Analysis of Injury Severity of Bicycle Accidents Using Non-parametric Association Rules

• Main Authors: Lu, Yu-Chieh, 盧郁潔
• Other Authors: Chang, Li-Yen Ph. D.
• Format: Others
• Language: zh-TW
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/77865475956288133210

碩士 === 國立嘉義大學 === 行銷與運籌研究所 === 99 === Traffic accidents often result in serious traffic congestion which not only causes excessive delay for road users but a great loss of productivity for the society. Therefore, traffic accidents have been a great concern for the public. Among these traffic accidents, bicycle accidents have not yet drawn considerably attention from the general public because bicycles are not regarded as a regular transportation mode. In 2007, 8,536 bicycle accidents occurred in Taiwan resulting in 141 people killed and 7982 people injured. With the increase of gasoline prices, the popularity of bicycle uses is expected to grow rapidly in a short period. Therefore, there is an increasing need to have a better understanding the characteristics of bicycle accidents and the factors resulting in severe injury for the bicyclists. To explore the factors resulting in severe injury, regression analysis has been extensively applied. However, most regression models have their own model assumptions and pre-defined underlying relationships between dependent and independent variables. If these assumptions are violated, the model could lead to erroneous estimations of injury likelihood. The association rules, one of the most widely applied data mining techniques, has been commonly employed in business administration, industry, and engineering. Association rules do not require any pre-defined underlying relationship between dependent variable and independent variables and has been shown to be an effective tool, particularly for dealing with prediction problems. This study collects the 2005-2007 bicycle accident data of three major cities in Taiwan. The findings by the association rules indicate that the bicyclist characteristics, environmental factors, road characteristics, driver/vehicle action prior to accident are associated with injury severity of bicycle accidents.