基于Hadoop和并行BP网络的打车需求量预测系统研究
    点此下载全文
引用本文:孟 哲,余 粟.基于Hadoop和并行BP网络的打车需求量预测系统研究[J].计算技术与自动化,2022,(3):117-120
摘要点击次数: 105
全文下载次数: 0
作者单位
孟 哲,余 粟 (上海工程技术大学 电子电气工程学院上海 200000) 
中文摘要:一个良好的打车需求量预测系统可以帮助完善城市的交通系统,帮助城市更高效地进行出租车的调度。基于Hadoop设计并搭建了一个打车需求量预测系统。除此之外,针对传统BP神经网络收敛速度慢的缺点,提出了一种基于MapReduce的并行BP神经网络,并将其用作系统的预测模型对打车需求量进行预测。根据实验结果,提出的系统能良好地对城市内某一区域一天内的打车需求量进行预测。
中文关键词:打车需求量  Hadoop  MapReduce  BP神经网络
 
Research on Taxi Demand Forecasting System Based on Hadoop and Parallel BP Network
Abstract:A good taxi demand forecasting system can help improve the city's transportation system and help the city dispatch taxis more efficiently. This paper discusses the theory of building a taxi demand prediction system based on Hadoop, then designs and builds a taxi demand prediction system. In addition, in view of the slow convergence speed of traditional BP neural network, a parallel BP neural network based on MapReduce is proposed in this paper. And it is used as the prediction model of the system to predict the taxi demand. According to the experimental results, the system proposed in this paper can predict the taxi demand in a certain area of the city in a day effectively.
keywords:taxi demand  Hadoop  MapReduce  BP neural network
查看全文   查看/发表评论   下载pdf阅读器