基于残差灰色估计交通事故数量挖掘算法仿真

Residual Grey Estimate Based Algorithm Simulation of Traffic Accidents Number Mining

在交通事故优化预测的研究中,交通事故量是根据历史数据进行挖掘推断的,不同历史阶段的数据对挖掘模型的影响程度存在差异,一旦历史数据时间间隔过长,将造成基础决策数据跨度较大,形成数据冗余干扰。传统的挖掘算法模型一旦受到这种大跨度的时间数据属性的干扰,将造成挖掘数据时间属性存在较大偏差,数据冲突加剧,导致计算的失准。提出了一种残差灰色估计算法用于交通事故发生数量的挖掘。将历史数据进行有序处理,建立残差灰色估计数学模型。通过估计状态转移方法,对预测误差进行补偿。克服了传统算法的弊端。实验证明,上述算法能够避免由于历史数据时间过长造成的预测时间偏差的缺陷,保证了预测的准确率。

In the research of optimizing the prediction for traffic accidents, the number of the traffic accidents was mined and deduced based on the historical data. A residual grey estimation algorithm was put forward in this paper to mine the number of traffic accidents. The history data were processed and the residual grey estimation mathematical model was established. By estimating the state transition method, the prediction error was compensated, o- vercoming the shortcomings of the traditional algorithm. Experimental results show that the algorithm can avoid the defect of prediction time deviation due to the too long historical data time, and ensure the accuracy of the prediction.