1. 5th Annual International Commerce Convention: Startup to Sustainability Initiatives and Challenges
Reduction in Accidental Death: Determining Driver Behavior Using Fuzzy Theory
Dr. Jabar Yousif and Dr. Dinesh Kumar Saini
Faculty of Computing and IT
Sohar University

2. OUTLINES Abstract Introduction Problem Statement Proposed Solution
System Objectives
Conclusion

3. ABSTRACT
The statistics from all over the world says the death rate due to road accidents are increasing year by year. There are countries where the road accident death rate is higher than normal death rate. The main cause of deaths is driver. This paper aims to develop a fuzzy model for determining the status of driver. It is important to early detect the driver fatigue and drowsiness to avoid accidents. The framework suggests to install a camera in the front of driver and sensors, which sends images directly to a cloud data center the information of driver including the current position of driver. The fuzzy model will be used to control and analysis the data of driver in the cloud center and send back the important decision about the status of driver, if it is normal or not.

4. Monitoring Techniques
Car Model
Methods for Detection support provided
Nissan
Nissan car company Blinking movements through infrared camera
Toyota
Steering Wheel sensors and pulse sensors
Mitsubishi
Mounted cameras and eye blinking
Chrysler
Speed, vehicle position, Delimitation
Siemens
Eye Lids
Complexica
Head Position and neural Networking
Renault
Infrared Light and eyelids
Ford model Falcon
Implement a driver fatigue warning system based on driving duration.
Volvo models S80, V70 and XC70
Implement a driver alert Control based detecting lane crossing.

6. Possible Solution

7. PROPOSED SOLUTION .

8. Fuzzy System Approach
A fuzzy system mainly consists of three stages namely, Fuzzification, rule Evaluation, and defuzzification. The first stage of fuzzy model is to convert the crisp data into a verbal variable using a membership function. The second stage is to convert the fuzzy input data into a fuzzy output data using If-Then rules. So, rules for fuzzy model for detecting the status drowsy of driver are the following:
R1: If the driver head in the safe range [σ], then the driver status is wake up.
R2: If the driver head in the safe range [dis1+σ], then the driver status is wake up.
R3: If the driver head in the safe range [dis2+σ], then the driver status is wake up.
R4: If the driver head in the sleepy range [> dis1+σ], then the driver status is sleepy.
R5: If the driver head in the sleepy range [<dis2+σ], then the driver status is sleepy.

9. System

10. CONCLUSION
The framework suggests installing a camera in the front of driver and sensors, which captured images directly, the information of driver including the current position of driver.
From the features captured through camera that monitor driver behavior will help in controlling the vehicle if the driver is sleepy and fatigue.
The fuzzy model is proposed to control and analysis the data of driver, the status of driver, if it is normal or not. The proposed framework can help to reduce the death rate.
Limitations: framework is proposed, cloud implementation is in process, it is not finished. .

11. References:
1. Horne, James A, & Baulk, S. D. (2003). Awareness of sleepiness when driving, Psychophysiology, 41(1), 161–165
2. Campagne, A., Pebayle, T., & Muzet, A. (2004). Correlation between driving errors and vigilance level: influence of the driver’s age. Physiology & behavior, 80(4), 515–524. doi: /j.physbeh
3. Ingre, M., ÅKerstedt, T., Peters, B., Anund, A., & Kecklund, Gör. (2006). Subjective sleepiness, simulated driving performance and blink duration: examining individual differences. Journal of sleep research, 15(1), 47–53.
4. Ji, Q., Lan, P., & Looney, C. (2006). A probabilistic framework for modeling and real-time monitoring human fatigue. Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, 36(5), 862–875.
5. Kaida, K., Takahashi, M., Åkerstedt, T., Nakata, A., Otsuka, Y., Haratani, T., & Fukasawa, K. (2006). Validation of the Karolinska sleepiness scale against performance and EEG variables. Clinical Neurophysiology, 117(7), 1574–1581.
6. Fan, X., Yin, B.-C., & Sun, Y.-F. (2007). Yawning detection for monitoring driver fatigue. Machine Learning and Cybernetics, 2007 International Conference on (Vol. 2, pp. 664– 668). IEEE.
7. Kaida, K., ÅKERSTEDT, T., KECKLUND, G., Nilsson, J. P., & Axelsson, J. (2007). Use of subjective and physiological indicators of sleepiness to predict performance during a vigilance task. Industrial health, 45(4), 520–526.
8. Saradadevi, M., & Bajaj, P. (2008). Driver fatigue detection using mouth and yawning analysis. Int.J.Comput.Sci.Netw.Security, 8(6), 183–188.
9. Ting, P.-H., Hwang, J.-R., Doong, J.-L., & Jeng, M.-C. (2008). Driver fatigue and highway driving: A simulator study. Physiology & behavior, 94(3), 448–453. doi: /j.physbeh
10. Dinges, D. F. (2009). An overview of sleepiness and accidents. Journal of sleep research, 4(s2), 4–14.
11. Horne, J A, & Reyner, L. A. (2009). Driver sleepiness. Journal of sleep research, 4(s2), 23– 29.
12. Liu, C. C., Hosking, S. G., & Lenné, M. G. (2009). Predicting driver drowsiness using vehicle measures: recent insights and future challenges. Journal of Safety Research, 40(4), 239–245.
13. Reyner, L A, Horne, J. A., & Flatley, D. (2010). Effectiveness of UK motorway services areas in reducing sleep-related and other collisions. Accident Analysis & Prevention, 42(4), 1416–1418. doi: /j.aap
14. Yao, K. P., Lin, W. H., Fang, C.-Y., Wang, J.-M., Chang, S.-L., & Chen, S.-W. (2010). Real-time vision-based driver drowsiness/fatigue detection system. Vehicular Technology Conference (VTC 2010-Spring), 2010 IEEE 71st (pp. 1–5). IEEE.
15. He, Q., Li, W., & Fan, X. (2011). Estimation of Driver’s Fatigue Based on Steering Wheel Angle. Engineering Psychology and Cognitive Ergonomics, 145–155.
16. Mets, M. A. J., Baas, D., Van Boven, I., Olivier, B., & Verster, J. C. (2012). Effects of coffee on driving performance during prolonged simulated highway driving. Psychopharmacology, 1–6.