發(fā)布時(shí)間：2018-01-19 05:01

  本文關(guān)鍵詞： 移動(dòng)軌跡 空間劃分 特征模型 模式匹配 終點(diǎn)預(yù)測(cè)逡逑　出處：《西安科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著科技的迅速發(fā)展,GPS定位設(shè)備以及無線通信技術(shù)的普及應(yīng)用程度大大提高,基于位置的移動(dòng)終端設(shè)備愈來愈趨向智能化,我們可以方便的收集移動(dòng)對(duì)象的軌跡數(shù)據(jù),這些數(shù)據(jù)蘊(yùn)含著大量的移動(dòng)行為特征規(guī)律,可以為城市交通規(guī)劃、廣告推送以及人群特征行為的研究提供決策支撐。因此,對(duì)移動(dòng)行為特征建模具有重要的研究意義。本文以移動(dòng)對(duì)象的軌跡數(shù)據(jù)為研究對(duì)象,以移動(dòng)對(duì)象的行為特征建模和移動(dòng)軌跡終點(diǎn)預(yù)測(cè)為主要目標(biāo)。本文的研究工作主要包括以下四個(gè)方面:(1)在數(shù)據(jù)預(yù)處理階段,本文以真實(shí)的移動(dòng)軌跡數(shù)據(jù)為基礎(chǔ),提出了兩種對(duì)于移動(dòng)軌跡所在空間區(qū)域的動(dòng)態(tài)結(jié)構(gòu)化表示方法——Q網(wǎng)格劃分法和KD-樹網(wǎng)格劃分法,避免了現(xiàn)有技術(shù)中常用到的等尺度網(wǎng)格劃分法存在的劃分粗糙、軌跡語(yǔ)義化程度差的問題;(2)在特征建模階段,針對(duì)在基于貝葉斯公式的預(yù)測(cè)算法中易遇到的“數(shù)據(jù)稀疏”問題,本文通過軌跡劃分與重構(gòu)的方法,在貝葉斯網(wǎng)絡(luò)理論和馬爾科夫模型的基礎(chǔ)上,提出了基于網(wǎng)格序列編號(hào)、基于軌跡序列編號(hào)的兩種步長(zhǎng)統(tǒng)計(jì)方法以及建立混合移動(dòng)行為特征建模的方法;(3)在軌跡預(yù)測(cè)階段,本文在OD模式匹配預(yù)測(cè)算法的基礎(chǔ)上加入了軌跡的局部特征點(diǎn),提出OMD特征點(diǎn)混合模式匹配預(yù)測(cè)方法,改善了O 特征點(diǎn)模式匹配預(yù)測(cè)算法只考慮移動(dòng)軌跡全局模式而造成的軌跡匹配度低的問題;(4)在預(yù)測(cè)結(jié)果修正階段,本文在粗粒度空間劃分模型的預(yù)測(cè)結(jié)果基礎(chǔ)上,融合了細(xì)粒度路網(wǎng)模型下的軌跡預(yù)測(cè)結(jié)果對(duì)原始預(yù)測(cè)結(jié)果進(jìn)行修正,提高了軌跡的預(yù)測(cè)精度。本文以Matlab2014作為實(shí)驗(yàn)平臺(tái),以深圳市真實(shí)的出租車移動(dòng)軌跡數(shù)據(jù)作為原始軌跡數(shù)據(jù)庫(kù)進(jìn)行實(shí)驗(yàn)驗(yàn)證和分析。通過數(shù)據(jù)預(yù)處理、空間結(jié)構(gòu)劃分、建立混合特征模型以及模式匹配預(yù)測(cè)等過程對(duì)軌跡的終點(diǎn)進(jìn)行預(yù)測(cè)并與實(shí)際終點(diǎn)進(jìn)行比較。實(shí)驗(yàn)結(jié)果表明,本算法的終點(diǎn)預(yù)測(cè)率可達(dá)到94.6%,實(shí)現(xiàn)了軌跡終點(diǎn)的預(yù)測(cè)功能。
[Abstract]:With the rapid development of science and technology, GPS positioning equipment and the popularity of wireless communication technology have been greatly improved, the mobile terminal equipment based on location is becoming more and more intelligent. We can conveniently collect the trajectory data of moving objects, which contains a large number of characteristics of mobile behavior, and can be used for urban traffic planning. The research of advertising push and crowd characteristic behavior provides decision support. Therefore, it is of great significance to model mobile behavior features. This paper takes the trajectory data of moving object as the research object. The main goal of this paper is to model the behavior characteristics of moving objects and predict the end point of moving trajectory. The research work in this paper mainly includes the following four aspects: 1) in the stage of data preprocessing. Based on the real moving trajectory data, this paper presents two dynamic structured representation methods for the space region of the moving trajectory, I. E. Q mesh division method and KD-tree grid partition method. It avoids the problems of rough partition and poor semantic degree of locus, which are often used in the prior art. 2) in the stage of feature modeling, aiming at the problem of "data sparsity" which is easily encountered in the prediction algorithm based on Bayesian formula, this paper adopts the method of trajectory partition and reconstruction. On the basis of Bayesian network theory and Markov model, two step size statistics methods based on grid sequence numbering and trajectory sequence numbering are proposed, as well as the modeling method of hybrid mobile behavior features. In the phase of trajectory prediction, based on OD pattern matching prediction algorithm, the local feature points of trajectory are added, and a hybrid pattern matching prediction method of OMD feature points is proposed. The O feature point pattern matching prediction algorithm only considers the problem of low trajectory matching degree caused by moving trajectory global pattern. 4) at the stage of forecasting result correction, this paper combines the track forecast result of fine grained road network model to revise the original forecast result based on the prediction result of coarse-grained space partition model. The accuracy of trajectory prediction is improved. In this paper, Matlab2014 is used as the experimental platform. The real taxi track data of Shenzhen city is used as the original track database for experimental verification and analysis. The spatial structure is divided by data preprocessing. The hybrid feature model and pattern matching prediction are established to predict the end point of the trajectory and compared with the actual end point. The experimental results show that the endpoint prediction rate of this algorithm can reach 94.6%. The prediction function of trajectory end point is realized.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U495

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 孟凡振;吳杰;卜旭松;馮鋒;;基于馬爾可夫鏈模型的井下目標(biāo)軌跡預(yù)測(cè)算法[J];計(jì)算機(jī)科學(xué);2014年S1期

2 李萬高;趙雪梅;孫德廠;;基于改進(jìn)貝葉斯方法的軌跡預(yù)測(cè)算法研究[J];計(jì)算機(jī)應(yīng)用;2013年07期

3 陳康;黃曉宇;王愛寶;陶彩霞;關(guān)迎暉;李磊;;基于位置信息的用戶行為軌跡分析與應(yīng)用綜述[J];電信科學(xué);2013年04期

4 劉震;付俊輝;趙楠;;基于移動(dòng)通信數(shù)據(jù)的用戶移動(dòng)軌跡預(yù)測(cè)方法[J];計(jì)算機(jī)應(yīng)用與軟件;2013年02期

5 丁治明;;一種適合于頻繁位置更新的網(wǎng)絡(luò)受限移動(dòng)對(duì)象軌跡索引[J];計(jì)算機(jī)學(xué)報(bào);2012年07期

6 唐蔚;張棟梁;范媛媛;;移動(dòng)計(jì)算環(huán)境下路網(wǎng)上移動(dòng)對(duì)象的位置更新[J];計(jì)算機(jī)科學(xué);2011年12期

7 袁冠;夏士雄;張磊;周勇;;基于結(jié)構(gòu)相似度的軌跡聚類算法[J];通信學(xué)報(bào);2011年09期

8 楊超;王志偉;;經(jīng)GA優(yōu)化的WNN在交通流預(yù)測(cè)中的應(yīng)用[J];計(jì)算機(jī)工程;2011年14期

9 李祥;周波;;一種基于樸素貝葉斯分類的性能預(yù)測(cè)方法[J];計(jì)算機(jī)應(yīng)用與軟件;2011年01期

10 彭曲;丁治明;郭黎敏;;基于馬爾可夫鏈的軌跡預(yù)測(cè)[J];計(jì)算機(jī)科學(xué);2010年08期

相關(guān)博士學(xué)位論文 前2條

1 袁晶;大規(guī)模軌跡數(shù)據(jù)的檢索、挖掘和應(yīng)用[D];中國(guó)科學(xué)技術(shù)大學(xué);2012年

2 余雪崗;無線局域網(wǎng)中的移動(dòng)預(yù)測(cè)研究及應(yīng)用[D];吉林大學(xué);2007年

相關(guān)碩士學(xué)位論文 前3條

1 吳宇晨;車輛自組織網(wǎng)絡(luò)中基于軌跡的路由算法研究[D];上海交通大學(xué);2013年

2 李路明;基于WiFi定位的軌跡預(yù)測(cè)的研究和實(shí)現(xiàn)[D];西安電子科技大學(xué);2013年

3 陳超;車載自組織網(wǎng)絡(luò)數(shù)據(jù)傳輸技術(shù)研究[D];湖南大學(xué);2012年

，

本文編號(hào)：1442711