IDENTIFICATION OF DRIVING CHARACTERISTICS USING MARKOV PROCESS MODEL

Yıl 2020, Cilt: 21 Sayı: 2, 314 - 321, 15.06.2020

Tuba Nur Serttaş , Ömer Nezih Gerek Fatih Onur Hocaoğlu

https://doi.org/10.18038/estubtda.584942

Öz

Considering the role of drivers in
traffic, it is an important advantage to know the driver characteristics in
advance. Taking this characteristic into consideration, the driver can be
warned socially and economically. In this study, taking into account this
situation, driving characteristics are removed within certain drivers and the
drivers are divided into two classes as calm and aggressive. The data recorded
via the smartphone is used directly when classification. By applying Markov
process method to the data, the drives are classified with 73% accuracy.

Anahtar Kelimeler

Driver classification, Markov Process, Drive data analysis

Destekleyen Kurum

Eskişehir Teknik Üniversitesi

Proje Numarası

1701F020

Teşekkür

This study is supported by Eskişehir Technical University Scientific Research Project numbered 1701F020.

Kaynakça

• [1] Huang C, Li L, Liu Y, Xiao L. Robust Observer Based Intermittent Forces Estimation for Driver Intervention Identification. IEEE Trans. Veh. Technol., Apr. 2020; 69(4): 3628–3640.
• [2] Jia S, Hui F, Li S, Zhao X, Khattak AJ. Long short-term memory and convolutional neural network for abnormal driving behaviour recognition. IET Intell. Transp. Syst., May 2020; 14(5): 306–312.
• [3] Lin X, Zhang K, Cao W, Zhang L. Driver Evaluation and Identification Based on Driving Behavior Data. In Proceedings - 2018 5th International Conference on Information Science and Control Engineering, 2019; 718–722.
• [4] Liu X, Liang J, Xu B. A Deep Learning Method for Lane Changing Situation Assessment and Decision Making. IEEE Access, 2019; 7:133749–133759.
• [5] Rahim MA, Liu J, Zhang Z, Zhu L, Li X, Khan S. Who is driving? Event-driven Driver Identification and Impostor Detection through Support Vector Machine. IEEE Sens. J., Jun. 2020; 20(12):1.
• [6] Rahim MA, Zhu L, Li X, Liu J, Zhang Z, Qin Z, Khan S, Gai K. Zero-to-Stable Driver Identification: A Non-Intrusive and Scalable Driver Identification Scheme. IEEE Trans. Veh. Technol.,Jan. 2020; 69(1): 163–171.
• [7] Regani SD, Xu Q, Wang B, Wu M, Ray Liu KJ. Driver Authentication for Smart Car Using Wireless Sensing. IEEE Internet Things J., Mar. 2020; 7(3): 2235–2246.
• [8] Van der El K, Pool DM, Van Paassen MRM, Mulder M. A Unifying Theory of Driver Perception and Steering Control on Straight and Winding Roads. IEEE Trans. Human-Machine Syst., Apr. 2020; 50(2): 165–175.
• [9] Aycard O, Charpillet F, Foht D and Mari JF. Place learning and recognition using hidden Markov models. In Proc, IEEE Int. Robots Syst., 1997, Grenoble, France, pp. 1741-1746.
• [10] Yang L, Widjaja BK and Prasad R. Application of hidden Markov models for signature verification. Pattern Recognition, 1995; 28:161-169.
• [11] Yang Y Xu Y. Human Action Learning via Hidden Markov Model. IEEE Trans. Syst. Man and Cyber.-Part A: Syst. And Humans, 1997; 27:1.
• [12] Pentland A, Liu A. Modeling and Prediction of Human Behavior. Neural Computation, 1999; 11:229-242.
• [13] Mitrovic D. Reliable Method for Events Recognition. IEEE Trans. on Intelligent Transp. Syst., June 2005; 6(2):198-205.
• [14] Torkkola K, Venkatesan S, Liu H. Sensor Sequence Modeling for Driving. FLAIRS Conference, 2005, Clearwater Beach, Florida, USA, pp. 721-727.
• [15] Zou X. Modeling Intersection Driving Behaviors: A Hidden Markov Model Approach-I. Jrnl. of Transportation Res. Board, 2006: 16-23.
• [16] Boyraz P, Acar M, Kerr D. Signal Modelling and Hidden Markov Models for Driving Manoeuvre Recognition and Driver Fault Diagnosis in an urban road scenario. Proc. Of IEEE IVS’07, 13-15 June 2007, Istanbul, Turkey: 987-992.
• [17] Sathyanarayana A, Boyraz P, Hansen JHL. Driver Behavior Analysis and Route Recognition by Hidden Markov Models. International Conference on Vehicular Electronics and Safety Columbus, September 22-24, 2008, OH, USA.
• [18] Regani SD, Xu Q, Wang B, Wu M, Ray Liu KJ. Driver Authentication for Smart Car Using Wireless Sensing. IEEE Internet Things J., Mar. 2020; 7(3): 2235–2246.
• [19] Fung NC, Wallace B, Chan ADC, Goubran R, Porter MM, Marshall S, Knoefel F. Driver identification using vehicle acceleration and deceleration events from naturalistic driving of older drivers. In 2017 IEEE International Symposium on Medical Measurements and Applications- Proceedings, 2017: 33–38.