Travel Mode Detection Using GPS Data and Socioeconomic Attributes Based on a Random Forest Classifier
Travel Mode Detection Using GPS Data and Socioeconomic Attributes Based on a Random Forest Classifier
复制标题
基于随机森林分类器的使用 GPS 数据和社会经济属性的出行模式检测
DOI：
10.1109/tits.2017.2723523
复制
发表时间：
2018-05
影响因子：
8.5
通讯作者：
Gao LJ
中科院分区：
文献类型：
--
作者：
Wang Bao;Gao Linjie;Juan Zhicai;Gao LJ
在过去的几年里，全球通过基于智能手机的旅行调查收集大规模GPS数据的数量迅速增长，随之而来的是交通模式检测受到了极大的关注。从基于准则的规则到机器学习技术，大量的方法被用来识别出行方式。然而，有限的样本量，不足的特征选择和解决混淆模式，这留下了改进的空间不太重视。因此，本文试图开发和评估一个随机森林分类器结合基于规则的方法来检测六种出行方式（地铁，步行，自行车，电动自行车，公共汽车和汽车）。从22个变量的初始列表中选择7个GPS相关变量作为特征集。因此，超过98%的地铁出行被正确识别，其余5种模式的分类的总体准确率高达93.11%。超过85%的行程被成功地确定为每一种模式，除了巴士。更重要的是，研究结果表明，社会经济属性数据可以显着提高对电动自行车的预测，并解决公共汽车和汽车模式之间的混淆。ROC曲线的使用为随机森林的优良分类能力提供了统计学上的证明。此外，与两个代表性的分类器的比较表明，随机森林分类器的适用性，包括多源属性的出行方式检测。
The past few years have witnessed the rapid growth in the collection of large-scale GPS data via smartphone-based travel surveys around the world, following which transportation modes detection received significant attention. A mass of methods varying from Criteria-based rules to Machine Learning technology were employed to recognize the travel modes. However, the limited sample size, deficient feature selection and the less emphasis on addressing confusion modes, which leave room for improvement. This paper therefore sought to develop and evaluate a Random Forest classifier combined with a rule-based method to detect six travel modes (subway, walking, bicycle, e-bike, bus and car). Seven GPS-related variables are selected as feature set from the initial list of 22 variables. Consequently, more than 98% subway trips were correctly identified and the overall accuracy of the rest five modes classification is obtained as high as 93.11%. More than 85% trips were successfully identified for each mode except for the bus. More importantly, results show that socioeconomic attributes data could significantly improve the prediction of e-bike and address the confusion between bus and car modes. The employment of ROC curve provides a statistical proof to the excellent classification capacity of Random Forest in this study. Besides, the comparison with two representative classifiers demonstrates the applicability of Random Forest classifier for travel modes detection incorporating multi-source attributes.
登录
查看更多内容
DOI：
10.1016/s1088-467x(97)00008-5
发表时间：
1997-05
期刊：
Intell. Data Anal.
影响因子：
--
作者：
M. Dash;Huan Liu
通讯作者：
M. Dash;Huan Liu
DOI：
10.1016/j.compenvurbsys.2015.04.001
发表时间：
2015-11
期刊：
Comput. Environ. Urban Syst.
影响因子：
--
作者：
T. K. Rasmussen;Jesper Bláfoss Ingvardson;Katrín Halldórsdóttir;O. A. Nielsen
通讯作者：
T. K. Rasmussen;Jesper Bláfoss Ingvardson;Katrín Halldórsdóttir;O. A. Nielsen
DOI：
--
发表时间：
2007
期刊：
--
影响因子：
--
作者：
Young-Ji Byon;B. Abdulhai;A. Shalaby
通讯作者：
Young-Ji Byon;B. Abdulhai;A. Shalaby
DOI：
10.1109/tits.2016.2516252
发表时间：
2016-02
影响因子：
8.5
作者：
Behrang Assemi;Hamid Safi;M. Mesbah;L. Ferreira
通讯作者：
Behrang Assemi;Hamid Safi;M. Mesbah;L. Ferreira
DOI：
10.1007/978-1-4419-9326-7_5
发表时间：
2012-01-01
期刊：
ENSEMBLE MACHINE LEARNING: METHODS AND APPLICATIONS
影响因子：
--
作者：
Cutler, Adele;Cutler, D. Richard;Stevens, John R.
通讯作者：
Stevens, John R.