Using the Interval Type-2 Fuzzy Inference Systems to Determine a Relationship Between the Road Characteristics Assessment and Road Traffic Accidents




Abstract:
There are several Type-2 fuzzy inference systems (T2FISs) tested in the research described in this paper. These models use one, two, or three input variables and all of them are described by one output variable. Input variables relate to the assessment of dangerous places on the observed road section, assessment of road characteristics, and frequency of driving. The assessment of dangerous places is obtained as an average score from assessing nine dangerous spots on the considered road section in Serbia called “Ibarska magistrala”. Assessment of road characteristics is based on seven scores, which means that participants assessed seven predefined road characteristics in the same road section. The frequency of driving is an input variable based on the criterion of how many times a week or a month the examinee drives on the observed road section. Output variable is The number of road traffic accidents that a driver had experienced. T2FISs are tested on a sample of 305 drivers and most of them are professional drivers. The results are perceived through the cumulative error that T2FISs make in the description of empirical data.

CITATION:

IEEE format

M. Čubranić-Dobrodolac, L. Švadlenka, S. Čičević, A. Trifunović, “Using the Interval Type-2 Fuzzy Inference Systems to Determine a Relationship Between the Road Characteristics Assessment and Road Traffic Accidents,” in Sinteza 2020 - International Scientific Conference on Information Technology and Data Related Research, Belgrade, Singidunum University, Serbia, 2020, pp. 227-232. doi:10.15308/Sinteza-2020-227-232

APA format

Čubranić-Dobrodolac, M., Švadlenka, L., Čičević, S., Trifunović, A. (2020). Using the Interval Type-2 Fuzzy Inference Systems to Determine a Relationship Between the Road Characteristics Assessment and Road Traffic Accidents. Paper presented at Sinteza 2020 - International Scientific Conference on Information Technology and Data Related Research. doi:10.15308/Sinteza-2020-227-232

BibTeX format
Download

RefWorks Tagged format
Download