Knowledge acquisition by decision trees from dangerous scenes at car-driving
The objective of this study is to obtain predictive rules and knowledge regarding dangerous scenes that drivers encounter when driving a car. First, dangerous objects and elements in scenes included in still and moving pictures are extracted as classes and attributions. Then, decision trees are made using those data, and their accuracy is examined through the K-cross validation method. In order to improve the accuracy, a data sort algorithm considering distributions of attributes and classes is proposed. Experiments are conducted to confirm that effective rules and knowledge can be obtained.
2012 IEEE SMC Hiroshima Chapter Young Researchers' Workshop Proceedings = 2012 IEEE SMC Hiroshima Chapter 若手研究会講演論文集
IEEE SMC Hiroshima Chapter
©Copyright by IEEE SMC Hiroshima Chapter. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting
republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
2012 IEEE SMC Hiroshima Chapter若手研究会, 2012年7月14日, 広島市立大学