[1]霍嘉男,成卫,李冰.基于多特征数据融合的城市道路行程速度预测[J].深圳大学学报理工版,2023,40(2):195-202.[doi:10.3724/SP.J.1249.2023.02195]
　HUO Jianan,CHENG Wei,and LI Bing.Urban road travel speed prediction based on multi-feature data fusion[J].Journal of Shenzhen University Science and Engineering,2023,40(2):195-202.[doi:10.3724/SP.J.1249.2023.02195]
点击复制

基于多特征数据融合的城市道路行程速度预测()
分享到：

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第40卷
期数:
2023年第2期
页码:
195-202
栏目:
交通物流
出版日期:
2023-03-15

文章信息/Info

Title:
Urban road travel speed prediction based on multi-feature data fusion
文章编号:
202302009
作者:
霍嘉男;  成卫;  李冰
昆明理工大学交通工程学院，云南昆明 650504
Author(s):
HUO Jianan;  CHENG Wei;  and LI Bing
Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650504, Yunnan Province, P.R.China
关键词:
智能交通; 多特征数据; 时间序列分析：速度预测; 长短期记忆神经网络; 深度学习
Keywords:
intelligent transportation;  multi-feature data;  time series analysis;  speed prediction;  long short-term memory (LSTM) neural network;  deep learning
分类号:
U491；TP391
DOI:
10.3724/SP.J.1249.2023.02195
文献标志码:
A
摘要:
城市道路速度预测有助于引导驾驶人选择较为畅通的路径，减少等待时间，提高出行效率．城市交通状况受到多种因素影响，考虑多种交通流特征数据与天气数据，建立基于长短期记忆（long short-term memory， LSTM）循环神经网络的道路行程速度预测组合模型．选取中国西安市南二环附近区域的滴滴出行浮动车数据，通过提取数据集的交通流特征（速度、流量、加速度和停车次数）和天气特征（温度、湿度、天气和风速）对道路行程速度进行预测．结果表明，与未加入外部特征的LSTM模型、误差逆传播（back propagation， BP）算法神经网络及支持向量回归（support vector regression， SVR）模型相比，融合多特征数据的组合模型平均绝对误差、均方误差和决定系数分别为2.695、13.838 和0.771，置信区间为（-1.235， 1.795），均优于其他模型，具有更高的精度和稳定性．
Abstract:
Urban road speed prediction is helpful to guide drivers to choose unimpeded routes, reduce waiting time and improve travel efficiency. Urban traffic conditions are affected by many factors. Based on the consideration of various traffic flow characteristic data and weather data, a combined model of road travel speed prediction based on long short-term memory (LSTM) cyclic neural network is established. The Didi floating car data in the area around the South Second Ring Road of Xi’an city are selected to predict the road travel speed by extracting the traffic flow characteristics (speed, flow, acceleration and stopping times) and weather characteristics (temperature, humidity, weather and wind speed) of the data set. The results show that compared with LSTM model, BP neural network model and SVR model without external features, the mean absolute error, mean square error and determination coefficient of the combined model with multi-feature data are 2.695, 13.838 and 0.771, and the confidence interval of (-1.235, 1.795) is better than other models. The combined model has higher accuracy and stability.

参考文献/References:

［1］ 陈亮，王金泓，何涛，等．基于SVR的区域交通碳排放预测研究［J］．交通运输系统工程与信息，2018，18（2）：13-19．
CHEN Liang, WANG Jinhong, HE Tao, et al. Forecast study of regional transportation carbon emissions based on SVR [J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(2): 13-19.(in Chinese)
［2］ 董洁霜，方天源，周亦威．基于ARIMA模型的城市路网交通运行指数预测研究［J］．智能计算机与应用，2021，11（12）：165-170．
DONG Jieshuang, FANG Tianyuan, ZHOU Yiwei. Research of prediction on urban road network traffic operation index based on ARIMA model [J]. Intelligent Computer and Applications, 2021, 11(12): 165-170.(in Chinese)
［3］ KRANTI K, PARID M, KATRYAI V K. Short term traffic flow prediction for a non urban highway using artificial neural network [J]. Procedia - Social and Behavioral Sciences, 2013, 104: 755-764.
［4］ 马秋芳．改进PSO优化的BP神经网络短时交通流预测［J］．计算机仿真，2019，36（4）：94-98，323．
MA Qiufang. BP neural network short-term traffic flow prediction based on improved particle swarm optimization [J]. Computer Simulation, 2019, 36(4): 94-98, 323.(in Chinese)
［5］ 车国鹏，刘永红．遗传算法优化BP神经网络的交通流参数预测［J］．综合运输，2018，40（6）：64-67，108．
CHE Guopeng, LIU Yonghong. A prediction of traffic flow parameters based on BP neural network optimized by genetic algorithm [J]. China Transportation Review, 2018, 40(6): 64-67, 108.(in Chinese)
［6］ 唐克双，陈思曲，曹喻旻，等．基于Inception卷积神经网络的城市快速路行程速度短时预测［J］．同济大学学报自然科学版，2021，49（3）：370-381．
TANG Keshuang， CHEN Siqu， CAO Yumin， et al. Short-term travel speed prediction for urban expressways based on convolutional neural network with inception module ［J］. Journal of Tongji University Natural Science， 2021， 49（3）： 370-381.（in Chinese）
［7］ 杨建喜，郁超顺，李韧，等．基于多周期组件时空神经网络的路网通行速度预测［J］．交通运输系统工程与信息，2021，21（3）：112-119，139．
YANG Jianxi, YU Chaoshun, LI Ren, et al. Traffic network speed prediction via multi-periodic-component spatial-temporal neural network [J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(3): 112-119, 139.(in Chinese)
［8］ 冯宁，郭晟楠，宋超，等．面向交通流量预测的多组件时空图卷积网络［J］．软件学报，2019，30（3）：759-769．
FENG Ning, GUO Shengnan, SONG Chao, et al. Multi-component spatial-temporal graph convolution networks for traffic flow forecasting [J]. Journal of Software, 2019, 30(3): 759-769.(in Chinese)
［9］ HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.
［10］ 马刚. 网约车用户出行行为分析及需求预测——以海口市为例［D］. 武汉：武汉大学，2020．
MA Gang. Online car-hailing users’ traveling behavior analysis and demand predicting: a Haikou City case study [D]. Wuhan: Wuhan University, 2020.(in Chinese)
［11］ LAI Yongxuan, ZHANG Kaixin, LIN Junqiang, et al. Taxi demand prediction with LSTM-based combination model [C]// IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom). Xiamen, China: IEEE, 2019: 944-950.
［12］ 卢家品. 数据驱动的车辆轨迹数据地图匹配方法［D］. 合肥：合肥工业大学，2020．
LU Jiapin. A data-driven map-matching method for driving trajectory data [D]. Hefei: Hefei University of Technology, 2020.(in Chinese)
［13］ 赵慧萍. 基于SVR和LSTM的公交车到站时间预测方法研究［D］. 大连：大连海事大学，2020．
ZHAO Huiping. Research on bus arrival time prediction method based on SVR and LSTM [D]. Dalian: Dalian Maritime University, 2020.(in Chinese)
［14］ 宋现敏，刘明鑫，马林，等. 基于极限学习机的公交行程时间预测方法［J］．交通运输系统工程与信息， 2018，18（5）：140-146， 154．
SONG Xianmin, LIU Mingxin, MA Lin, et al. Bus travel time prediction based on extreme learning machine [J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 140-146, 154.(in Chinese)

相似文献/References:

[1]吴鹏昆,吴园园,徐兵.ATIS环境下的多用户多准则交通均衡模型分析[J].深圳大学学报理工版,2015,32(2):213.[doi:10.3724/SP.J.1249.2015.02213]
　Wu Pengkun,Wu Yuanyuan,and Xu Bing.Multiclass and multicriteria stochastic traffic network equilibrium model based on ATIS[J].Journal of Shenzhen University Science and Engineering,2015,32(2):213.[doi:10.3724/SP.J.1249.2015.02213]
[2]黄中伟,庄焰,谭也平.城市车流加减速延误分析[J].深圳大学学报理工版,2002,19(3):60.
　HUANG Zhong-wei,ZHUANG Yan,TAN Ye-ping.Analysis for Acceleration and Deceleration Delay in Urban Traffic Flow[J].Journal of Shenzhen University Science and Engineering,2002,19(2):60.
[3]薛召杰,袁秋芳,季楷丰.基于缓冲时间的共享车位分配鲁棒方法[J].深圳大学学报理工版,2022,39(2):216.[doi:10.3724/SP.J.1249.2022.02216]
　XUE Zhaojie,YUAN Qiufang,and JI Kaifeng.Robust method of shared parking allocation based on buffer time[J].Journal of Shenzhen University Science and Engineering,2022,39(2):216.[doi:10.3724/SP.J.1249.2022.02216]

备注/Memo

备注/Memo:
Received: 2021-07-28; Revised: 2022-03-18; Accepted: 2022-04-13; Online (CNKI): 2022-05-24
Foundation: National Natural Science Foundation of China (52002161); Fundamental Research Project of Yunnan Province (202101AU070026); Talent Training Foundation of Kunming University of Science and Technology (KKZ3202002039)
Corresponding author: Lecture LI Bing. E-mail: bing.li@kust.edu.cn
Citation: HUO Jianan, CHENG Wei, LI Bing. Urban road travel speed prediction based on multi-feature data fusion [J]. Journal of Shenzhen University Science and Engineering, 2023, 40(2): 195-202.(in Chinese)
基金项目：国家自然科学基金资助项目（52002161）；云南省基础研究计划资助项目（202101AU070026）；昆明理工大学人培基金资助项目（KKZ3202002039）
作者简介：霍嘉男（1996—），昆明理工大学硕士研究生．研究方向：交通信息工程及控制．E-mail: kmust-hjn@163.com
引文：霍嘉男，成卫，李冰.基于多特征数据融合的城市道路行程速度预测［J］.深圳大学学报理工版，2023，40（2）：195-202.
更新日期/Last Update: 2023-03-30