Fuzzy Decision System for Safety on Roads

The topic of road safety is a crucial problem because it has become nowadays one of the main causes of death, despite the efforts made by the countries trying to improve the roads conditions. When starting a journey, there are different factors, both objective and subjective, that influence on the driving safety. In this work, we apply fuzzy logic to model these subjective considerations. A committee machine that combines the information provided by three fuzzy systems has been generated. Each of these fuzzy systems gives a degree of risk when traveling taking into account fuzzy conditions of three variables: car (age, last check, the wear on brakes and wheels, etc.); driver (tiredness, sleeping time, sight, etc.); and characteristics of the trip (day or night, weather conditions, length, urban or country road, etc). The final system gives not only the degree of risk according to this fuzzy prediction but the degree in which this risk could be decreased if some of the conditions change according to the advice the fuzzy decision system provides, such as, for example, if the driver takes a rest, or if the tyres are changed.

[1]  Kazuya Takeda,et al.  Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification , 2007, Proceedings of the IEEE.

[2]  Baoding Liu Uncertain Risk Analysis and Uncertain Reliability Analysis , 2010 .

[3]  George J. Klir,et al.  Fuzzy sets and fuzzy logic - theory and applications , 1995 .

[4]  Javier Montero,et al.  Fuzzy Specification in Real Estate Market Decision Making , 2010, Int. J. Comput. Intell. Syst..

[5]  Matilde Santos,et al.  Improving reliatibity and performance in computer systems by means of fuzzy specifications. , 2009 .

[6]  L Suganthi,et al.  Fuzzy Clustering of Locations for Degree of Accident Proneness based on Vehicle User Perceptions , 2008 .

[7]  U. Trutschel,et al.  Circadian alertness simulator for fatigue risk assessment in transportation: application to reduce frequency and severity of truck accidents. , 2004, Aviation, space, and environmental medicine.

[8]  E. Petridou,et al.  Human factors in the causation of road traffic crashes , 2004, European Journal of Epidemiology.

[9]  L. Evans,et al.  The dominant role of driver behavior in traffic safety. , 1996, American journal of public health.

[10]  Young-Jun Kweon,et al.  Overall injury risk to different drivers: combining exposure, frequency, and severity models. , 2003, Accident; analysis and prevention.

[11]  Roger W. Logan,et al.  Risk Reduction as the Product of Model Assessed Reliability, Confidence, and Consequence , 2005 .

[12]  P. Pongpaibool,et al.  Detection of hazardous driving behavior using fuzzy logic , 2008, 2008 5th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[13]  Yi-Lang Chen Driver personality characteristics related to self-reported accident involvement and mobile phone use while driving , 2007 .

[14]  Roger W. Logan,et al.  Validation, Uncertainty, and Quantitative Reliability at Confidence (QRC) , 2003 .

[15]  I. D. Brown,et al.  Driver fatigue : Fatigue , 1994 .

[16]  Bohdan T. Kulakowski,et al.  Prediction of Risk of Wet-Pavement Accidents: Fuzzy Logic Model , 2000 .

[17]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[18]  Matilde Santos Peñas,et al.  Making decisions on brain tumor diagnosis by soft computing techniques , 2010, Soft Comput..

[19]  Ruediger Lamm,et al.  Fuzzy Model for Safety Evaluation Process of New and Old Roads , 2004 .

[20]  G. Guyatt,et al.  The independent contribution of driver, crash, and vehicle characteristics to driver fatalities. , 2002, Accident; analysis and prevention.

[21]  Ajith Abraham,et al.  Traffic Accident Analysis Using Machine Learning Paradigms , 2005, Informatica.

[22]  J. Horne,et al.  Sleep related vehicle accidents , 1995, BMJ.