Please wait a minute...
Tsinghua Science and Technology  2021, Vol. 26 Issue (4): 403-416    doi: 10.26599/TST.2020.9010014
Transportation Mode Identification with GPS Trajectory Data and GIS Information
Ji Li(),Xin Pei(),Xuejiao Wang(),Danya Yao*(),Yi Zhang(),Yun Yue()
Department of Automation, Tsinghua University.
National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing 100084, China.
National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data (NEL-PSRPC), Beijing 100041, China.
Download: PDF (5926 KB)      HTML
Export: BibTeX | EndNote (RIS)      


Global Positioning System (GPS) trajectory data can be used to infer transportation modes at certain times and locations. Such data have important applications in many transportation research fields, for instance, to detect the movement mode of travelers, calculate traffic flow in an area, and predict the traffic flow at a certain time in the future. In this paper, we propose a novel method to infer transportation modes from GPS trajectory data and Geographic Information System (GIS) information. This method is based on feature extraction and machine learning classification algorithms. While using GIS information to improve inference accuracy, we ensure that the algorithm is simple and easy to use on mobile devices. Applied to GeoLife GPS trajectory dataset, our method achieves 91.1% accuracy while inferring transportation modes, such as walking, bike, bus, car, and subway, with random forest classification algorithm. GIS features in our method improved the overall accuracy by 2.5% while raising the recall of the bus and subway transportation mode categories by 3.4% and 18.5%. We believe that many algorithms used in detecting the transportation modes from GPS trajectory data that do not utilize GIS information can improve their inference accuracy by using our GIS features, with a slight increase in the consumption of data storage and computing resources.

Key wordstransportation mode      Global Positioning System (GPS)      Geographic Information System (GIS)      random forest     
Received: 16 October 2019      Published: 12 January 2021
Fund:  National Key Basic Research and Development Program of China(2017YFC0820502);Director Foundation Project of National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data (PSRPC), and the National Natural Science Foundation of China(61673233)
Corresponding Authors: Danya Yao     E-mail:;;;;zhyi@;
About author: Ji Li received the BS degree from Huazhong University of Science and Technology, China in 2006, and the MS degree from Peking University, China in 2014. He is currently a PhD candidate at the Department of Automation, Tsinghua University, China. He has participated in several research projects granted from MOST, NSFC, etc. His research interests include Intelligent Transportation System (ITS) and data-driven traffic safety analysis.|Xin Pei received the BEng and MEng degrees from Tsinghua University, China in 2005 and 2007, respectively, and the PhD degree from the University of Hong Kong in 2011. She is currently an associate professor at the Department of Automation, Tsinghua University. Her current research interests include road safety evaluation and driving behavior analysis. She is the Principal Investigator (PI)/co-PI of 3 road safety related NSFC projects. She has published more than 50 SCI/EI indexed papers, especially, there are 7 papers published on the Journal of Accident Analysis and Prevention, which is a top journal for road safety analysis.|Xuejiao Wang received the PhD degree from the Tsinghua University in 2018. She is currently an engineer in the National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data (NEL-PSRPC). Her research interests include deep learning, computational intelligence, and design of system engineering|Danya Yao received the BEng, MEng, and PhD degrees from Tsinghua Unversity in 1988, 1990, and 1994, respectively. He is currently a professor at Tsinghua University. His active research areas include vehicle infrastructure cooperation systems, advanced detection technology, and systems engineering. He has published more than 100 papers. He is the PI/co-PI of more than 5 national research programs, including 863 program, 973 program, and NSFC project. He was ever the chief expert of the National High-Tech Research and Development Program Research of China on Key Technologies of Intelligent Vehicle-Infrastructure Co-operation System.|Yi Zhang received the BEng and MEng degrees from Tsinghua University, China in 1986 and 1988, respectively, and the PhD degree from the University of Strathclyde, UK in 1995. He is currently a professor in control science and engineering at Tsinghua University. His main research interests include intelligent transportation systems, intelligent vehicle-infrastructure cooperative systems, analysis of urban transportation systems, urban road network management, traffic data fusion and dissemination, urban traffic control and management, advanced control theory and applications, advanced detection and measurement, and systems engineering.|Yun Yue received the BS degree from ChangAn University, China in 2004, and the MS and PhD degrees from Tsinghua University, China in 2011 and 2019, respectively. She is currently a postdoctor in the Department of Automation, Tsinghua University. Her research interests include road safety evaluation, traffic safety simulation, and travel behavior analysis.
Cite this article:

Ji Li,Xin Pei,Xuejiao Wang,Danya Yao,Yi Zhang,Yun Yue. Transportation Mode Identification with GPS Trajectory Data and GIS Information. Tsinghua Science and Technology, 2021, 26(4): 403-416.

URL:     OR

Fig. 1 A bus GPS trajectory segment obtained from GeoLife dataset.
Fig. 2 A subway GPS trajectory segment obtained from GeoLife dataset.
Fig. 3 Number of trajectories of five transportation modes.
Fig. 4 Distribution of time duration of all trajectories.
Fig. 5 Distribution of duration of all intervals between every two adjacent data points.
Fig. 6 Distribution of average speed.
Fig. 7 Distribution of 85th percentile of speed.
Fig. 8 Distribution of speed variance.
Fig. 9 Distribution of acceleration variance.
Fig. 10 Distribution of average heading change speed.
Fig. 11 Distribution of 85th percentile of heading change speed.
Fig. 12 Distribution of heading change speed variance.
Fig. 13 Distribution of straight rate.
Fig. 14 Distribution of stop rate.
Fig. 15 Ratio of low-speed points near bus station.
Fig. 16 Distribution of ratio of low-speed points near subway station.
Fig. 17 Average value of Feature 14 of each transportation mode of trajectories that contain low-speed points.
Fig. 18 Average value of Feature 15 of each transportation mode of trajectories that contain low-speed points.
Classification algorithmTrain samples accuracyTest samples accuracy
XGboost 89.388.5
ANN 93.388.3
Table 1 Classification accuracy of six algorithms. (%)
InferenceRecall (%)
Ground truthBike2644028089.2
Precision (%)92.387.385.693.696.0-
Table 2 Confusion matrix of RF algorithm on test samples.
FeatureTrain samples accuracyTest samples accuracy
Table 3 Classification accuracy with different features using RF algorithm. (%)
InferenceRecall (%)
Ground truthBike2635028088.9
Precision (%)93.984.775.092.790.6-
Table 4 Confusion matrix of RF algorithm with Features 1-11.
InferenceRecall (%)
Ground truthBike2664026089.9
Precision (%)92.485.576.593.490.0-
Table 5 Confusion matrix of RF algorithm with Features 1-13.
[1]   Murakami E., Wagner D. P., and Neumeister D. M., Using global positioning systems and personal digital assistants for personal travel surveys in the United States, in Proc. of International Conference on Transport Survey Quality and Innovation, .
doi: 10.1109/CCC.2009.17
[2]   Murakami E. and Wagner D. P., Can using global positioning system (GPS) improve trip reporting? Transportation Research Part C: Merging Technologies, vol. 7, nos. 2&3, pp. 149-165, 1999.
[3]   Ashbrook D. and Starner T., Using GPS to learn significant locations and predict movement across multiple users, Personal and Ubiquitous Computing, vol. 7, no. 5, pp. 275-286, 2003.
[4]   Zheng Y., Liu L., Wang L., and Xie X., Learning transportation mode from raw GPS data for geographic applications on the web, in Proceedings of the 17th International Conference on World Wide Web, Beijing, China, 2008, pp. 247-256.
[5]   Zheng Y., Chen Y., Li Q., Xie X., and Ma W. Y., Understanding transportation modes based on GPS data for web applications, ACM Transactions on the Web, vol. 4, no. 1, pp. 1-36, 2010.
[6]   Wang B., Wang Y., Qin K., and Xia Q., Detecting transportation modes based on LightGBM classifier from GPS trajectory data, in Proceedings of 26th International Conference on Geoinformatics, Kunming, China, 2018, pp. 1-7.
[7]   Liu H. and Lee I., End-to-end trajectory transportation mode classification using Bi-LSTM recurrent neural network, in Proceedings of 12th International Conference on Intelligent Systems and Knowledge Engineering, Nanjing, China, 2017, pp. 1-5.
[8]   Xiao G., Juan Z., and Zhang C., Travel mode detection based on GPS track data and Bayesian networks, Computers, Environment and Urban Systems, vol. 54, pp. 14-22, 2015.
[9]   Brunauer R., Hufnagl M., Rehrl K., and Wagner A., Motion pattern analysis enabling accurate travel mode detection from GPS data only, in Proceedings of 16th International IEEE Conference on Intelligent Transportation Systems, The Hague, the Netherlands, 2013, pp. 404-411.
[10]   Xu C., Ji M., Chen W., and Zhang Z., Identifying travel mode from GPS trajectories through fuzzy pattern recognition, in Proceedings of Seventh International Conference on Fuzzy Systems and Knowledge Discovery, Yantai, China, 2010, pp. 889-893.
[11]   Stopher P., FitzGerald C., and Zhang J., Search for a global positioning system device to measure person travel, Transportation Research Part C: Emerging Technologies, vol. 16, no. 3, pp. 350-369, 2008.
[12]   Bantis T. and Haworth J., Who you are is how you travel: A framework for transportation mode detection using individual and environmental characteristics, Transportation Research Part C: Emerging Technologies, vol. 80, pp. 286-309, 2017.
[13]   Li H. F. and Wang W., The option model of traffic mode based on neural network, Journal of Highway and Transportation Research and Development, vol. 24, no. 7, pp. 132-136, 2007.
[14]   Chung E. H. and Shalaby A., A trip reconstruction tool for GPS-based personal travel surveys, Transportation Planning and Technology, vol. 28, no. 5, pp. 381-401, 2005.
[15]   Gong H., Chen C., Bialostozky E., and Lawson C. T., A GPS/GIS method for travel mode detection in New York City, Computers, Environment and Urban Systems, vol. 36, no. 2, pp. 131-139, 2012.
[16]   Bohte W. and Maat K., Deriving and validating trip purposes and travel modes for multi-day GPS-based travel surveys: A large-scale application in the Netherlands, Transportation Research Part C: Emerging Technologies, vol. 17, no. 3, pp. 285-297, 2009.
[17]   Tsui S. Y. A. and Shalaby A. S., Enhanced system for link and mode identification for personal travel surveys based on global positioning systems, Transportation Research Record, vol. 1972, no. 1, pp. 38-45, 2006.
[18]   Stenneth L., Wolfson O., Yu P. S., and Xu B., Transportation mode detection using mobile phones and GIS information, in Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, New York, NY, USA, 2011, pp. 54-63.
[19]   Biljecki F., Ledoux H., and Van Oosterom P., Transportation mode-based segmentation and classification of movement trajectories, International Journal of Geographical Information Science, vol. 27, no. 2, pp. 385-407, 2013.
[20]   Feng T. and Timmermans H. J., Transportation mode recognition using GPS and accelerometer data, Transportation Research Part C: Emerging Technologies, vol. 37, pp. 118-130, 2013.
[21]   Reddy S., Mun M., Burke J., Estrin D., Hansen M., and Srivastava M., Using mobile phones to determine transportation modes, ACM Transactions on Sensor Networks, vol. 6, no. 1, pp. 1-27, 2010.
[22]   Reddy S., Burke J., Estrin D., Hansen M., and Srivastava M., Determining transportation mode on mobile phones, in Proceedings of 12th IEEE International Symposium on Wearable Computers, Los Alamitos, CA, USA, 2008, pp. 25-28.
[23]   Bedogni L., Di Felice M., and Bononi L., Context-aware Android applications through transportation mode detection techniques, Wireless Communications and Mobile Computing, vol. 16, no. 16, pp. 2523-2541, 2016.
[24]   Su X., Caceres H., Tong H., and He Q., Online travel mode identification using smartphones with battery saving considerations, IEEE Transactions on Intelligent Transportation Systems, vol. 17, no. 10, pp. 2921-2934, 2016.
[25]   Su X.. Travel mode identification with smartphone sensors, PhD dissertation, The City University of New York, New York, NY, USA, 2017.
[26]   Fang S. H., Liao H. H., Fei Y. X., Chen K. H., Huang J. W., Lu Y. D., and Tsao Y., Transportation modes classification using sensors on smartphones, Sensors, vol. 16, no. 8, pp. 1324-1339, 2016.
[27]   Jeyakumar J. V., Lee E. S., Xia Z., Sandha S. S., Tausik N., and Srivastava M., Deep convolutional bidirectional LSTM based transportation mode recognition, in Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, Singapore, 2018, pp. 1606-1615.
[28]   Yu M. C., Yu T., Wang S. C., Lin C. J., and Chang E. Y., Big data small footprint: The design of a low-power classifier for detecting transportation modes, Proceedings of the VLDB Endowment, vol. 7, no. 13, pp. 1429-1440, 2014.
[29]   Stenneth L., Thompson K., Stone W., and Alowibdi J., Automated transportation transfer detection using GPS enabled smartphones, in Proceedings of 2012 15th International IEEE Conference on Intelligent Transportation Systems, Anchorage, AK, USA, 2012, pp. 802-807.
[30]   Web query interface for POI information in the area around a certain point in China, , 2020.
[31]   Breiman L., Friedman J. H., Olshen R. A., and Stone C. J., Classification and Regression Trees. Boston, MA, USA: Wadsworth International Group, 1984.
[32]   Breiman L., Random forests, Machine Learning, vol. 45, no. 1, pp. 5-32, 2001.
[33]   Freund Y., Schapire R., and Abe N., A short introduction to boosting, Journal-Japanese Society For Artificial Intelligence, vol. 14, no. 5, pp. 771-780, 1999.
[34]   Chen T. and Guestrin C., XGboost: A scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 785-794.
[35]   Ke G., Meng Q., Finley T. W., Wang T., Chen W., Ma W., Ye Q., and Liu T., LightGBM: A highly efficient gradient boosting decision tree, in Proceedings of Advances in Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 3146-3154.
[36]   Srivastava N., Hinton G., Krizhevsky A., Sutskever I., and Salakhutdinov R., Dropout: A simple way to prevent neural networks from overfitting, The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
[1] Wei Jiang, Junyu Lin, Huiqiang Wang, Shichen Zou. Hybrid Semantic Service Matchmaking Method Based on a Random Forest[J]. Tsinghua Science and Technology, 2020, 25(6): 798-812.
[2] . Agent-Based Evacuation Model Incorporating Fire Scene and Building Geometry[J]. Tsinghua Science and Technology, 2008, 13(5): 708-714.
[3] . MEMS-Based Low-Cost Flight Control System for Small UAVs[J]. Tsinghua Science and Technology, 2008, 13(5): 614-618.
[4] . Fire Spread Model for Old Towns Based on Cellular Automaton[J]. Tsinghua Science and Technology, 2008, 13(5): 736-740.