基于組合模型的短時(shí)交通流量預(yù)測算法

芮蘭蘭; 李欽銘

doi:10.11999/JEIT150846

基于組合模型的短時(shí)交通流量預(yù)測算法

doi: 10.11999/JEIT150846

芮蘭蘭¹,
李欽銘¹

基金項(xiàng)目:

國家自然科學(xué)基金創(chuàng)新研究群體科學(xué)基金(61121061)，國家自然科學(xué)基金(61302078, 61372108)，北京高等學(xué)校青年英才計(jì)劃項(xiàng)目(YETP0476)

計(jì)量
- 文章訪問數(shù): 1802
- HTML全文瀏覽量: 187
- PDF下載量: 981
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2015-07-14
- 修回日期: 2016-01-08
- 刊出日期: 2016-05-19

Short-term Traffic Flow Prediction Algorithm Based on Combined Model

RUI Lanlan¹,
LI Qinming¹

Funds:

Funds for Creative Research Groups of China (61121061), The National Natural Science Foundation of China (61302078, 61372108), Beijing Higher Education Young Elite Teacher Project (YETP0476)

摘要

摘要: 交通流量預(yù)測是實(shí)現(xiàn)智能交通技術(shù)的核心問題，及時(shí)準(zhǔn)確地預(yù)測道路交通流量是實(shí)現(xiàn)動(dòng)態(tài)交通管理的前提，短時(shí)交通流量的預(yù)測是交通流量預(yù)測的重要組成部分。該文針對十字路口的短時(shí)交通流量預(yù)測問題設(shè)計(jì)了基于交通流量序列分割和極限學(xué)習(xí)機(jī)(Extreme Learning Machine, ELM)組合模型的交通流量預(yù)測算法(Traffic Flow Prediction Based on Combined Model, TFPBCM)。該算法首先采用K-means對交通流量數(shù)據(jù)在時(shí)間上進(jìn)行序列分割，然后采用ELM對各個(gè)序列進(jìn)行建模和預(yù)測。仿真實(shí)驗(yàn)證明，與單一的BP(Back Propagation)神經(jīng)網(wǎng)絡(luò)和ELM相比，該組合模型算法建模時(shí)間為BP的1/10, ELM建模時(shí)間的4倍，均方誤差為BP的1/50, ELM的1/20，該組合模型算法決定系數(shù)R2更接近于1，模型可信度更高。
- 短時(shí)交通流量 /
- K均值算法 /
- 極限學(xué)習(xí)機(jī) /
- 組合模型算法
Abstract: Traffic flow prediction is a key problem of realizing intelligent transportation technology. Forecasting traffic flow in time and accurately is the precondition to realize the dynamic traffic management. Short -term traffic flow prediction is an important part of traffic flow prediction. In this paper, the Traffic Flow Prediction Based on Combined Model (TFPBCM) based on traffic flow sequence partition and Extreme Learning Machine (ELM) is designed for the short time traffic flow forecasting. The algorithm divides the traffic flow into different patterns along a time dimension by K-means, and then models and forecasts for each pattern by ELM. The proposed algorithm is compared with Back Propagation (BP) and ELM. The combined model algorithm on modeling time is 1/10 of BP, but is 4 times ELM. Its MSE is 1/50 of BP and 1/20 of ELM. The combined model algorithms coefficient of detemination (R2 ) is close to 1, so the credibility of the model is higher than others.
- Short-term traffic flow /
- K-means algorithm /
- Extreme Learning Machine (ELM) /
- Traffic Flow Prediction Based on Combined Model (TFPBCM)

HTML全文

參考文獻(xiàn)(31)

蘭云. 短時(shí)交通流量預(yù)測研究[D]. [碩士論文], 西北工業(yè)大學(xué), 2002.

LAN Yun. The study on short time traffic flow prediction[D]. [Master dissertation], Northwestern Polytechnical University, 2002.

范騰騰. 城市道路交通流量短時(shí)預(yù)測研究[D]. [碩士論文], 北京交通大學(xué), 2012.

FAN Tengteng. The research of urban road traffic flow short-term prediction[D]. [Master dissertation], Beijing Jiaotong University, 2012.

覃明貴. 城市道路交通數(shù)據(jù)挖掘研究與應(yīng)用[D]. [博士論文], 復(fù)旦大學(xué), 2010.

QIN Minggui. Research and application on the urban traffic data mining[D]. [Ph.D. dissertation], Fudan University, 2010.

曹虹. 基于BP神經(jīng)網(wǎng)絡(luò)的交通流量預(yù)測[D]. [碩士論文], 長安大學(xué), 2012.

CAO Hong. Traffic flow prediction based on BP neural network[D]. [Master dissertation], Changan University, 2012.

曹煒. 基于BP神經(jīng)網(wǎng)絡(luò)的城市交通流量預(yù)測與路口分析[D]. [碩士論文], 昆明理工大學(xué), 2006.

CAO Wei. The city traffic flow prediction and cross analysis based on BP neural network[D]. [Master dissertation], Kunming University of Science and Technology, 2006.

尚寧, 覃明貴, 王亞琴, 等. 基于BP神經(jīng)網(wǎng)絡(luò)的路口短時(shí)交通流量預(yù)測方法[J]. 計(jì)算機(jī)應(yīng)用與軟件, 2006, 23(2): 32-33, 57.

SHANG Ning, QIN Minggui, WANG Yaqin, et al. A BP neural network method for short-term traffic flow forecasting on crossroads[J]. Computer Applications and Software, 2006, 23(2): 32-33, 57.

翟敏. 極限學(xué)習(xí)機(jī)的自適應(yīng)網(wǎng)絡(luò)結(jié)構(gòu)選擇方法研究[D]. [碩士論文], 西北大學(xué), 2014.

ZHAI Min. Research on adaptive network structure selection method for extreme learning machine[D]. [Master dissertation], Northwest University, 2014.

甘露. 極限學(xué)習(xí)機(jī)的研究與應(yīng)用[D]. [碩士論文], 西安電子科技大學(xué), 2014.

GAN Lu. Research and application of extreme learning machine[D]. [Master dissertation], Xidian University, 2014.

王智慧. BP神經(jīng)網(wǎng)絡(luò)和ELM算法研究[D]. [碩士論文], 中國計(jì)量學(xué)院, 2012.

WANG Zhi-hui. Research on BP neural networks and ELM Algorithms[D]. [Master dissertation], China Jiliang University, 2012.

張一. 基于卡爾曼濾波的短時(shí)交通流量預(yù)測模型研究[D]. [碩士論文], 沈陽工業(yè)大學(xué), 2014.

ZHANG Yi. Research of short-term traffic volume prediction based on kalman filtering[D]. [Master dissertation], Shenyang University of Technology, 2014.

羅向龍. 交通流量經(jīng)驗(yàn)?zāi)B(tài)分解與神經(jīng)網(wǎng)絡(luò)短時(shí)預(yù)測方法[J]. 計(jì)算機(jī)工程與應(yīng)用, 2010, 46(26): 212-214. doi: 10.3778/j.issn. 1002-8331.2010.26.066.

LUO Xianglong. Short-term traffic flow prediction method based on EMD and artificial neural network[J]. Computer Engineering and Applications, 2010, 46(26): 212-214. doi: 10.3778/j.issn.1002-8331.2010.26.066.

沈永增. 基于混沌粒子群優(yōu)化小波神經(jīng)網(wǎng)絡(luò)的短時(shí)交通流預(yù)測[J]. 計(jì)算機(jī)應(yīng)用與軟件, 2014, 31(6): 84-87. doi: 10.3969 /j.issn.1000-386x.2014.06.024.

SHEN Yongzeng. Short-time traffic flow forecast based on WNN optimised by CPSO[J]. Computer Applications and Software, 2014, 31(6): 84-87. doi: 10.3969/j.issn.1000-386x. 2014.06.024.

朱征宇. 一種結(jié)合SVM與卡爾曼濾波的短時(shí)交通流預(yù)測模型[J]. 計(jì)算機(jī)科學(xué), 2013, 40(10): 248-251.

ZHU Zhengyu. Short-term traffic flow forecasting model combining SVM and Kalman filtering[J]. Computer Science, 2013, 40(10): 248-251.

TCHRAKIAN T T, BASU B, and OMAHONY M. Real-time traffic flow forecasting using spectral analysis[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2): 519-526.

CHEN Syuanyi and CHOU Weiyao. Short-term traffic flow prediction using EMD-based recurrent Hermite neural network approach[C]. 15th International IEEE Conference on Intelligent Transportation Systems, Anchorage, 2012: 1821-1826.

CHAN K Y, DILLON T S, SINGH J, et al. Neural- network-based models for short-term traffic flow forecasting using a hybrid exponential smoothing and Levenberg- Marquardt algorithm[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(2): 644-654.

XU Yanyan, KONG Qingjie, and LIU Yuncai. Short-term traffic volume prediction using classification and regression trees[C]. IEEE Intelligent Vehicles Symposium(IV), Gold Coast, 2013: 493-498.

WILLIAMS B M. Modeling and forecasting vehicular traffic flow as a seasonal stochastic time series process[D]. [Ph.D. dissertation], University of Virginia, 1999: 243-246.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)