A Machine Learning Based Driver Skill Assist System
S. Balakrishnan1, V.Kamatchi Sundari2, Ram Vishnu R3, S. Sheeba Rani4
1Dr. S. Balakrishnan, Professor and Head, Department of Computer Science and Business Systems, Sri Krishna College of Engineering and Technology, Coimbatore (Tamil Nadu), India.
2Dr. V. Kamatchi Sundari, Professor, Department of Electronics and Communication Engineering, Prince Shri Venkateswara Padmavathy Engineering College, Chennai (Tamil Nadu), India.
3Mr. Ram Vishnu R, UG Student, Department of Information Technology, Sri Krishna College of Engineering and Technology, Coimbatore (Tamil Nadu), India.
4Dr. S. Sheeba Rani, Associate Professor, Department of Electrical and Electronics Engineering, Sri Krishna College of Engineering and Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 29 May 2019 | Revised Manuscript received on 11 June 2019 | Manuscript Published on 22 June 2019 | PP: 597-600 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C11270283S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A driver’s driving skill is a key factor for vehicle handling in risk situations. This paper presents an approach to sense the driving pattern on all likes of gear shifting, braking, speed control of the driver alongside the corresponding vehicle’s response and is assessed based on pre-defined set of guidelines for an initial period called the “Test phase”, of the driver. Then implementing the assessed results as either an increment or a decrement on a gradient scale ranging from 0 to 100, called “Score”, the driver is put into either of the two categories “Good” or “Bad”. If the driver falls into “Bad” he is instructed on his driving pattern thus providing the instructions about ways of improving his driving collectively called as “Improving phase”. Likewise if the driver falls into “Good”, the system remains in the “Test phase” until it encounters any change. Further, our system learns about the driver’s pattern throughout and uses decision making algorithms to continuously decide the phases and the actions. Thus it improves the driving skill of any person producing more skilled drivers thereby averting accidents and reduces road rush severely.
Keywords: Driver Skill Assist, Machine Learning, Markov Decision Process (MDP), Fuzzy Algorithm.
Scope of the Article: Machine Learning