Review and evaluation of methods in transport mode detection based on GPS tracking data

作     者：Paria Sadeghian Johan Håkansson Xiaoyun Zhao Paria Sadeghian;Johan H?kansson;Xiaoyun Zhao

作者机构：School of Technology and Business StudiesDalarna UniversityFalunSweden Integrated Transport Research LabKTH Royal Institute of TechnologyStockholmSweden 

出 版 物：《Journal of Traffic and Transportation Engineering(English Edition)》 (交通运输工程学报（英文版）)

年 卷 期：2021年第8卷第4期

页      面：467-482页

核心收录：

学科分类：08[工学] 0838[工学-公安技术] 

基　　金：the financial supported by the Swedish Energy Agency (project no. 46068-1) 

主　　题：Traffic engineering Transport mode detection Machine learning Statistical learning Rule-based method Deep learning 

摘      要：Mobility data,based on global positioning system(GPS)tracking,have been widely used in many areas,such as analyzing travel patterns,investigating transport safety and efficiency,and evaluating travel *** modes are essential factors in understanding mobility within the transport ***,in this study,a significant number of algorithms were tested for transport mode ***,no conclusive recommendations can be drawn regarding which method should be *** evaluation of the performance of the algorithms was not discussed systematically either in current *** paper aims to provide an in-depth review of the methods applied in transport mode detection based on GPS tracking *** performances of the reviewed methods are then compared and evaluated to provide guidance in choosing algorithms for transport mode detection based on GPS tracking *** results indicate that the majority of current studies are based on a supervised learning method for transport mode *** of the reviewed methods first require manual dataset labeling,which can produce major drawbacks,such as inefficiency and human *** was also found that deep learning approaches have the potential to deal with large amounts of unlabeled raw GPS datasets and increase the accuracy and efficiency of transport mode detection.