Diagnosis of transportation modes on mobile phone using logistic regression classification

• Published in: IET software Vol. 12; no. 2; pp. 142 - 151
• Main Authors: Ballı, Serkan, Sağbaş, Ensar Arif
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.04.2018
• Subjects: accelerometer; Global Positioning System; GPS; gyroscope sensor; logistic regression classification; mobile phone; Research Article; smart phones; smartphone sensors; traffic engineering computing; transportation modes; transportation modes; smartphone sensors; mobile phone; logistic regression classification; accelerometer; smart phones; traffic engineering computing; GPS; gyroscope sensor; Global Positioning System
• ISSN: 1751-8806; 1751-8814; 1751-8814
• DOI: 10.1049/iet-sen.2017.0035

The aim of this study is to detect transportation modes of people by using smartphone sensors. Therefore, a mobile application was developed for this purpose and global positioning system (GPS), accelerometer, and gyroscope sensor data were collected while the subjects were walking, running, biking, and travelling by bus or by car. The application was running for over 8 h. Sensor data were tagged with 12 s intervals and 2500 patterns were obtained. Eleven features were selected from the data set and machine learning methods were applied to detect transportation modes using different sensor combinations. Performances of the methods were discussed in terms of accuracy ratios. Best results were obtained from GPS, accelerometer, and gyroscope sensor combination data using logistic regression method with 99.6% accuracy rate.