An Automated Driver’s Context Recognition Approach Using Smartphone Embedded Sensors

Citation

Hossen, Md Ismail and Bari, Ahsanul and Goh, Michael Kah Ong and Tee, Connie and Lau, Siong Hoe (2020) An Automated Driver’s Context Recognition Approach Using Smartphone Embedded Sensors. In: Computational Science and Technology. Lecture Notes in Electrical Engineering (Computational Science and Technology), 603 . Springer Verlag, pp. 105-112. ISBN 9789811500572

[img] Text
10.1007@978-981-15-0058-9.pdf - Published Version
Restricted to Repository staff only

Download (46MB)

Abstract

Context recognition plays an important role in connecting the space between high-level applications and low-level sensors. To recognize human context, various kinds of sensors have been adopted. Among the variety of exploited sensors, smartphone internal sensors such as accelerometer and gyroscope are widely used due to convenience, non-intrusiveness and low deployment cost. Automatic detection of driver’s context is a very crucial factor to determine the driver’s behaviors. This paper proposes an approach to recognize driver’s context which is a very specific research direction in the domain of human context recognition. The objective of this approach is to automatically detect the contexts of drivers using a smartphone’s internal sensors. The proposed algorithm explores the power of a smartphone’s built-in accelerometer and gyroscope sensors to automatically recognize the driver’s context. Supervised machine learning k-nearest neighbor is employed in the proposed algorithm. Empirical results validated the efficiency of the proposed algorithm.

Item Type: Book Section
Uncontrolled Keywords: Machine learning, context recognition, accelerometer, gyroscope
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 16 Dec 2020 09:28
Last Modified: 16 Dec 2020 09:28
URII: http://shdl.mmu.edu.my/id/eprint/7948

Downloads

Downloads per month over past year

View ItemEdit (login required)