An Analysis of User Transportation Mode Base on Mobility Behavior

• Main Authors: Cing-Hong Ye, 葉擎宏
• Other Authors: Jenq-Muh Hsu
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/46365458169266096942

碩士 === 國立嘉義大學 === 資訊工程學系研究所 === 101 === With the rapid development of Information Technology, the Global Positioning System (GPS) is widely and freely used to record the various kinds of path and trajectory for people. Therefore, the GPS-related applications have become much popular in our daily lives. However, it is an important issue to analyze and predict the user behaviors among the trajectory analysis from the original GPS data. Besides, there are many erroneous records of GPS data affecting the precision of GPS trajectories which may destroy the continuity of the trajectory, velocity, acceleration of the GPS trajectory when we identify the transportation mode from GPS trajectory. It should be fixed the unreasonable information before using the of GPS trajectory and then the feature extraction of GPS trajectory will be enhance the quality of features to classify different transportation modes based on user behaviors. By the way, this thesis try to find a way for extracting the mobility features from GPS trajectory and adopts the inference algorithms, decision tree and logistic regression model, for precisely identify the transport modes.