Research Information System
Thesis Type: Doctorate
Institution Of The Thesis: Gazi Üniversitesi, Fen Bilimleri Enstitüsü, Turkey
Approval Date: 2019
Thesis Language: Turkish
Student: MUSTAFA TEKE
Supervisor: FECİR DURAN
Open Archive Collection: AVESIS Open Access Collection
Abstract:In this study, a system has been designed and implemented by using wireless sensor network to inform vehicle drivers about the condition of the road surface and to help ensure the safety of passengers and vehicles. Icing on roads that most threaten road and driving safety has been chosen as the focus of the study. For the determination of icing on the road surface, soil temperature, air temperature, relative humidity, air pressure and conductivity values on the road surface have been used as the input data set of the classification. Using the single-board computer Raspberry Pi, the road surface condition was estimated by using the classification algorithms collected from the road surface and the data read instantly. The road surface condition has been classified as dry, wet and icy road surface by K-NN (K-Nearest Neighbor) algorithm, which was determined experimentally to have the highest success and fastest response time. As a result of real-time and high-performance classification, drivers approaching the coordinate of sensor network locations are notified via mobile application developed. With the mobile application, if the road surface is icy, the driver is warned visually and audibly, and as a result, it is observed that the driving safety is increased.