Paper Infomation
Forecast of Short-term Traffic Flow in Chengdu City Based on Decision Tree Model
Full Text(PDF, 705KB)
Author: Jingdian Yang
Abstract: With the rapid increase in the population in the central area of Chengdu, congestion in a certain period has become one of the stubborn diseases that restrict the development of the city. By accurately predicting the short-term road traffic information in the future, it can effectively improve the traffic efficiency of vehicles in a specific period. In this paper, data training is carried out according to the collected relevant indicators, and a decision tree classification model is established. The model can be used to predict the traffic flow on the road in a short period of time based on the time of the road, weather, average speed, and other indicators, and then the relevant regulatory authorities can use the advanced new media today to push, so that the citizens can plan their trips reasonably.
Keywords: Traffic Jam, Machine Learning, Decision Tree, Prediction
References:
[1] 易斌,宋程,刘翰宁.基于大数据的交通拥堵影响因素关联性实证分析[J].交通与运输,2021,37(02):30-35.
[2] 郑苗,吕永艺.城市道路中智能交通应用研究[J].智能建筑与智慧城市,2021(03):130-131+137.
[3] 晏雨婵,白璘,武奇生,叶珍.基于多指标模糊综合评价的交通拥堵预测与评估[j].计算机应用研究,2019,36(12)
[4] 刘张,李坚,王超,蔡世民,唐明,黄琦,陈照辉. 基于复杂城市道路网络的交通拥堵预测模型[j]. 电子科技大学学报. 2016,45(01).
[5] 支野,王大珊,丛浩哲,饶众博. 道路交通事故数据深度挖掘技术与应用——以深圳市为例[j]. 城市交通. 2018,16(03).
[6] 薛红军,陈广交,李鑫民,顾理.基于决策树理论的交通流参数短时预测[j].交通信息与安全,2016,34(03).
[7] 于田. 基于机器学习的交通流缺失数据填补和短时交通流预测方法研究[D].北京交通大学,2019.