本文選題：浮動(dòng)車軌跡 + 模糊綜合評(píng)價(jià)�。� 參考：《大連理工大學(xué)》2014年碩士論文

【摘要】：交通擁堵問(wèn)題,嚴(yán)重影響市民日常生活,在一定程度上限制了社會(huì)、經(jīng)濟(jì)穩(wěn)定發(fā)展。緩解交通擁堵,尤其是常發(fā)性擁堵,已迫在眉睫。緩解交通擁堵的重要前提是交通擁堵評(píng)估與預(yù)測(cè),但是現(xiàn)有方法在準(zhǔn)確性、實(shí)時(shí)性和穩(wěn)定性三方面的性能不能滿足交通需求。 為了提高擁堵評(píng)估與預(yù)測(cè)的性能,本文提出基于浮動(dòng)車軌跡的擁堵評(píng)估與預(yù)測(cè)方法。對(duì)于評(píng)估方面,本文提出一種基于多指標(biāo)權(quán)重適應(yīng)變化的模糊綜合評(píng)價(jià)法。它通過(guò)對(duì)指標(biāo)賦權(quán)和多指標(biāo)模糊矩陣變換進(jìn)行綜合評(píng)價(jià),根據(jù)擁堵交通流特性給指標(biāo)適應(yīng)賦權(quán),比以往固定權(quán)重法,能夠提高評(píng)估準(zhǔn)確率和實(shí)時(shí)性能。對(duì)于預(yù)測(cè)方面,本文提出一種基于優(yōu)化SVM (Support Vector Machine)的擁堵預(yù)測(cè)方法,它包括VP(Volume Predict)模塊、SP (Speed Predict)模塊、優(yōu)化模塊以及擁堵?tīng)顟B(tài)劃分模塊。VP模塊和SP模塊用于預(yù)測(cè)交通量和平均速度,優(yōu)化模塊對(duì)VP模塊和SP模塊中SVM的懲罰系數(shù)以及多個(gè)核函數(shù)參數(shù)進(jìn)行優(yōu)化,擁堵?tīng)顟B(tài)劃分模塊將預(yù)測(cè)的交通流參數(shù)轉(zhuǎn)化為市民所認(rèn)知的擁堵?tīng)顟B(tài)。它核心算法是粒子群優(yōu)化算法PSO (Particle Swarm Optimization)和SVM, PSO計(jì)算復(fù)雜度低,結(jié)合SVM不同核函數(shù)有不同的預(yù)測(cè)精度和擬合能力,能在最短時(shí)間內(nèi)找到固定最優(yōu)解,可滿足預(yù)測(cè)準(zhǔn)確率、實(shí)時(shí)性、穩(wěn)定性。 最后,本文對(duì)提出的交通擁堵評(píng)估和預(yù)測(cè)方法進(jìn)行仿真驗(yàn)證。實(shí)驗(yàn)內(nèi)容分為兩部分：本文提出的評(píng)估方法與指標(biāo)固定賦權(quán)的模糊綜合評(píng)價(jià)法的對(duì)比和本文提出的預(yù)測(cè)優(yōu)化方法與經(jīng)典優(yōu)化算法的對(duì)比。實(shí)驗(yàn)證明本文提出的評(píng)估與預(yù)測(cè)方法在準(zhǔn)確率、實(shí)時(shí)性和穩(wěn)定性上均具有優(yōu)勢(shì)。
[Abstract]:The problem of traffic jam seriously affects the daily life of citizens and restricts the stable development of society and economy to a certain extent. It is urgent to ease traffic congestion, especially frequent congestion. The important premise of alleviating traffic congestion is traffic congestion evaluation and prediction, but the performance of existing methods in accuracy, real-time and stability can not meet the traffic demand. In order to improve the performance of congestion assessment and prediction, a new method based on floating vehicle trajectory is proposed in this paper. In the aspect of evaluation, a fuzzy comprehensive evaluation method based on multi-index weight adaptation is proposed in this paper. Through the comprehensive evaluation of index weighting and multi-index fuzzy matrix transformation, the index can be weighted according to the traffic congestion characteristics. Compared with the previous fixed weight method, it can improve the accuracy and real-time performance of the evaluation. In the aspect of prediction, a congestion prediction method based on optimized SVM support Vector Machine is proposed. It includes VP(Volume predictor module, optimization module and congestion partition module. VP module and SP module are used to predict traffic volume and average speed. Optimization module optimizes the penalty coefficient of SVM and several kernel function parameters in VP module and SP module. The congestion state partition module converts the predicted traffic flow parameters into the congestion state known by citizens. Its core algorithms are particle swarm optimization (PSO) and particle Swarm optimization (SVM). PSO has low computational complexity. Combining with different kernel functions of SVM, it has different prediction accuracy and fitting ability, and can find the fixed optimal solution in the shortest time. Stability. Finally, the proposed traffic congestion assessment and prediction methods are verified by simulation. The experiment is divided into two parts: the comparison between the evaluation method proposed in this paper and the fuzzy comprehensive evaluation method with fixed index weighting, and the comparison between the proposed prediction optimization method and the classical optimization algorithm. Experiments show that the proposed evaluation and prediction method has advantages in accuracy, real-time and stability.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：U491.265

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 姚智勝;邵春福;高永亮;;基于支持向量回歸機(jī)的交通狀態(tài)短時(shí)預(yù)測(cè)方法研究[J];北京交通大學(xué)學(xué)報(bào);2006年03期

2 楊兆升;王媛;管青;;基于支持向量機(jī)方法的短時(shí)交通流量預(yù)測(cè)方法[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2006年06期

3 龍小強(qiáng);譚云龍;;基于模糊綜合評(píng)價(jià)的城市道路交通擁堵評(píng)價(jià)研究[J];交通標(biāo)準(zhǔn)化;2011年11期

4 葉嫣;呂智林;;基于粒子群優(yōu)化的神經(jīng)網(wǎng)絡(luò)短時(shí)交通流量預(yù)測(cè)[J];計(jì)算機(jī)工程與設(shè)計(jì);2009年18期

5 虞曉芬,傅玳;多指標(biāo)綜合評(píng)價(jià)方法綜述[J];統(tǒng)計(jì)與決策;2004年11期

6 李曉斌;;基于遺傳算法優(yōu)化支持向量機(jī)的交通流量預(yù)測(cè)[J];微電子學(xué)與計(jì)算機(jī);2010年10期

7 姚智勝;邵春福;;基于狀態(tài)空間模型的道路交通狀態(tài)多點(diǎn)時(shí)間序列預(yù)測(cè)[J];中國(guó)公路學(xué)報(bào);2007年04期

，

本文編號(hào)：1796904