Transportation modes detection in Bangkok using GPS logger data and GIS data | |
| Author | Kunnaree Kritiyutanont |
| Call Number | AIT Thesis no.RS-15-11 |
| Subject(s) | Geographic information systems--Bangkok Transportation |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Remote Sensing and Geographic Information Systems |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. RS-15-11 |
| Abstract | Person trips and transportation mode surveys could be in multiple formats, such as telephone interviews and questionnaires. These data collecting rely on manual labelling of data after a survey, and thus, it requires more manpower, time and budget. However, the information technology has introduced advanced data collecting methods such as a mobile phone or a data logger device that can easily record travel time and location data of people. This kind of information plays an essential role in transportation surveying. GPS data can be used to find many features involved in travelling, but those data are need to process and find transportation modes used before further analysis. The main objectives of this study are to collect person’s trip data by using GPS logger devices and find suitable procedure for data collection and preparation, to detect and analyze transportation modes used in Bangkok using GPS logger and GIS data. Since the transportation modes in Bangkok are unique and various, there are many problems, such as traffic condition and complex of transportation network systems. So, it is hard to determine transportation modes. Therefore, GIS data is used to help detecting transportation modes that have specific routes and stations. Sample data was acquired from students from 4 different universities in Bangkok, they were asked to keep GPS logger devices for 1 week to collect person trip data. Random Forest Classifier was used for transportation modes detection. Modes considered in this study are walking, 2 wheels vehicles, 4 wheels vehicles, bus, skytrain, subway and boat. Moreover, activities of persons in a week were focused such as, stationary and modes transferring points. In conclusion, the transportation modes could be automatically detected using our algorithms. Moreover, it can be applied for other person trip data from mobile phone applications that can collect huge number of dataset. The output data can be used for further analysis and visualization. This will be very useful in transportation surveying and other related topics. |
| Year | 2015 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. RS-15-11 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Nagai, Masahiko |
| Examination Committee(s) | Nakamura, Shinichi;Surachet Pravinvongvuth |
| Scholarship Donor(s) | Royal Thai Government;AIT Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2015 |