Deneysel Olarak Ölçülen Farklı Sürüş Davranışlarının K En Yakın Komşuluklar Yöntemleriyle Sınıflandırılması

Year 2021, Issue: 28, 790 - 794, 30.11.2021

Tuba Nur Serttaş , Fatih Serttaş

https://doi.org/10.31590/ejosat.1011026

Abstract

Bu çalışmada, 13 farklı sürücünün aynı aracı, aynı güzergahta ve aynı çevre koşullarında sürmesi sağlanmıştır. Sürüşler başlamadan araca araç takip cihazı monte edilmiş ve eş zamanlı olarak akıllı telefon uygulaması kullanılmıştır. Sürüşlerin kontrollü bir şekilde gerçekleştirildiği rota, sürüş davranışlarını ortaya çıkarabilecek özelliklere sahip olacak şekilde seçilmiştir. Açısal hız ile ilgili sonuçların doğru bir şekilde alınabilmesi için sağa-sola dönüş ve u dönüşü manevralarının kullanıldığı bölümler bulunmaktadır. Aynı amaçla yolda tümsek, çukur, yaya, araç ve hız limitlerinin olmasına özen gösterilmiştir. Ardından sürücüler agresif, sakin veya normal olarak sınıflandırılmaktadır. Sınıflandırma yöntemi olarak k en yakın komşuluklar metodolojileri kullanılmıştır. Fine KNN yöntemi ile %84,6 doğruluk elde edilmiştir.

Keywords

Sürüş karakteristiği, Sınıflandırma, Fine KNN, Weighted KNN, Deneysel sürüş

Classification of Experimentally Measured Different Driving Behaviors using K Nearest Neighbors Methods

Abstract

In this study, 13 different drivers were provided to drive the same vehicle on the same route and environmental conditions. Before the rides started, a vehicle tracking device was mounted on the vehicle and a smartphone application was used simultaneously. The route where the driving is carried out in a controlled way has been chosen to have features that can reveal driving behaviors. There are sections where right-left turns and U-turn maneuvers are used to obtain accurate angular velocity results. For the same purpose, care has been taken to ensure bumps, potholes, pedestrian, vehicle, and speed limits on the road. Afterward, drivers are classified as aggressive, calm, or usual. KNN methodologies are used as the classification method. Fine KNN application reaches 84,6% accuracy ratio.

Keywords

Driving characteristic, Classification, Fine KNN, Weighted KNN, Experimental driving

References

• Ayuso, M., Guillén, M., & Pérez-Marín, A. M. (2014). Time and distance to first accident and driving patterns of young drivers with pay-as-you-drive insurance. Accident Analysis & Prevention, 73, 125-131.
• Boyraz, P., Acar, M., & Kerr, D. (2007, June). Signal modelling and hidden markov models for driving manoeuvre recognition and driver fault diagnosis in an urban road scenario. In 2007 IEEE Intelligent Vehicles Symposium (pp. 987-992). IEEE.
• Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
• Daza, I. G., Hernández, N., Bergasa, L. M., Parra, I., Yebes, J. J., Gavilán, M., ... & Sotelo, M. A. (2011, October). Drowsiness monitoring based on driver and driving data fusion. In 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC) (pp. 1199-1204). IEEE.
• Fix, E., & Hodges, J. L. (1989). Discriminatory analysis. Nonparametric discrimination: Consistency properties. International Statistical Review/Revue Internationale de Statistique, 57(3), 238-247.
• Fu, R., Wang, H., & Zhao, W. (2016). Dynamic driver fatigue detection using hidden Markov model in real driving condition. Expert Systems with Applications, 63, 397-411.
• Gadepally, V., Kurt, A., Krishnamurthy, A., & Özgüner, Ü. (2011, October). Driver/vehicle state estimation and detection. In 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC) (pp. 582-587). IEEE.
• Gadepally, V., Krishnamurthy, A., & Ozguner, U. (2013). A framework for estimating driver decisions near intersections. IEEE Transactions on Intelligent Transportation Systems, 15(2), 637-646.
• Malta, L., Miyajima, C., & Takeda, K. (2009). A study of driver behavior under potential threats in vehicle traffic. IEEE Transactions on Intelligent Transportation Systems, 10(2), 201-210.
• Miyajima, C., Nishiwaki, Y., Ozawa, K., Wakita, T., Itou, K., Takeda, K., & Itakura, F. (2007). Driver modeling based on driving behavior and its evaluation in driver identification. Proceedings of the IEEE, 95(2), 427-437.
• Miyajima, C., Yamazaki, S., Bando, T., Hitomi, K., Terai, H., Okuda, H., ... & Takeda, K. (2015, June). Analyzing driver gaze behavior and consistency of decision making during automated driving. In 2015 IEEE Intelligent Vehicles Symposium (IV) (pp. 1293-1298). IEEE.
• Oliver, N., & Pentland, A. P. (2000, October). Graphical models for driver behavior recognition in a smartcar. In Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No. 00TH8511) (pp. 7-12). IEEE.
• Oliver, N., & Pentland, A. P. (2000, June). Driver behavior recognition and prediction in a SmartCar. In Enhanced and Synthetic Vision 2000 (Vol. 4023, pp. 280-290). International Society for Optics and Photonics.. Sakaguchi, Y., Okuwa, M., Takiguchi, K. I., & Akamatsu, M. (2003).
• Measuring and modelling of driver for detecting unusual behavior for driving assistance. In Proceedings: International Technical Conference on the Enhanced Safety of Vehicles (Vol. 2003, pp. 7-p). National Highway Traffic Safety Administration.
• Sałapatek, D., Dybała, J., Czapski, P., & Skalski, P. (2017). Driver drowsiness detection systems. Zeszyty Naukowe Instytutu Pojazdów/Politechnika Warszawska, 3(112), 41-48.
• Takeda, K., Hansen, J. H., Boyraz, P., Malta, L., Miyajima, C., & Abut, H. (2011). International large-scale vehicle corpora for research on driver behavior on the road. IEEE Transactions on Intelligent Transportation Systems, 12(4), 1609-1623.