Heartbeat Detection Technology for Monitoring Driver's Physical Condition Aisin Seiki Company, Limited

Format:

Book

Conference/Event

Author/Creator:

Tsuchiya, Kento, author.

Contributor:

Mochizuki, Kenta

Ohtsuki PhD, Tomoaki

Yamamoto, Kōhei.

Conference Name:

WCX SAE World Congress Experience (2020-04-21 : Detroit, Michigan, United States)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2020

Summary:

In recent years, the number of reported traffic accidents due to sudden deterioration in driver's physical condition has been increasing, and 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 has occurred, the damage can be reduced by emergency evacuation immediately after detecting sudden changes. Therefore, we focused on the technology to detect the heartbeat interval wiht 24GHz microwave doppler radar, which can acquire heartbeat non-contactly while maintaining the interior design and passenger's privacy. Doppler radar with microwave is sensitive enough to detect heartbeat, but vibration noise is also superimposed on the sensor signal easily. So, in general algorithm studied widely,the problem is that the accuracy of detecting the heartbeat interval deteriorates especially while driving, because superimposition of vehicle vibration on the frequency band used for heartbeat analysis, and the SN ratio decreases.In order to solve this problem, we have been developing an algorithm that extracts power spectrum over wide band including harmonic components of heartbeat and detects the peaks of power spectrum fluctuation.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

Notes:

Vendor supplied data

Publisher Number:

2020-01-1212

Access Restriction:

Restricted for use by site license