中文摘要：

为了提高短时交通流预测的精确性,提出了一种基于云模型的短时交通流智能预测方法。该方法利用云模型拟合交通流,分别用历史交通流和当前交通流建立历史云和当前云,共同生成预测云,用来预测交通流。结合广州市某交叉口交通流量采集数据,进行了仿真试验,以平均绝对误差（MAE）和平均绝对百分比误差（MAPE）两个指标来衡量预测效果,结果表明了该预测方法具有较高的预测精度。该方法既考虑到交通流历史变化,又顾及交通流实时变化,同时将交通流做整体性处理,很好地避开了噪声引起的预测误差问题,兼顾了预测精度和实时性的要求。

英文摘要：

In order to improve the prediction precision of the short-term traffic flow,a prediction method of short-term traffic flow based on cloud model is proposed by artificial intelligence with uncertainty.The traffic flow is fit by cloud model.The historical cloud and the present cloud are built by historical traffic flow and present traffic flow.The forecast cloud is produced by both clouds.Then,combining with the volume of the short-term traffic flow of an intersection in Guangzhou city,the model is calculated and simulated through programming.Max absolute error（MAE） and mean absolute percent error（MAPE） are used to estimate the effect of prediction.The simulation results indicate that this prediction method is effective and advanced.The change of the historical and real time traffic flow is taken into account in this method.Because the short-term traffic flow is dealt with as a whole,the error of prediction is avoided.The prediction precision and real-time prediction are satisfied.