ntrol for improved efficiency,in 2004IEEE Intelligent Vehicles Symposium，2004:951 ~956
[0016] M. Kihlj M. Sichit iu, Η. P. Joshij Design and evaluation of two geocast protocols for vehicular ad-hoc networks,Journal of Internet Engineering, vol. 2, no. I, 2008
[0017] Ozan Tonguzj Nawapom ffisitpongphan, Broadcasting in VANETj in 2007Mobile Networking for Vehicular Environments, 2007:7 ~ 12
[0018] M. Durresij A. Durresij L. Barollij Emergency Broadcast Protocol for Inter-Vehicle Communications, in Ilth International Conference on Parallel and Distributed Systems. Proceedings，2005, vol. 2:402 ~406
[0019] G. Korkmazj E. Ekicij F. Ozgi'mer, Li. Ozgiiner, Urban Multi-hop Broadcast Protocol for Inter-vehicle Communication Systems, in Proceedings of the 1st ACM International Workshop on Vehicular Ad Hoc Networks，New York，USA，2004:76 ~85
[0020] Yang K. Ou S. Chen H. He J. A multihop peer communication protocol with fairness guarantee for IEEE 802. 16based vehicular networks, IEEE Transactions on Vehicular Technology，2007, 56(6):3358 ~3370
[0021] Shan L. Liu F. Yang K. Performance analysis of group handover scheme for IEEE 802. 16j-enabled vehicular networks,Proceedings of the Joint International Conferences on Asia-Pacific Web Conference and Web-Age Information Management. 2009
[0022] M. Sherman, K. M. McNeill, K. Conner, P. Khuuj and T. McNevinj A PMP-Friendly MANET Networking Approach for WiMAX/IEEE 802. 16TM, in IEEE Military Communication Conference. MILC0M，2006:1 ~7
[0023] 范存群，王尚廣，孫其博，等.車聯(lián)網(wǎng)中基于貝葉斯決策的垂直切換方法研究 [J]，通信學報，2013(7):34 ~41
[0024] DOYLE N Cj JABER N Rj TEPE K E. Complete architecture and demonstration design for a new combined WiMAX/DSRC system with improved vehicular networking efficiency[J]，Ad Hoc Networks. 2013, 11 (7):2026 ~2048
[0025] 劉富強，單聯(lián)海.車載移動異構(gòu)無線網(wǎng)絡架構(gòu)及關(guān)鍵技術(shù)，中興通訊技術(shù) [J]· 2010:16(3)
[0026] CHANG B-JjHUANG B-JjLIANG Y-H. Wireless Sensor Network-Based Adaptive Vehicle Navigation in Multihop-Relay WiMAX Networks[C]，22nd International Conference on Advanced Information Networking and Applications,2008. AINA2008. 2008:56 ~63
[0027] CHOU C-Mj LI C-Yj CHIEN ff-M, et al. A Feasibility Study on Vehicle-t〇-Infrastructure Communication: WiFi vs. WiMAX[C],2013IEEE 14th International Conference on Mobile Data Management. Los Alamitosj CA, USA:IEEE Computer Society，2009:397 ~398
[0028] MOJELA L SjBOOYSEN M J. On the use of WiMAX and Wi-Fi to provide in-vehicle connectivity and media distribution [C],2013IEEE International Conference on Industrial Technology (ICIT) · 2013:1353 ~1358
[0029] ZHAO QjZHU YjCHEN Cj et al.ffhen 3G Meets VANET:3G-Assisted Data Delivery in VANETs[J]，IEEE Sensors Journal. 2013, 13(10):3575 ~3584
[0030] YAAC0UB EjFILALI FjABU-DAYYA A. SVC video streaming over cooperative LTE/802.Ilp vehicle-t〇-infrastructure communications[C]，2013:1 ~5
[0031] G. el mouna Zhiouaj H. Labiodj N. Tabbanej and S. Tabbanej An Efficient Qos Based Gateway Selection Algorithm for VANET to LTE Advanced Hybrid Cellular Network, in Proceedings of the 15th ACM International Conference on Modeling,Analysis and Simulation of Wireless and Mobile Systems, New York，USA，2012:353 ~356
[0032] 孫志軍，薛磊，許陽明，王正.深度學習研究綜述[J].計算機應用研 究· 2012(08)
[0033] Hinton, G. E. , &Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313:504 ~ 507
[0034] HINTON Gj 0SINDER0 SjTEH Y. A fast learning algorithm for deep belief nets[J]，Neural Computation，2006, 18(7):1527 ~1554
[0035] VINCENT Pj LAR0CHELLE HjBENGIO Yj et al. Extracting and composing robust features with denoising autoencoders[C], Proc of the 25th International Conference on Machine Learning. New York:ACM Press，2008:1096 ~1103
[0036] CSDN Websites. [EB/0L]. http://blog. csdn. net/zouxy09/article/ details/8781543, 2014/03/12
[0037] 胡昭華，樊鑫，梁德群，宋耀良.基于雙向非線性學習的軌跡跟蹤和識別[J]， 計算機學報· 2007 (08)
[0038] L. Deng, G. Hinton, B. Kingsbury, New types of deep neural network learning for speech recognition and related applications:An overview, Proc. Int. Conf. Acoust., Speech, Signal Process. 2013
[0039] Yoshua Bengio,Learning Deep Architectures for Al, Foundations and Trends in Machine Learning，2 (I)，2009
【發(fā)明內(nèi)容】
高速公路中大規(guī)模網(wǎng)絡實時數(shù)據(jù)量龐大，大量數(shù)據(jù)聚集會產(chǎn)生數(shù)據(jù)冗余，并且車聯(lián)網(wǎng) 大規(guī)模網(wǎng)絡環(huán)境下的數(shù)據(jù)含有豐富的信息維度，需要采取有效機制挖掘車聯(lián)網(wǎng)海量數(shù)據(jù)中 的一般性規(guī)律和數(shù)據(jù)間的關(guān)聯(lián)性特征。目前還沒有針對車聯(lián)網(wǎng)大規(guī)模網(wǎng)絡環(huán)境下對復雜數(shù) 據(jù)進行處理的有效方法。針對高速公路，本發(fā)明給出一種基于自編碼網(wǎng)絡的車聯(lián)網(wǎng)網(wǎng)絡節(jié) 點篩選方法AE-NSM(AutoEncoder-Node Selection Method)，基于該節(jié)點篩選方法設計新 的通達性路由機制D 本發(fā)明技術(shù)方案為： 一種基于自編碼網(wǎng)絡的車聯(lián)網(wǎng)網(wǎng)絡節(jié)點篩選方法，其特征在于，整個路由機制包含三 個部分，數(shù)據(jù)預處理，自編碼網(wǎng)絡訓練，節(jié)點篩選算法實現(xiàn)： 一、數(shù)據(jù)預處理 通過交通仿真軟件，獲取車輛行駛方向山，行駛速度Vp加速度經(jīng)煒度IondP Iat i， 所在道路r,， 兩車距離可通過經(jīng)緯度來計算。首先，設A點與B點的經(jīng)緯度分別為（LgA，LaA)和 (LgB，LaB)，按照零度經(jīng)線，東經(jīng)取正值，西經(jīng)取負值，北煒取90 -煒度，南煒取90+煒度，則 經(jīng)過標準化后A、B兩點的經(jīng)煒度被記為（FLgA，F(xiàn)LaA)和（FLgB，F(xiàn)LaB)。根據(jù)三角推導，可 以通過如下公式5計算兩點之間的距離。
R = 6371. 004km 其中Distance即為兩點間距離，R為地球