This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Heartbeat Detection Technology for Monitoring Driver’s Physical Condition
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 14, 2020 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
In recent years, the number of reported traffic accidents due to sudden deterioration in driver’s physical condition has been increasing, it is expected to develop a system that prevents accidents even if physical condition suddenly changes while driving, or reduces damage through vehicle body control. For this purpose, it is necessary to detect sudden changes of the driver’s physical condition, and research is being conducted widely. Among them, it is reported that some of such changes may appear in the heartbeat interval. In other words, by acquiring the driver’s heartbeat interval in real time, it may be possible to detect the sudden changes, and reduce traffic accident. Even if a traffic accident occurs, the damage can be reduced by emergency evacuation immediately after detecting sudden changes. Therefore, we focused on the technology to detect the heartbeat interval with 24GHz microwave Doppler radar, which can detect heartbeat non-contactly while maintaining the interior design and passenger’s privacy. Doppler radar with microwave is sensitive enough to detect heartbeat, however vibration noise is also superimposed on the sensor signal easily. Thus, in general algorithm studied widely, the problem is that the accuracy of detecting the heartbeat interval deteriorates particularly while driving, because the car vibration is superimposed on the frequency band used for heartbeat analysis, and the SNR (Signal to Noise power Ratio) decreases. To solve this problem, we developed an algorithm that extracts power spectrum over wide band including harmonic components of heartbeat and detects the peaks. This time, our new peak-searching method, in which multiple peak intervals are selected simultaneously based on the previous estimation results, suppresses false detection of peaks caused by vibration noise. As a result, the error rate of the heartbeat interval detection was reduced by half compared to the conventional algorithm in which a peak is detected based on previous heartbeat intervals.
CitationTsuchiya, K., Mochizuki, K., Ohtsuki, T., and Yamamoto, K., "Heartbeat Detection Technology for Monitoring Driver’s Physical Condition," SAE Technical Paper 2020-01-1212, 2020, https://doi.org/10.4271/2020-01-1212.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
|[Unnamed Dataset 2]|
|[Unnamed Dataset 3]|
- Ministry of Land, Infrastructure, Transport and Tourism , “Trends of Traffic Accidents Caused by Driver’s Physical Conditions and Efforts to Prevent Such Accidents (Kenkou kiin jiko hassei joukyou to kenkou kiin jiko boushi no tame no torikumi),” 1-5, http://www.mlit.go.jp/common/001210258.pdf.
- Tervo, T.M.T., Neira, W., Sulander, P., and Kivioja, A. , “Observation Failures/Distraction and Disease Attack/Incapacity as Cause(s) of Fatal Road Crashes in Finland,” Traffic Injury Prevention, Feb. 2008.
- Nakagawa, T., Kawachi, T., Futatsuyama, K., and Nishi, K. , “Monitoring the Physical Condition of Drivers as they Drive,” 103-106, https://www.denso.com/jp/ja/innovation/technology/dtr/v21/paper-11.pdf.
- Sang-Joong, J., Heung-Sub, S., and Wan-Young, C. , “Driver Fatigue and Drowsiness Monitoring System with Embedded Electrocardiogram Sensor on Steering Wheel,” IET Intelligent Transport Systems 8(1), Feb. 2014.
- Fujikawa, K., Suzuki, Y., Miyajima, M., Yamakawa, T. et al. , “Development of Epilepic Seizure Prediction Algorithm Using One Class SVM,” in 57th ISCIE, Nov. 2014, 1565-1570.
- Kadoya, K., Shindo, T., and Kaneko, S. , “Modeling of a Cardiovascular System for Detecting Sudden Disease (Taichou kyuuhen kenchi ni muketa shinzou-kekkan-kei model no kouchiku),” in Dynamics and Design Conference 2018, Aug. 2018.
- Horihata, Y., Sugita, N., and Yoshizawa, M. , “Image Plethysmogram Using Infrared Camera,” in The Society of Instrument and Control Engineers Tohoku Chapter 301st Research Meeting, May 2016, 1-4, http://www.topic.ad.jp/sice/htdocs/papers/301/301-8.pdf.
- Mogi, E. and Ohtsuki, T. , “Heartbeat Detection with Doppler Radar Based on Spectrogram,” in IEEE ICC 2017 Symposium E-Health Track, 3-4.
- Droitcour, A.D. , “Non-Contact Measurement of Heart and Respiration Rates with a Single Chip Microwave Doppler Radar,” Submitted to the Department of Electrical Engineering and the Committee on Graduate Studies of Stanford University, June 2006, 7-10.
- Izumi, S. , “Non-Contact Instantaneous Heart Rate and Respiration Extraction In-Car System Using Microwave Doppler Sensor (Micro-ha Doppler sensor wo mochiita shasaiouyou hisesshoku shinpaku hendou / kokyuu monitoring gijutu no kaihatsu),” 2016, 69-77, ISSN 2185-8950.
- Oishi, K., Okumura, S., Sakamoto, T., Sato, T. et al. , “Non-Contact Interbeat Interval Measurement Using Higher Harmonic Components of Body Surface Displacement with Ultra-Wideband Doppler Radar,” 1-2, http://www-lab26.kuee.kyoto-u.ac.jp/~tsato/publ-pdf/ieicej2018oishi.pdf.
- Mochizuki, K., Ohnishi, Y., Aoyagi, Y., Shinohara, M. et al. , “Vibration Influence Elimination Methods for Heartbeat Detection by Doppler Radar in Cars,” in 25th ITS World Congress, Sept. 2018, 1-8.
- Yamamoto, K., Toyoda, K., and Ohtsuki, T. , “Spectrogram-Based Non-Contact RRI Estimation by Accurate Peak Detection Algorithm,” IEEE Access, 4-6, 2018.
- Kotake, Y. and Sato, N. , “Bland-Altman Analysis for the Accuracy Evaluation of the Cardiac Output Monitor,” J Jpn Soc Intensive Care Med. 263-272, 2009.