【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。更多还原

【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.更多还原