Open government data mining and visualization : a case study of new year festival traffic accidents in Thailand | |
| Author | Baimatpuncho, Muhammad |
| Call Number | AIT RSPR no.IM-17-02 |
| Subject(s) | Data mining--Computer programs Visual communication Big data--Social aspects |
| Note | A research submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Research studies project report ; no. IM-17-02 |
| Abstract | Traffic accident considered as one of the major public health problem through out the world as listed by “The World Health Organization (WHO) “claiming around 1.27 million deaths and between 20 and 50 million injuries annually worldwide indicating that Namibia, Thailand and Iran, are the top listed countries. Road accident epidemic has hampered Thailand’s economic and social profile for several decades as a major cause of death. Every year, more than ten thousand people lost their lives on the roads or at the hospital during treatment. According to the dataset, the number of traffic accidents during New Year festivals in Thailand has increased rapidly leading to more number of cases of deaths and injuries. There is lack of proper treatment and preventive measures that can be implemented to handle the traffic accident issues in Thailand. Therefore, to minimize the problem this study will analyse the important causes of accident and provide the result in the form of data visualization via interactive web application. Users can use the application and get the visualize result of the accident analysed data as per their input criteria as well as use the data mining result to prepare preventive majors taking into consideration the possible causes of accidents leading to death. The dataset is the open government data, collected by hospital around Thailand. The dataset contains the information on the accident aspect. Different data mining techniques, Naïve Bayes, K-Means and Association rules have been applied with the dataset to find out the important causes of traffic accidents. Comparing the accuracy result of the three different model, Weight by correlation and Naive Bayes classification techniques gave the best result which show that alcohol, transportation, vehicle types are the three main deciding factors of traffic accident victims to be cured or face death. The data obtained from traffic accidents have been analysed, classified and predicted and the result obtained by data mining has been applied into the interactive web application using data visualization techniques. The users such as police, hospital staff, and emergency team can access the application to get more, clear information on the accident and condition leading to death cases. The analyse result help users to prepare and plan proper preventive major, necessary medical equipment and other necessary support that might be needed during the time of emergency. |
| Year | 2017 |
| Corresponding Series Added Entry | Asian Institute of Technology. Research studies project report ; no. IM-17-02 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Vatcharaporn Esichaikul; |
| Examination Committee(s) | Chutiporn Anutariya;Teerawat Issariyakul; |
| Scholarship Donor(s) | Royal Thai Government Fellowship; |
| Degree | Research studies project report (M. Sc.) - Asian Institute of Technology, 2017 |