本論文設計了一個利用心衝擊描記圖於車用環境下的心率偵測系統，而心衝
擊描記圖的原理是源自於心臟的收縮與舒張所引起之身體細微振動。在我們的系
統中，透過將氣囊放置在車用座椅的表面，並且經由壓阻式感測器來測量身體相
關的生理振動並轉換為電訊號。為了消除源自於汽車行駛所產生的振動雜訊，我
們透過加速計來收集垂直於地面的加速度值，作為後續雜訊消除的參考訊號。所
有的訊號會經過240 赫茲的取樣頻率轉換成數位訊號之後進行後續的訊號處
理。
我們的心率偵測系統分成三個部分: 模板擷取、雜訊消除、以及心率偵測。
首先，在汽車熄火的環境下，我們使用k-平均集群演算法來擷取個人化的心跳訊
號模板，用來作為特定受測者的心跳訊號特徵。在汽車行駛的環境下，我們使用
頻譜相減的方法來進行雜訊消除，並且使用加速計作為參考訊號。心率偵測的部
分使用模板匹配的方式來強化心跳訊號的心跳特徵，並且利用希爾伯特轉換擷取
出心跳脈衝訊號，最後使用短時間傅立葉傳換來估計心跳脈衝訊號的心率。我們
利用心電圖以及市售的心率偵測器Polar H1 作為效能評估的依據。
在心跳峰值檢測的靈敏度可以達到 80.08%，而心率偵測的平均絕對誤差為
5.19 bpm (beats-per-minute)；誤差小於10 bpm 的準確率為84.60%。

In this thesis, we design a heart rate detection system via Ballistocardiogram (BCG), which
is caused from subtle body vibrations derived from cardiac contractions and relaxation. In our
system, the body-related physiological vibrations were measured by placing an air bag on the
surface of the car seat and converted into electric signal via a piezoresistive sensor. To reduce
the noise caused by the vehicle’s motion, we used accelerometer to measure the acceleration
signal which is perpendicular to the ground. This signal would serve as a reference signal
for subsequent noise reduction. All the signals were converted to digital signals at a 240 Hz
sampling frequency for subsequent digital signal processing.
Our heart rate detection system is divided into three parts: template extraction, noise reduction,
and heart rate detection. First, in the car stopping scenario, k-means clustering algorithm
was applied to extract personalized heartbeat template that is used to characterize
the heartbeat feature of a particular subject. In the car driving scenario, spectral subtraction
was performed to reduce noise, and accelerometer was used as the noise reference signal. The
heart rate detection part used template matching to enhance the heartbeat characteristics of the
BCG signals, and used Hilbert transform to extract the pulse signal, followed by short-time
Fourier Transform to estimate heart rate. We used Electrocardiogram (ECG) and Polar H1, a
commercially available heart rate monitor, for performance evaluation.
The sensitivity of heartbeat detection can reach 80.08%, while the mean absolute error
(MAE) of heart rate detection is 5.19 beats-per-minute (bpm). The accuracy of heart rate
error that is less than 10 bpm is 84.60%.

Abstract i
1 Introduction 1
1.1 Backgrounds . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 Main Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.4 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2 Related Works 7
2.1 Different Vital Sign Monitoring Methodologies in Automotive Environments 7
2.1.1 Bioelectrical Effects . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1.2 Mechanical Effects . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.1.3 Comparsion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.2 Ballistocardiogram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.2.1 BCG Fundamental . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.2.2 Relationship between ECG and BCG . . . . . . . . . . . . . . . . . 16
2.2.3 BCG Measurement Approaches . . . . . . . . . . . . . . . . . . . . 18
2.3 BCG Analysis Methodologies . . . . . . . . . . . . . . . . . . . . . . . . . 19
2.3.1 Clustering Method . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
2.3.2 Discrete Wavelet Transform Method . . . . . . . . . . . . . . . . . . 21
2.3.3 Hilbert Transform Method . . . . . . . . . . . . . . . . . . . . . . . 23
2.3.4 Template Matching Method . . . . . . . . . . . . . . . . . . . . . . 26
2.3.5 Short-Time Energy Method . . . . . . . . . . . . . . . . . . . . . . 27
2.3.6 Smoothed Length Transform Method . . . . . . . . . . . . . . . . . 28
2.3.7 Comparison . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
3 Proposed Algorithm for Heart Rate Detection 31
3.1 System Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
3.1.1 Sensing Components . . . . . . . . . . . . . . . . . . . . . . . . . . 32
3.2 Overview of Proposed Algorithm . . . . . . . . . . . . . . . . . . . . . . . . 34
3.3 Heartbeat Template Extraction . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.3.1 Heartbeat Candidates Extraction . . . . . . . . . . . . . . . . . . . . 36
3.3.2 Classification with K-Means Clustering . . . . . . . . . . . . . . . . 39
3.4 Noise Reduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
3.4.1 Spectral Subtraction . . . . . . . . . . . . . . . . . . . . . . . . . . 48
3.4.2 Brief Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
3.5 Heartbeat Detection and Heart Rate Estimation . . . . . . . . . . . . . . . . 56
4 Implementation Results and Discussion 61
4.1 Simulation Results under Different Scenario . . . . . . . . . . . . . . . . . . 63
4.2 Comparison and Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . 71
5 Conclusion and Future Works 75
5.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75
5.2 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76
Bibliography 82

[1] “Global status report on road safety,” 2015. [Online]. Available: https://www.who.int/
violence injury prevention/road safety status/2015/en/.
[2] “Car accident from drowsy driving statistics,” 2017. [Online]. Available: https:
//www.nhtsa.gov/risky-driving/drowsy-driving.
[3] Y. Masaki, D. Mitsuo,W. Junichi, O. Shin, T. Noriyasu, H. Tomoyuki, and M. Yasufumi,
“Hand-held monitor of sympathetic nervous system using salivary amylase activity and
its validation by driver fatigue assessment,” Biosensors and Bioelectronics, vol. 21, no. 7,
pp. 1007–1014, 2006.
[4] H. J. Baek, G. S. Chung, K. K. Kim, and K. S. Park, “A smart health monitoring chair
for nonintrusive measurement of biological signals,” IEEE Transactions on Information
Technology in Biomedicine, vol. 16, no. 1, pp. 150–158, 2012.
[5] J. Gomez-Clapers and R. Casanella, “A fast and easy-to-use ecg acquisition and heart
rate monitoring system using a wireless steering wheel,” IEEE Sensors Journal, vol. 12,
no. 3, pp. 610–616, 2012.
[6] J. Schneider, C. Koellner, and S. Heuer, “An approach to automotive ecg measurement
validation using a car-integrated test framework,” in 2012 IEEE Intelligent Vehicles Symposium,
2012, pp. 950–955.
[7] T. Blocher, J. Schneider, M. Schinle, andW. Stork, “An online ppgi approach for camera
based heart rate monitoring using beat-to-beat detection,” in 2017 IEEE Sensors Applications
Symposium (SAS), 2017, pp. 1–6.
[8] E. Schires, P. Georgiou, and T. S. Lande, “Vital sign monitoring through the back using
an uwb impulse radar with body coupled antennas,” IEEE Transactions on Biomedical
Circuits and Systems, vol. 12, no. 2, pp. 292–302, 2018.
[9] G. Wusk and H. Gabler, “Non-invasive detection of respiration and heart rate with a
vehicle seat sensor,” Sensors, vol. 18, no. 5, p. 1463, 2018.
[10] G. Balakrishnan, F. Durand, and J. Guttag, “Detecting pulse from head motions in
video,” in 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013,
pp. 3430–3437.
[11] C. Br¨user, C. H. Antink, T. Wartzek, M. Walter, and S. Leonhardt, “Ambient and unobtrusive
cardiorespiratory monitoring techniques,” IEEE Reviews in Biomedical Engineering,
vol. 8, pp. 30–43, 2015.
[12] H. Shin, S. Jung, J. Kim, and W. Chung, “Real time car driver’s condition monitoring
system,” in SENSORS, 2010 IEEE, 2010, pp. 951–954.
[13] W.-J. Lin, “A physiological information extraction method based on wearable ppg sensors
with motion artifact removal,” Academic thesis, Department of Electrical Engineering,
National Tsing Hua University, 2014.
[14] I. Sadek, J. Biswas, and B. Abdulrazak, “Ballistocardiogram signal processing: a review,”
Health information science and systems, vol. 7, no. 1, p. 10, 2019.
[15] L. Giovangrandi, O. T. Inan, R. M. Wiard, M. Etemadi, and G. T. A. Kovacs, “Ballistocardiography—
a method worth revisiting,” in 2011 Annual International Conference
of the IEEE Engineering in Medicine and Biology Society, 2011, pp. 4279–4282.
[16] E. Pinheiro, O. Postolache, and P. Gir˜ao, “Theory and developments in an unobtrusive
cardiovascular system representation: ballistocardiography,” The open biomedical engineering
journal, vol. 4, p. 201, 2010.
[17] W. R. Scarborough, “Proposals for ballistocardiographic nomenclature and conventions:
Revised and extended: Report of committee on ballistocardiographic terminology,” Circulation,
vol. 14, pp. 435–450, 09 1956.
[18] I. Starr, A. Rawson, H. Schroeder, and N. Joseph, “Studies on the estimation of cardiac
ouptut in man, and of abnormalities in cardiac function, from the heart’s recoil and
the blood’s impacts; the ballistocardiogram,” American Journal of Physiology-Legacy
Content, vol. 127, no. 1, pp. 1–28, 1939.
[19] W. R. SCARBOROUGH, S. A. TALBOT, J. R. BRAUNSTEIN, M. B. RAPPAPORT,
W. DOCK, W. R. SCARBOROUGH, W. Hamilton, J. E. SMITH, J. L. NICKERSON,
S. A. TALBOT et al., “Proposals for ballistocardiographic nomenclature and conventions:
Revised and extended: Report of committee on ballistocardiographic terminology,”
Circulation, vol. 14, no. 3, pp. 435–450, 1956.
[20] O. T. Inan, M. Etemadi, R. M.Wiard, G. T. Kovacs, and L. Giovangrandi, “Non-invasive
measurement of valsalva-induced hemodynamic changes on a bathroom scale ballistocardiograph,”
in 2008 30th Annual International Conference of the IEEE Engineering in
Medicine and Biology Society. IEEE, 2008, pp. 674–677.
[21] J. H. Shin, K. M. Lee, and K. S. Park, “Non-constrained monitoring of systolic blood
pressure on a weighing scale,” Physiological measurement, vol. 30, no. 7, p. 679, 2009.
[22] R. Casanella, J. Gomez-Clapers, and R. Pallas-Areny, “On time interval measurements
using bcg,” in 2012 Annual International Conference of the IEEE Engineering
in Medicine and Biology Society. IEEE, 2012, pp. 5034–5037.
[23] J. H. Shin and K. S. Park, “Hrv analysis and blood pressure monitoring on weighing
scale using bcg,” in 2012 Annual International Conference of the IEEE Engineering in
Medicine and Biology Society. IEEE, 2012, pp. 3789–3792.
[24] W. R. Scarborough, “Proposals for ballistocardiographic nomenclature and conventions:
Revised and extended: Report of committee on ballistocardiographic terminology,” Circulation,
vol. 14, pp. 435–450, 09 1956.
[25] R. Gonzalez-Landaeta, O. Casas, and R. Pallas-Areny, “Heart rate detection from an
electronic weighing scale,” Physiological Measurement, vol. 29, pp. 979–88, Aug 2008.
[26] T. Koivistoinen, S. Junnila, A. Varri, and T. Koobi, “A new method for measuring the ballistocardiogram
using emfi sensors in a normal chair,” in The 26th annual international
conference of the IEEE engineering in medicine and biology society, vol. 1. IEEE,
2004, pp. 2026–2029.
[27] K. Watanabe, T. Watanabe, H. Watanabe, H. Ando, T. Ishikawa, and K. Kobayashi,
“Noninvasive measurement of heartbeat, respiration, snoring and body movements of a
subject in bed via a pneumatic method,” IEEE transactions on biomedical engineering,
vol. 52, no. 12, pp. 2100–2107, 2005.
[28] C. Br¨user, K. Stadlthanner, S. de Waele, and S. Leonhardt, “Adaptive beat-to-beat heart
rate estimation in ballistocardiograms,” IEEE Transactions on Information Technology
in Biomedicine, vol. 15, no. 5, pp. 778–786, 2011.
[29] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed. Pearson/Prentice
Hall, 2018, ch. 7.10.
[30] I. Sadek, J. Biswas, B. Abdulrazak, Z. Haihong, and M. Mokhtari, “Continuous and unconstrained
vital signs monitoring with ballistocardiogram sensors in headrest position,”
in 2017 IEEE EMBS International Conference on Biomedical Health Informatics (BHI),
2017, pp. 289–292.
[31] J. Jin, X. Wang, S. Li, and Y. Wu, “A novel heart rate detection algorithm in ballistocardiogram
based on wavelet transform,” in 2009 Second International Workshop on
Knowledge Discovery and Data Mining, 2009, pp. 76–79.
[32] L. Marple, “Computing the discrete-time ”analytic” signal via fft,” IEEE Transactions
on Signal Processing, vol. 47, no. 9, pp. 2600–2603, 1999.
[33] B. Y. Su, K. C. Ho, M. Skubic, and L. Rosales, “Pulse rate estimation using hydraulic bed
sensor,” in 2012 Annual International Conference of the IEEE Engineering in Medicine
and Biology Society, 2012, pp. 2587–2590.
[34] J. H. Shin, B. H. Choi, Y. G. Lim, D. U. Jeong, and K. S. Park, “Automatic ballistocardiogram
(bcg) beat detection using a template matching approach,” in 2008 30th Annual
International Conference of the IEEE Engineering in Medicine and Biology Society,
2008, pp. 1144–1146.
[35] K. Lydon, B. Y. Su, L. Rosales, M. Enayati, K. Ho, M. Rantz, and M. Skubic, “Robust
heartbeat detection from in-home ballistocardiogram signals of older adults using
a bed sensor,” in 2015 37th annual international conference of the IEEE engineering in
medicine and biology society (EMBC). IEEE, 2015, pp. 7175–7179.
[36] E. J. Pino, J. A. Ch´avez, and P. Aqueveque, “Bcg algorithm for unobtrusive heart rate
monitoring,” in 2017 IEEE Healthcare Innovations and Point of Care Technologies (HIPOCT).
IEEE, 2017, pp. 180–183.
[37] J. Pan and W. J. Tompkins, “A real-time qrs detection algorithm,” IEEE Transactions on
Biomedical Engineering, vol. BME-32, no. 3, pp. 230–236, 1985.
[38] A. K. Jain, “Data clustering: 50 years beyond k-means,” Pattern recognition letters,
vol. 31, no. 8, pp. 651–666, 2010.
[39] S. V. Vaseghi, Advanced Digital Signal Processing and Noise Reduction, 4th ed. John-
Wiley Sons Ltd., 2008, ch. 10.4.
[40] A. V. Oppenheim and R. W. Schafer, Discrete-Time Signal Processing, 3rd ed. Pearson/
Prentice Hall., 2010, ch. 7.5.1.
[41] S. Boll, “Suppression of acoustic noise in speech using spectral subtraction,” IEEE
Transactions on acoustics, speech, and signal processing, vol. 27, no. 2, pp. 113–120,
1979.
[42] J. Rosenberg, A. Amjad, P. Breeze, D. Brillinger, and D. Halliday, “The fourier approach
to the identification of functional coupling between neuronal spike trains,” Progress in
biophysics and molecular biology, vol. 53, no. 1, pp. 1–31, 1989.
[43] Q. Xie, Y. Li, G. Wang, and Y. Lian, “An unobtrusive system for heart rate monitoring
based on ballistocardiogram using hilbert transform and viterbi decoding,” IEEE Journal
on Emerging and Selected Topics in Circuits and Systems, vol. 9, no. 4, pp. 635–644,
2019.
[44] Y.-C. Chang, “Physiological signal detection with automotive seat sensors,” Academic
thesis, Department of Electrical Engineering, National Tsing Hua University, 2019.