本文選題：據(jù)融合 + 機(jī)器學(xué)習(xí)　； 參考：《北京交通大學(xué)》2017年碩士論文

【摘要】：隨著社會(huì)的發(fā)展,道路中機(jī)動(dòng)車的數(shù)量也在迅速增加。與其密切相關(guān)的智能交通系統(tǒng)也在快速發(fā)展。但傳統(tǒng)智能交通系統(tǒng)存在固有的缺點(diǎn):道路交通相關(guān)信息只能在特定位置被檢測(cè),僅能獲取類似交通流量等較為簡(jiǎn)要數(shù)據(jù);路上固定基礎(chǔ)設(shè)施需要耗費(fèi)大力維護(hù)。已經(jīng)存在的道路識(shí)別和預(yù)測(cè)方法存在以下不足:1)所利用的數(shù)據(jù)不夠充足;2)輸入特征基本是手工提取;3)所用的學(xué)習(xí)方法次優(yōu)。本文著重研究車聯(lián)網(wǎng)中大數(shù)據(jù)融合在智能交通服務(wù)中的具體應(yīng)用…-道路故障檢測(cè)系統(tǒng)。車聯(lián)網(wǎng)作為物聯(lián)網(wǎng)在智能交通系統(tǒng)中的具體應(yīng)用,能夠使道路中的眾多車輛實(shí)現(xiàn)互通,不僅能夠使車輛節(jié)點(diǎn)之間進(jìn)行通信,車輛與路邊單元之間也能進(jìn)行通信共同實(shí)現(xiàn)車聯(lián)網(wǎng)大數(shù)據(jù)環(huán)境下的新型智能交通信息體系。本文通過結(jié)合車聯(lián)網(wǎng)中關(guān)鍵技術(shù)車載自組織網(wǎng)絡(luò)(VANET,Vehicular Ad Hoc Network)來實(shí)現(xiàn)大數(shù)據(jù)技術(shù)在交通服務(wù)系統(tǒng)中的應(yīng)用。接下來根據(jù)智能交通信息服務(wù)對(duì)實(shí)時(shí)性和準(zhǔn)確性的首要需求,將系統(tǒng)工作過程分為數(shù)據(jù)收集和數(shù)據(jù)分析兩個(gè)階段進(jìn)行研究分析。首先,深入研究了車聯(lián)網(wǎng)中VANET在大數(shù)據(jù)環(huán)境下所面臨的通信負(fù)載問題的相關(guān)解決方案,通過對(duì)車輛節(jié)點(diǎn)進(jìn)行分簇,形成各個(gè)群組,設(shè)計(jì)相關(guān)通信協(xié)議以群組的傳播方法收集數(shù)據(jù)。實(shí)現(xiàn)以低通信負(fù)載來接收道路中的車輛節(jié)點(diǎn)信息,避免了與道路中的每一車輛進(jìn)行點(diǎn)對(duì)點(diǎn)通信,這一部分對(duì)應(yīng)上文所說的數(shù)據(jù)收集部分。其次,在數(shù)據(jù)分析階段利用機(jī)器學(xué)習(xí)方法實(shí)現(xiàn)相應(yīng)交通服務(wù)功能。本文經(jīng)過一系列對(duì)比分析后選擇了支持向量機(jī)(SVM,Support Vector Machine)和深度神經(jīng)網(wǎng)絡(luò)(DNN,Deep Neural Network)兩種方法,并對(duì)這兩種算法進(jìn)行相應(yīng)改進(jìn)使其適用于本文所應(yīng)用的車聯(lián)網(wǎng)的數(shù)據(jù)融合的實(shí)際問題中。在道路故障檢測(cè)系統(tǒng)中,作為一個(gè)分類問題,分別應(yīng)用SVM和DNN對(duì)道路故障進(jìn)行識(shí)別檢測(cè);作為一個(gè)回歸問題,用DNN對(duì)故障位置進(jìn)行判斷預(yù)測(cè)。最后,本文利用微型的交通軟件VISSIM模擬產(chǎn)生實(shí)驗(yàn)所需的交通數(shù)據(jù)。并對(duì)數(shù)據(jù)進(jìn)行處理以及歸一化等操作,利用本文提出的方法對(duì)道路故障進(jìn)行識(shí)別和位置預(yù)測(cè),分析輸入特征以及訓(xùn)練數(shù)據(jù)對(duì)系統(tǒng)判別精度的影響。并且對(duì)比了不同的DNN結(jié)構(gòu)對(duì)結(jié)果的影響,分析其中的過擬合現(xiàn)象。實(shí)驗(yàn)結(jié)果表明,該模型切實(shí)可行,在故障識(shí)別問題中基本能夠達(dá)到95%以上的檢測(cè)率,位置估測(cè)也能夠滿足實(shí)際的應(yīng)用。這樣的實(shí)驗(yàn)結(jié)果可以作為智能交通服務(wù)應(yīng)用功能實(shí)現(xiàn)的參考,并且其中位置估計(jì)對(duì)于道路交通管理和維護(hù)可以有良好的輔助作用。
[Abstract]:With the development of society, the number of motor vehicles in the road is also increasing rapidly. The intelligent transportation system, which is closely related to it, is also developing rapidly. However, the traditional intelligent transportation system has its inherent disadvantages: road traffic related information can only be detected in a specific location, and can only obtain relatively simple data such as traffic flow, and the road fixed infrastructure needs to be maintained with great effort. The existing road recognition and prediction methods have the following shortcomings: 1) the data used is not enough) the input feature is basically extracted by hand) the learning method used in this paper is suboptimal. This paper focuses on the specific application of large data fusion in intelligent transportation service. -Road fault detection system. As the concrete application of the Internet of things in the intelligent transportation system, the vehicle networking can make many vehicles in the road interoperate, not only make the communication between the vehicle nodes, The communication between the vehicle and the roadside unit can also realize the new intelligent transportation information system under the big data environment. In this paper, the application of big data technology in traffic service system is realized by combining with the key technology of vehicle network, vehicle Ad Hoc network. Then, according to the first requirement of real-time and accuracy of intelligent transportation information service, the working process of the system is divided into two stages: data collection and data analysis. First of all, the paper deeply studies the solutions to the communication load problem of VANET in the big data environment, and forms each group by clustering the vehicle nodes. Design related communication protocols to collect data by group propagation. A low communication load is implemented to receive the vehicle node information in the road, thus avoiding point-to-point communication with each vehicle in the road. This part corresponds to the data collection section mentioned above. Secondly, in the data analysis stage, the machine learning method is used to realize the corresponding traffic service function. After a series of comparative analysis, two methods, support Vector Machine (SVM) and Deep Neural Network (DNN), are selected in this paper, and these two algorithms are improved to be applicable to the practical problems of data fusion in the network of cars in this paper. In the road fault detection system, as a classification problem, SVM and DNN are used to identify and detect road faults, and as a regression problem, DNN is used to judge and predict the fault location. Finally, the traffic data needed in the experiment are generated by using the micro traffic software VisSIM. The method proposed in this paper is used to identify and predict the road faults, and the influence of input features and training data on the system discriminating accuracy is analyzed. The effects of different DNN structures on the results are compared, and the phenomenon of overfitting is analyzed. The experimental results show that the model is feasible, and the detection rate of more than 95% can be basically achieved in the problem of fault identification, and the location estimation can also meet the practical application. The experimental results can be used as a reference for the application of intelligent transportation services, and the location estimation can be helpful to traffic management and maintenance.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN929.5;U495

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 李哲;;大數(shù)據(jù)時(shí)代:智能交通發(fā)展的機(jī)遇和挑戰(zhàn)[J];經(jīng)濟(jì)研究導(dǎo)刊;2014年33期

2 姜竹勝;湯新寧;陳效華;;車聯(lián)網(wǎng)架構(gòu)分析及其在智能交通系統(tǒng)中的應(yīng)用[J];物聯(lián)網(wǎng)技術(shù);2012年11期

3 張秀紅;陳力;胡剛;;基于RBF的城市快速路交通異常事件自動(dòng)檢測(cè)算法分析[J];交通科技與經(jīng)濟(jì);2011年02期

4 徐濤;劉好德;楊曉光;張明月;;基于數(shù)據(jù)融合的城市道路交通事件自動(dòng)檢測(cè)[J];交通信息與安全;2010年04期

5 魏麗英;夏明;田春林;;基于LVQ神經(jīng)網(wǎng)絡(luò)的城市快速路事件自動(dòng)檢測(cè)算法[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2010年02期

6 張慧哲;王堅(jiān);梅宏標(biāo);;基于FCM與模糊粗糙集理論的交通事件檢測(cè)模型[J];計(jì)算機(jī)工程與應(yīng)用;2008年23期

7 YOUSEFI Saleh;FATHY Mahmood;BENSLIMANE Abderrahim;;Performance of beacon safety message dissemination in Vehicular Ad hoc NETworks (VANETs)[J];Journal of Zhejiang University(Science A:An International Applied Physics & Engineering Journal);2007年12期

8 金敬強(qiáng);武富春;;信息融合技術(shù)的發(fā)展現(xiàn)狀與展望[J];電腦開發(fā)與應(yīng)用;2006年01期

相關(guān)碩士學(xué)位論文 前2條

1 韓智穎;基于車聯(lián)網(wǎng)的高速公路交通信息平臺(tái)設(shè)計(jì)與關(guān)鍵技術(shù)研究[D];吉林大學(xué);2014年

2 劉化勝;智能車輛視覺導(dǎo)航中道路檢測(cè)算法的研究[D];南京航空航天大學(xué);2004年

，

本文編號(hào)：2044629