As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
The purpose of the exploratory research is to employ a classification-based data mining technique to develop a vehicle accident prediction model. Data from 2014 to 2016 was collected from the open government data of Taoyuan municipality, Taiwan, that contains five categories as the potential determinants of vehicle accident, namely temporal, environmental, human (drivers), vehicle, and miscellaneous. Each category contains various variables. The class has 11 values (e.g., head, neck, leg (foot), multiple wounds). The mining mechanism used was ID3 which is a classification-based technique. The dataset used contains 92,558 cases. Steps were conducted including data preparation, mining mechanism implementation, and validation. The results reveal that variables in human category holds the highest classification power and the environmental ones reveals the lowest. The overall prediction accuracy is 73.05%. The total number of rule discovered is 10226, of which 4088 are reliable that the conflict rate is no less than 0.5. Findings and discussions are also addressed.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.