基于粗糙集-模糊识别技术的交通流状态识别算法研究

Study on Auto-Identification Algorithm of Traffic Flow State Based on Rough Set and Fuzzy Theory

构建了基于粗糙集约简的交通流状态模糊识别算法,利用粗糙集属性约简技术在多个交通流参数中获得反映交通流变化的表征变量及其重要度值,在此基础上采用模糊识别方法构建交通流状态识别算法,算法针对三种交通流状态的识别,包括正常状态、常发性拥堵状态、偶发性拥堵状态.利用实际城市快速路的数据,以识别率和误报率为衡量指标,将文中的算法与其他算法进行了对比研究,结果表明在同样的误报率水平下可以得到更高的识别率.

In this paper,we first used rough set theory to get variables reflecting traffic flow changing and their weight coefficients.Then we used fuzzy recognition technique to establish traffic flow state identification algorithm,which can detect three traffic patterns： normal state,recurrent congestion and traffic incident.In the end,we used FIR-IR curve to evaluate the performance of this algorithm with other two auto-identification algorithms.The result shows that this algorithm has better performance.