-H. Wu, Y.-Y. Chen, M. Tanveer, K. Muhammad, and K.-L. Hua, “Spatio- temporal self-attention network for fire detection and segmentation in video surveillance,” IEEE Ac- cess, vol. 10, pp. 1259–1275, 2022.
[4] F. S. Abousaleh, N.-H. Yu, K.-L. Hua, and W.-H. Cheng, “Medical image denoising using sparse representations,” in 2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST), pp. 422–427, 2017.
[5] T.-C. Lin, D. S. Tan, H.-L. Tang, S.-C. Chien, F.-C. Chang, Y.-Y. Chen, W.-H. Cheng, and K.-L. Hua, “Pedestrian detection from lidar data via cooperative deep and hand-crafted features,” in 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1922–1926, 2018.
[6] Y. Huang, D.-X. Wu, C.-W. You, C.-L. Yang, S.-Y. Lau, K.-L. Hua, W.-H. Cheng, Y.-L. Chen, and J. Y.-J. Hsu, “Poster: Exploring the need for sensor learning and collaboration in iot-based parking sys- tems,” in Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems, SenSys ’15, (New York, NY, USA), p. 423–424, Association for Computing Machinery, 2015.
[7] F. Wang, X. Zeng, C. Wu, B. Wang, and K. R. Liu, “mmhrv: Contactless heart rate variability monitor- ing using millimeter-wave radio,” IEEE Internet of Things Journal, vol. 8, no. 22, pp. 16623–16636, 2021.
[8] F. Wang, F. Zhang, C. Wu, B. Wang, and K. R. Liu, “Vimo: Multiperson vital sign monitoring using commodity millimeter-wave radio,” IEEE Internet of Things Journal, vol. 8, no. 3, pp. 1294–1307, 2020.
[9] Y. Wang, Y. Shui, X. Yang, Z. Li, and W. Wang, “Multi-target vital signs detection using frequency- modulated continuous wave radar,” EURASIP Journal on Advances in Signal Processing, vol. 2021, no. 1, pp. 1–19, 2021.
[10] J.-D. Lin, H.-H. Lin, J. Dy, J.-C. Chen, M. Tanveer, I. Razzak, and K.-L. Hua, “Lightweight face anti- spoofing network for telehealth applications,” IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 5, pp. 1987–1996, 2022.
[11] X. Zhang, Y. Gu, H. Yan, Y. Wang, M. Dong, K. Ota, F. Ren, and Y. Ji, “Wital: A cots wifi de- vices based vital signs monitoring system using nlos sensing model,” IEEE Transactions on Human- Machine Systems, 2023.
[12] F. Adib, H. Mao, Z. Kabelac, D. Katabi, and R. C. Miller, “Smart homes that monitor breathing and heart rate,” in Proceedings of the 33rd annual ACM conference on human factors in computing systems, pp. 837–846, 2015.
[13] Z. Yang, P. H. Pathak, Y. Zeng, X. Liran, and P. Mohapatra, “Vital sign and sleep monitoring using millimeter wave,” ACM Transactions on Sensor Networks (TOSN), vol. 13, no. 2, pp. 1–32, 2017.
[14] S.-W. Sun, T.-C. Mou, F. Chih-Chieh, P.-C. Chang, K.-L. Hua, and H.-c. Shih, “Baseball player behav- ior classification system using long short-term memory with multimodal features,” Sensors (Switzer- land), vol. 19, 03 2019.
[15] S. Z. Gurbuz, M. M. Rahman, E. Kurtoglu, T. Macks, and F. Fioranelli, “Cross-frequency training with adversarial learning for radar micro-doppler signature classification (rising researcher),” in Radar Sensor Technology XXIV, vol. 11408, pp. 58–68, SPIE, 2020.
[16] V. C. Chen, F. Li, S.-S. Ho, and H. Wechsler, “Micro-doppler effect in radar: phenomenon, model, and simulation study,” IEEE Transactions on Aerospace and electronic systems, vol. 42, no. 1, pp. 2–21, 2006.
[17] Z. Chen, T. Zheng, C. Cai, and J. Luo, “Movi-fi: Motion-robust vital signs waveform recovery via deep interpreted rf sensing,” in Proceedings of the 27th annual international conference on mobile computing and networking, pp. 392–405, 2021.
[18] U. Ha, S. Assana, and F. Adib, “Contactless seismocardiography via deep learning radars,” in Pro- ceedings of the 26th annual international conference on mobile computing and networking, pp. 1–14, 2020.
[19] T. Zheng, Z. Chen, S. Zhang, C. Cai, and J. Luo, “More-fi: Motion-robust and fine-grained respiration monitoring via deep-learning uwb radar,” in Proceedings of the 19th ACM conference on embedded networked sensor systems, pp. 111–124, 2021.
[20] J. Gong, X. Zhang, K. Lin, J. Ren, Y. Zhang, and W. Qiu, “Rf vital sign sensing under free body movement,” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 5, no. 3, pp. 1–22, 2021.
[21] “Ipaq short form 2023. taiwan hpa website, https://www.hpa.gov.tw/pages/detail.aspx?nodeid=876 pid=4900,” 2023.
[22] H. Cheng, “A simple, easy-to-use spreadsheet for automatic scoring of the international physical ac- tivity questionnaire (ipaq) short form,” ResearchGate, 2016.
[23] K. Schwarz, M. Sideris, and R. Forsberg, “The use of fft techniques in physical geodesy,” Geophysical Journal International, vol. 100, no. 3, pp. 485–514, 1990.
[24] Y. Rong, A. Dutta, A. Chiriyath, and D. W. Bliss, “Motion-tolerant non-contact heart-rate measure- ments from radar sensor fusion,” Sensors, vol. 21, no. 5, p. 1774, 2021.
[25] J.-M. Muñoz-Ferreras, Z. Peng, R. Gómez-García, and C. Li, “Random body movement mitigation for fmcw-radar-based vital-sign monitoring,” in 2016 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems (BioWireleSS), pp. 22–24, IEEE, 2016.
[26] S. Iyer, L. Zhao, M. P. Mohan, J. Jimeno, M. Y. Siyal, A. Alphones, and M. F. Karim, “mm-wave radar- based vital signs monitoring and arrhythmia detection using machine learning,” Sensors, vol. 22, no. 9, p. 3106, 2022.
[27] Z.-K. Yang, H. Shi, S. Zhao, and X.-D. Huang, “Vital sign detection during large-scale and fast body movements based on an adaptive noise cancellation algorithm using a single doppler radar sensor,” Sensors, vol. 20, no. 15, p. 4183, 2020.
[28] T. Zheng, Z. Chen, C. Cai, J. Luo, and X. Zhang, “V2ifi: In-vehicle vital sign monitoring via compact rf sensing,” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 4, no. 2, pp. 1–27, 2020.
[29] G. Mauro, M. De Carlos Diez, J. Ott, L. Servadei, M. P. Cuellar, and D. P. Morales-Santos, “Few-shot user-adaptable radar-based breath signal sensing,” Sensors, vol. 23, no. 2, p. 804, 2023.
[30] B. Zhang, B. Jiang, R. Zheng, X. Zhang, J. Li, and Q. Xu, “Pi-vimo: Physiology-inspired robust vital sign monitoring using mmwave radars,” ACM Transactions on Internet of Things, vol. 4, no. 2, pp. 1–27, 2023.
[31] Z. Wang, B. Jin, S. Li, F. Zhang, and W. Zhang, “Ecg-grained cardiac monitoring using uwb signals,” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 6, no. 4, pp. 1–25, 2023.
[32] J. Ni, L. Muhlstein, and J. McAuley, “Modeling heart rate and activity data for personalized fitness recommendation,” in The World Wide Web Conference, pp. 1343–1353, 2019.
[33] Y. Yu, X. Si, C. Hu, and J. Zhang, “A review of recurrent neural networks: Lstm cells and network architectures,” Neural Computation, vol. 31, no. 7, pp. 1235–1270, 2019.
[34] K.-L. Hua, S. Hidayati, F.-L. He, C.-P. Wei, and Y.-C. F. Wang, “Context-aware joint dictionary learn- ing for color image demosaicking,” Journal of Visual Communication and Image Representation, vol. 38, 03 2016.
[35] A. Talavera, D. S. Tan, A. Azcarraga, and K.-L. Hua, “Layout and context understanding for image synthesis with scene graphs,” pp. 1905–1909, 09 2019.
[36] X. Li, S. Wu, and L. Wang, “Blood pressure prediction via recurrent models with contextual layer,” in Proceedings of the 26th International Conference on World Wide Web, pp. 685–693, 2017.
[37] C. Schneider, F. Hanakam, T. Wiewelhove, A. Döweling, M. Kellmann, T. Meyer, M. Pfeiffer, and A. Ferrauti, “Heart rate monitoring in team sports—a conceptual framework for contextualizing heart rate measures for training and recovery prescription,” Frontiers in Physiology, vol. 9, 05 2018.
[38] S. Patro and K. K. Sahu, “Normalization: A preprocessing stage,” arXiv preprint arXiv:1503.06462, 2015.
[39] R. Dey and F. M. Salem, “Gate-variants of gated recurrent unit (gru) neural networks,” in 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 1597–1600, 2017.
[40] “60ghz 3d detection model sc1220at2 webpage, https://www.socionext.com/en/products/assp/radar- sensor/sc1220/,” 2023.
[41] “2023 polar h10 website https://www.polar.com/tw-zh/products/accessories/h10,” 2023.