Real Time Car Driver’s Condition Monitoring System Heung-Sub Shin * , Sang-Joong Jung * , Jong-Jin Kim + and Wan-Young Chung + Department of Electronic Engineering Pukyong National University Busan 608-737, South Korea + wychung@pknu.ac.kr Abstract—Driver’s drowsiness and fatigue have been major causes of the serious traffic accidents, which make this an area of great socioeconomic concern. This paper describes the design of ECG (Electrocardiogram) sensor with conductive fabric electrodes and PPG (Photoplethysmogram) sensor to obtain physiological signals for car driver's health condition monitoring. ECG and PPG signals are transmitted to base station connected to the server PC via personal area network for practical test. Intelligent health condition monitoring system is designed at the server to analyze the PPG and ECG signals. Our purpose for intelligent health condition monitoring system is managed to process HRV signals analysis derived from the physiological signals in time and frequency domain and to evaluate the driver's drowsiness status. I. INTRODUCTION Recently, the number of car accident due to driver’s inattention has become a serious problem for society. In particular, driver’s drowsiness and fatigue have been one of the major causes of the serious traffic accidents. According to the U.S. National Highway Traffic Safety Administration (NHTSA), falling asleep while driving is responsible for at least 100,000 automobile crashes annually. An annual average of roughly 40,000 nonfatal injuries and 1,550 fatalities result from these crashes [1]. The National Sleep Foundation also reported that 60% of adult drivers have driven while feeling drowsy and 37% have even actually fallen asleep at the wheel [2]. For these reason, many researches related with automotive mechanism have been widely studied in driver’s safety and convenience field; especially, the methods of using physiological signals (ECG, PPG, EEG, Blood Pressure and etc.) have been studied in ubiquitous healthcare field which have been one of the leading issue since driver’s fatigue and drowsiness are closely related with the physiological signals [3]–[4]. However, the existing methods for measurement of physiological signals are inconvenient and complicated because the wired electrodes ought to be directly connected on the body. To improve these inconvenient factors, researches over the relations between drowsiness and fatigue are studied by using wearable sensor [5]–[6]. Many efforts have been focused on how to get the physiological signals under convenient and noninvasive measurement environment. In this paper, car driver’s condition monitoring system is designed by using ECG and PPG sensors to obtain physiological signals on the steering wheel to overcome the limitations of existing measurement methods. Measured ECG and PPG signals is transmitted to base station via personal area network for storing, analyzing, and displaying the information with the fatigue and drowsiness condition. II. SYSTEM DESIGN Fig. 1 shows the overall system architecture for car driver’s condition monitoring system. The proposed system consists of three parts: sensor, personal area network and server. The sensor part includes ECG sensor, PPG sensor, and wireless sensor node which measure physiological signals from user’s hands and send data to a base station via IEEE 802.15.4. The transmitted physiological signals from wireless sensor node are saved, analyzed and displayed at the server through personal area network environment for practical test properly. A. Composition of Sensors and Wireless Sensor Node To obtain physiological signals, ECG and PPG sensors are designed on the steering wheel for drivers. Fig. 2 shows block diagram of ECG and PPG sensors designed to be attached with wireless sensor node for wireless communication. Conductive fabric electrodes are used for measurements of ECG signals on the steering wheel to maximize convenience. Figure 1. System architecture of real time car driver’s condition monitoring system. 978-1-4244-8168-2/10/$26.00 ©2010 IEEE 951 IEEE SENSORS 2010 Conference