1. Wristband-Type Driver Vigilance Monitoring System Using Smartwatch IEEE SENSORS JOURNAL, VOL. 15, NO. 10, OCTOBER 2015 Boon-Giin Lee, Member, IEEE, Boon-Leng Lee, and Wan-Young Chung, Member, IEEE Presenter: Siao, Jing-Jhou Advisor: Dr. Pei-Jarn Chen Date:2015/12/16 1

2. Outline Introduction Methodology Experimental results Conclusion 2

3. Introduction 3

4. Driver vigilance Vehicle-based control behavior  Steering wheel movement Physiological state  Photoplethysmogram (PPG)  Respiration signals 4

5. Steering wheel movement Smartwatch motion sensors  Accelerometer  Gyroscope sensors 5

6. PPG sensor A sport wristband with a Bluetooth low energy module Transmitted the PPG signals to smartwatch 6

7. Methodology 7

8. Wearable type monitoring system Sensor module (sensing and A/D convert) Smartwatch module (receive, analysis, information display, and alert) 8

9. Hardware specification 9

10. Wearable type monitoring system 10

11. Steering wheel angles (SWA) Pitch (rotate at x-axis) Roll (rotate at y-axis) Yaw (rotate at z-axis) 11

12. Wristband-type system Wristband-type system 12

13. Hands position regarding to the steering angle 13

14. 14 Angle derivation

15. Photoplethysmogram 15

16. PPG-Derived Respiration 16

17. Features extracted from motion sensors, PPG, and PDR 17

18. Karolinska sleepiness scale (KSS) 18

19. Weighted fuzzy c-means (WFCM) Fuzzy c-means is an essential tool to find the proper cluster structure of given data sets in pattern and image classification A weighted fuzzy C-Means algorithm is proposed to improve the performance of both FCM models for high-dimensional multiclass pattern recognition problems 19

20. Weighted fuzzy c-means (WFCM) 20

21. Accuracy rate ( the age and gender) 21

22. Comparison of classifiers 22

23. Experimental Results 23

24. Driver Vigilance Monitoring System 24

25. Driver Vigilance Monitoring System 25

26. Conclusion 26

27. Conclusion This study presents the steering wheel movement derived from motion sensors is a great indicator to measure driver vigilance level. On the other hand,by integrating the driver physiological state into vigilance prediction, it can increases the true prediction rate (96.5%) as well as reduces the false prediction rate (4.2%). 27

28. Thanks for your attention ! 28