摘 要
城市交通诱导系统是智能交通系统(ITS: Intelligent Transport System)的一个重要组成部分,诱导系统的实现基础是对交通流数据进行有效地处理。其中包括交通流的短时预测、交通状况的拥堵判断以及个性化的诱导服务等。
首先,在实际的应用中,通过对交通流数据的预测,可以获知未来一段时刻内路网中的交通发展趋势。但实时性和准确性往往不可兼得。为了解决这个问题,本文提出一种结合周相似特性的短时交通流的分形预测方法,并对该方法的最大预测步长进行了探讨。
其次,以杭州市实际数据进行实例计算,达到了预期的效果。证明所提出的理论和算法的可行性和准确性。
最后 分别简单介绍了数据挖掘以及模式识别技术、行使路线诱导技术和多目标个性化行驶路线获取常用算法。
关键词:城市智能交通诱导系统 短时预测 分形理论 个性化行使路线
ABSTRACT
Traffic Guidance System plays an important role in the Intelligent Transport System, and the key to its establishment is whether traffic flow parameters can be dealt with effectively. Among them there are short-time traffic flow prediction、traffic condition judgments and individual guidance service and so on.
Firstly, in practical application, future traffic evolution trend could be acquired via forecasting traffic flow data. But the real-time performance and accuracy couldn’t be obtained simultaneous. To solve this problem, this paper puts forward a forecasting model based on fractal and weekly-similarly. furthermore, how many time step of this method is studied.
Secondly, Taking the actual figures of Hangzhou to calculate, the results was coherent with our expectation. Hence, proving the the theory and way of calculation both valid and reliable.
Finally,Were briefly introduced data mining and pattern recognition technology, the exercise
of multi-objective route guidance technology and personalized traffic routes for common algorithms.
Keywords:Urban Traffic Guidance System short-time prediction fractal theory individual vehicle path