Understanding Travel behaviour from Sparse GPS Data
Understanding travel behaviour and travel demand is of constant importance to transportation communities and agencies in every country. Nowadays, attempts have been made to automatically infer the modes of transport from positional data (such as GPS data) to significantly reduce the cost in time and budget of conventional travel diary surveys. Some limitations, however, exist in the literature, in aspects of data collection (sample size selected, duration of study, granularity of data, device type), data pre-processing (managing GPS errors, choice of modes, trip information generalisation, data labelling strategy), the classification method used and the choice of variables used for classification, track segmentation methods used (clustering techniques), and using transport network datasets. Therefore, this research attempts to fully understand these aspects and their effect on the process of inference of mode of transport. Furthermore, this research aims to solve a classiﬁcation problem of sparse GPS data into different transportation modes (car, walk, cycle, underground, train and bus). To address the data collection issues, we conduct studies that aim to identify the optimal sample size, study duration, and data collection rate that best suits the purpose of this study. As for the data pre-processing issues, we standardise guidelines for managing GPS errors and the required level of detail of the collected trip information. We also develop an online WebGIS-based travel diary that allows users to view, edit, and validate their track information to assure obtaining high quality information. After addressing the validation issues, we develop an inference framework to detect the mode of transport from the collected data. We ﬁrst study the variables that could contribute positively to this classiﬁcation, and statistically quantify their discriminatory power using ANOVA analysis. We then introduce a novel approach to carry out this inference using a framework based on Support Vector Machines (SVMs) classiﬁcation. The classification process is followed by a segmentation phase that identifies stops, change points and indoor activity in GPS tracks using an innovative trajectory clustering technique developed for this purpose. The final phase of the framework develops a network matching technique that verifies the classification and segmentation results by testing their obedience to rules and restrictions of different transport networks. The framework is tested using coarse-grained GPS data, which has been avoided in previous studies, achieving almost 90% accuracy with a Kappa statistic reﬂecting almost perfect agreement.
- Bolbol, A, Cheng, T and Tsapakis, I, 2012. A Spatio-Temporal Approach for Identifying the Sample Size for GPS-Based Travel Surveys: A Case Study of London’s Road Network. Journal of Transport Geography, Submitted (in review).
- Tsapakis, I, Turner, J, Cheng, T, Heydecker, B and Bolbol, A, 2012. Effects of Tube Strikes on Journey Times in the Transport Network of London. Transportation Research Record, TRB, National Research Council, Washington D.C, 2012.
- Bolbol, A, Cheng, T, Tsapakis, I & Haworth, J, 2012. Inferring hybrid transportation modes from sparse GPS data using a moving window SVM classification, Computers, Environment and Urban Systems, Available online 12 July 2012, ISSN 0198-9715,10.1016/j.compenvurbsys.2012.06.001. (http://www.sciencedirect.com/science/article/pii/S0198971512000543)
- Tsapakis, I Cheng, T & Bolbol, A, 2012. Impact of Weather Conditions on Macroscopic Urban Travel Times. Journal of Transport Geography. Manuscript submitted for publication.
- Tsapakis, I, Schneider, W H, Bolbol, A and Skarlatidou, A, 2011. Discriminant Analysis for Assigning Short-Term Counts to Seasonal Adjustment Factor Groupings. Transportation Research Record, TRB, National Research Council, Washington D.C, 2011.
- Bolbol, A, Cheng, T, Tsapakis, I and Chow, A, 2012. Sample Size Calculation for Studying Transportation Modes from GPS Data, Procedia - Social and Behavioral Sciences, Volume 48, 2012, Pages 3040-3050, ISSN 1877-0428, 10.1016/j.sbspro.2012.06.1271. (http://www.sciencedirect.com/science/article/pii/S1877042812030145)
- Tsapakis, I Cheng, T & Bolbol, A, 2012. Understanding Effects of Tube Strikes on Macroscopic and Link Travel Times. Transport Research Arena, Athens, April. Manuscript submitted for publication.
- Bolbol, A Cheng, T Skarlatidou, A & Tsapakis, I, 2011. A GIS-Machine Learning Approach for Inferring Travel Mode from Sparse GPS Data. Proceedings of 9th International Conference on Survey Methods in Transport (ISCTSC), Termas Puyehue, Chile, November 14-18, 2011.
- Bolbol, A. Cheng, T and Haworth, J, 2011. Using a Moving Window SVMs Classification to Infer Travel Mode from GPS Data. Geocomputation 2011, UCL, July.
- Bolbol, A. Cheng, T. Tsapakis, I. and Skarlatidou, A., 2011. Identifying Intermediary Modes from GPS Data. Presented at Association of American Geographers Annual Meeting, Seattle, Washington, April, 2011.
- Skarlatidou, A, Cheng, T, Hacklay, M and Bolbol, A, 2011. Investigating non-experts' trust perceptions in Spatial Decision Support Systems for public use. Presented at Association of American Geographers Annual Meeting, Seattle, Washington, April, 2011.
- Tsapakis, I, Cheng, T and Bolbol, A, 2011. Effect of Adverse Weather Conditions on Urban Speeds and Travel Time Reliability of Bus Lane and Non-Bus Lane Users. Presented at Association of American Geographers Annual Meeting, Seattle, Washington, April, 2011.
- Bolbol, A, Cheng, T, and Paracha, A, 2010. GEOTRAVELDIARY: Towards Online Automatic Travel Behaviour Detection. WebMGS: 1st International Workshop on Pervasive Web Mapping, Geoprocessing and Services, 2010, Politecnico di Milano, Como, Italy.
- Bolbol, A and Cheng, T, 2010. GPS Data Collection Setting For Pedestrian Activity Modelling. GISRUK 2010: Proceedings of Geographical Information Science Research UK Conference 2010, UCL, London.
Page last modified on 17 dec 13 14:25