Traffic Safety Based On Context Awareness Computing

• Main Authors: CHEN,GUAN-JHIH, 陳冠至
• Other Authors: Liaw,Ji-Horng
• Format: Others
• Language: zh-TW
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/xmx476

碩士 === 聖約翰科技大學 === 資訊工程系碩士班 === 106 === In recent years, the vigorous development of the Internet of Things (IoT) has also seen more and more applications in traffic safety. In view of this, the issues of traffic safety in Taiwan are discussed in detail. Some measures are put forward that combine Internet of Things (IOT) and context-aware computing and standard. In this thesis, the dynamic Bayesian network is applied to traffic safety. Firstly, based on the statistics of traffic accidents in Taiwan over the past 6 years, the first four major items of traffic accidents in Taiwan are listed and the driver's four states are based on environmental factors that may affect the driver's condition, as well as the settings of the already popular sensor as a relevant node, to draw a dynamic Bayesian network diagram. After that, referring to the domestic and international papers and related works, we select the parameters that are in line with the simulation and finally evaluate the simulated results to prove that the driver's state assumption and the dynamic Bayesian network are feasible and accuracy. Future sensor applications in the automotive situation popularization, I hope this driver status assumption standard can be used as one of the relevant reference standard in Taiwan area.