| 基于实测数据评估交通事件检测中神经网络应用性的研究 |
| |
| 引用本文： | 沈晓蓉,王川久,郝佳,范跃祖,孙先仿.基于实测数据评估交通事件检测中神经网络应用性的研究[J].公路交通科技,2005,22(9):127-129,145. |
| |
| 作者姓名： | 沈晓蓉 王川久 郝佳 范跃祖 孙先仿 |
| |
| 作者单位： | 1. 北京航空航天大学自动化科学与电气工程学院,北京,100083
2. 北京宽广电信高技术发展有限公司,北京,100083 |
| |
| 基金项目： | 北京市自然科学基金资助（4032014）、北京市教育委员会共建项目建设计划资助. |
| |
| 摘 要： | 神经网络为交通事件自动检测技术摆脱传统方法探测率低、误报率高的状况提供了新的解决思路。在以往局限于仿真数据研究的基础上,本文利用I-880数据库实测交通事件数据对神经网络在交通事件自动检测中的实际应用进行了研究,结果表明:神经网络应用于交通事件自动检测技术中,具有较高的探测率和较低的误报率,但该算法可移植性较差,在实际应用中要予以考虑。
|
| 关 键 词： | 神经网络 交通事件检测 可移植性 I-880数据库 |
| 文章编号： | 1002-0268（2005）09-0127-03 |
| 收稿时间： | 2004-06-18 |
| 修稿时间： | 2004-06-18 |
Research on Applicability of Neural Network with Field Data of Automatic Traffic Incident Detection |
| |
| SHEN Xiao-rong,WANG Chuan-jiu,HAO Jia,FAN Yue-zu,SUN Xian-fang.Research on Applicability of Neural Network with Field Data of Automatic Traffic Incident Detection[J].Journal of Highway and Transportation Research and Development,2005,22(9):127-129,145. |
| |
| Authors: | SHEN Xiao-rong WANG Chuan-jiu HAO Jia FAN Yue-zu SUN Xian-fang |
| |
| Institution: | 1. Automation Science and Electrical Engineering College, Beijing University of Aeronautics and Astronautics, Beijing 100083, China; 2.Beijing Kuan Guang Teleeom Hitech Development. Co.Ltd, Beijing 100083, China |
| |
| Abstract: | Neural network provides a new method to solve the problem of low detection rate and high false alarm for Automatic Incident Detection (ADD) technology. Based on the similar researches limited with simulation data, the paper evaluates neural network application with field traffic incidents data of I-880 database. The result shows that neural network has high detection rate and low false alarm rate. However, the algorithm is poor in transferability, which needs to be considered in field application. |
| |
| Keywords: | Neural network Traffic incident detection Tiansferability I-880 database |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
