本文關(guān)鍵詞：基于貝葉斯網(wǎng)絡(luò)多方法組合的短時(shí)交通流量預(yù)測(cè)，由筆耕文化傳播整理發(fā)布。

基于貝葉斯網(wǎng)絡(luò)多方法組合的短時(shí)交通流量預(yù)測(cè)

Short-Term Freeway Traffic Flow Prediction Based on Multiple Methods with Bayesian Network

[1] [2] [3]

WANG Jian,DENG Wei,ZHAO Jin-bao （Transportation College,Southeast University,Nanjing 210096,China）

東南大學(xué)交通學(xué)院,南京210096

文章摘要：貝葉斯網(wǎng)絡(luò)是處理不確定信息和進(jìn)行概率推理的有力工具,針對(duì)短時(shí)交通流量預(yù)測(cè)的難題,提出一種基于貝葉斯網(wǎng)絡(luò)的多方法組合預(yù)測(cè)模型.首先建立幾種基本預(yù)測(cè)模型并對(duì)交通流量進(jìn)行預(yù)測(cè),然后將預(yù)測(cè)的結(jié)果和實(shí)際結(jié)果按一定步長(zhǎng)進(jìn)行離散處理,把離散后的結(jié)果用貝葉斯網(wǎng)絡(luò)進(jìn)行學(xué)習(xí),更新貝葉斯網(wǎng)絡(luò)參數(shù),通過(guò)聯(lián)合推理求得各個(gè)基本預(yù)測(cè)模型預(yù)測(cè)結(jié)果組合下可能組合預(yù)測(cè)值的后驗(yàn)概率,把后驗(yàn)概率最大所對(duì)應(yīng)的值作為預(yù)測(cè)值.通過(guò)對(duì)實(shí)際道路交通流量的預(yù)測(cè)表明,本文提出的貝葉斯網(wǎng)絡(luò)多方法組合預(yù)測(cè)模型的預(yù)測(cè)結(jié)果精度優(yōu)于單一的預(yù)測(cè)模型,從而論證了本文提出的貝葉斯網(wǎng)絡(luò)多方法組合預(yù)測(cè)模型具有一定的實(shí)用性.

Abstr：Bayesian network is one of the most efficient models in the uncertain knowledge and reasoning field.A method based on Bayesian networks of combination mode is put forward to solve the problem of short-term traffic flow prediction.First,several basic prediction models are used to predict the traffic flow.The prediction results and the actual traffic flow are discretized by certain step length.Then,the parameters of the Bayesian network are updated by learning those data.Through combination of reasoning,every possible value of Posterior probability of each data generated by the results of every basic prediction model can be calculated.Then the largest value of Posterior probability would be the final result of combined prediction.The prediction of traffic flow in real road indicates that the prediction results by Bayesian network combination model are more accurate than single prediction model.It thus proves that the proposed model is applicable for the real condition.

文章關(guān)鍵詞：

Keyword：:traffic engineering combined model Bayesian network traffic flow ARIMA algorithm wavelet analysis BP neural network

相關(guān)文章：

[1] 基于排隊(duì)論的交叉口交通流研究   《科技信息》  2010年35期
[2] An improved cellular automaton model considering the effect of traffic lights and driving behaviour   《中國(guó)物理B：英文版》  2011年04期
[3] 國(guó)家級(jí)經(jīng)濟(jì)開發(fā)區(qū)道路自行車換算系數(shù)探討   《中國(guó)工程咨詢》  2011年04期
[4] 基于BP神經(jīng)網(wǎng)絡(luò)的動(dòng)態(tài)交通流量預(yù)測(cè)   《吉林建筑工程學(xué)院學(xué)報(bào)》  2011年02期
[5] 基于最小二乘支持向量機(jī)的交通流量預(yù)測(cè)模型   《北京交通大學(xué)學(xué)報(bào)：自然科學(xué)版》  2011年02期
[6] 基于網(wǎng)絡(luò)對(duì)偶均衡的有邊約束的交通流分配模型   《交通運(yùn)輸系統(tǒng)工程與信息》  2011年02期
[7] 交通流量調(diào)查設(shè)備之淺析   《公路交通科技：應(yīng)用技術(shù)版》  2011年02期

課題項(xiàng)目：國(guó)家十一五科技支撐計(jì)劃項(xiàng)目（2006BAJ18B03）

  本文關(guān)鍵詞：基于貝葉斯網(wǎng)絡(luò)多方法組合的短時(shí)交通流量預(yù)測(cè)，由筆耕文化傳播整理發(fā)布。