基于长短期记忆神经网络模型的共享单车短时需求量预测  

Short-term Demand Forecasting of Shared Bicycles Based on Long Short-term Memory Neural Network Model

作　　者：曹旦旦 范书瑞[1] 张艳[1] 夏克文[1] CAO Dan-dan;FAN Shu-rui;ZHANG Yan;XIA Ke-wen(School of Electronics and Information Engineering,Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]河北工业大学电子息信工程学院,天津300401

出　　处：《科学技术与工程》2020年第20期8344-8349,共6页Science Technology and Engineering

基　　金：国家自然科学基金联合基金(U1813222);河北省重点研发计划(19210404D,20351802D);河北省高等学校科学技术研究重点项目(ZD2019010);教育部产学合作协同育人项目(201801335014);河北省研究生创新项目。

摘　　要：共享单车具有很强的流动性和高随机性,为了更加准确地预测某区域内每小时的单车使用数量,通过爬取纽约市Citi Bike共享单车的天气特征数据信息,并分析时间因子、气象因子等对单车需求量的影响;采用长短期记忆(long short-term memory,LSTM)神经网络模型预测共享单车的短期需求量,并与传统的循环神经网络(recurrent neural network,RNN)和BP(back-propagation)神经网络模型预测结果进行比较。实验结果表明:影响单车需求量的主要因素包括温度、节假日、季节以及早晚高峰时间段等因素;与传统BP神经网络算法和循环神经网络RNN算法相比,LSTM鲁棒性高,泛化能力强,且预测结果曲线与真实结果曲线相吻合;预测精度高(精确度为0.860)均方根误差最小(为0.090),误差小。可见LSTM模型可以用来对共享单车的短时需求量进行预测。Shared bicycles have high mobility and randomness. In order to predict accurately on the bicycles usage amount per hour in one area, and crawling the weather characteristics data of bicycles shared by Citi Bike in New York City, the influence of time and meteorological factors on the demand for bicycles were analyzed. The long short-term memory(LSTM) neural network model was used to predict the short-term bicycles demand for shared bicycles. Then the model was compared with the traditional recurrent neural network(RNN) and back-propagation network(BP) neural network model prediction results. The experimental results show that the main factors affecting the demand for bicycles include temperature, holidays, seasons and morning and evening peak time periods. Compared with traditional BP neural network algorithm and cyclic neural network RNN algorithm, LSTM has high robustness and strong generalization ability, and the prediction result curve is consistent with the real result curve. The prediction accuracy is high(Accuracy=0.860), the root mean square error is the smallest(RMSE=0.090), and the error is small. It can be seen that the LSTM model can be used to predict the short-term demand for shared bicycles.

关 键 词：共享单车 网络爬虫 数据分析 长短期记忆(LSTM)神经网络 需求预测 

分 类 号：TU448[建筑科学—岩土工程]