本文關(guān)鍵詞：基于半監(jiān)督學(xué)習(xí)的無線傳感器網(wǎng)絡(luò)節(jié)點(diǎn)定位問題研究　出處：《西南交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 無線傳感器網(wǎng)絡(luò) 節(jié)點(diǎn)定位 半監(jiān)督學(xué)習(xí) DV-Hop SVM SSL

【摘要】：隨著大數(shù)據(jù)和云計(jì)算技術(shù)的發(fā)展,無線傳感器網(wǎng)絡(luò)(Wireless Sensor Network,WSN)已經(jīng)步入大數(shù)據(jù)時(shí)代。作為新型的無線通信網(wǎng)絡(luò),WSN的主要目標(biāo)是獲取網(wǎng)絡(luò)環(huán)境中的數(shù)據(jù),這些數(shù)據(jù)來自于傳感器節(jié)點(diǎn),節(jié)點(diǎn)所處的位置不同,數(shù)據(jù)代表的意義也就不同。因此,節(jié)點(diǎn)的位置信息是WSN的重要參數(shù),節(jié)點(diǎn)定位是WSN的一項(xiàng)重要任務(wù)。隨著機(jī)器學(xué)習(xí)技術(shù)的發(fā)展,將半監(jiān)督學(xué)習(xí)思想引入WSN節(jié)點(diǎn)定位中,可以減小算法對(duì)信標(biāo)節(jié)點(diǎn)比例的敏感度,并且可以獲得較高的定位精度。本文基于DV-Hop算法思想,建立了監(jiān)督學(xué)習(xí)和半監(jiān)督學(xué)習(xí)的定位算法模型,并對(duì)算法的定位性能進(jìn)行了比較。本文首先介紹WSN節(jié)點(diǎn)定位的基本概念以及無需測(cè)距定位算法的定位原理,并對(duì)三個(gè)無需測(cè)距定位算法進(jìn)行仿真分析,對(duì)比三個(gè)算法在不同信標(biāo)節(jié)點(diǎn)比例下的平均定位誤差和定位覆蓋率。其次,本文將經(jīng)典DV-Hop定位算法獲取跳數(shù)的思想引入到支持向量機(jī)(Support Vector Machine,SVM)中,建立基于跳數(shù)的多分類SVM定位算法模型。該SVM定位算法根據(jù)"一對(duì)多"的構(gòu)造思想,將WSN網(wǎng)絡(luò)區(qū)域等分為多個(gè)網(wǎng)格,將信標(biāo)節(jié)點(diǎn)的網(wǎng)格編號(hào)以及所有節(jié)點(diǎn)的跳數(shù)向量作為支持向量機(jī)訓(xùn)練參數(shù),訓(xùn)練網(wǎng)格編號(hào)與跳數(shù)向量的映射模型,并通過訓(xùn)練好的模型預(yù)測(cè)未知節(jié)點(diǎn)的位置坐標(biāo)。仿真結(jié)果表明,在節(jié)點(diǎn)通信半徑較大,信標(biāo)節(jié)點(diǎn)比例較高,網(wǎng)格劃分長(zhǎng)度較小的情況下,相比經(jīng)典DV-Hop算法以及O-DV-Hop改進(jìn)算法,基于跳數(shù)的多分類SVM算法的定位精度較高。最后,本文將基于跳數(shù)的多分類SVM算法與機(jī)器學(xué)習(xí)算法中的k近鄰算法相結(jié)合,建立基于協(xié)同訓(xùn)練的半監(jiān)督SVM(SSL)定位算法模型。該SSL定位算法同時(shí)訓(xùn)練兩個(gè)定位模型,取標(biāo)記結(jié)果一致的節(jié)點(diǎn)作為新的信標(biāo)節(jié)點(diǎn),并將該信標(biāo)節(jié)點(diǎn)的參數(shù)輸入定位模型中進(jìn)行訓(xùn)練,不斷更新定位模型,直到全部節(jié)點(diǎn)定位完成。仿真結(jié)果表明,相比基于跳數(shù)的多分類SVM算法,SSL算法不僅定位精度有所提高,并且降低了算法對(duì)信標(biāo)節(jié)點(diǎn)比例的敏感度。
[Abstract]:With the development of big data and cloud computing technology, wireless sensor network (WSN) wireless Sensor Network. WSNs have entered the era of big data. As a new wireless communication network, the main goal of WSN is to obtain the data in the network environment. These data come from sensor nodes and the nodes are located in different positions. Therefore, the location information of nodes is an important parameter of WSN, and node location is an important task of WSN. With the development of machine learning technology. Introduction of semi-supervised learning into WSN node localization can reduce the sensitivity of the algorithm to the beacon node ratio and obtain high positioning accuracy. This paper is based on the DV-Hop algorithm. The location algorithm model of supervised learning and semi-supervised learning is established, and the localization performance of the algorithm is compared. Firstly, this paper introduces the basic concept of WSN node localization and the positioning principle of the location algorithm without ranging. And the simulation analysis of three location algorithms without ranging, compared with the three algorithms in different beacon node proportion of the average positioning error and location coverage. Secondly. In this paper, the classical DV-Hop localization algorithm is introduced to support Vector Machine (SVM). A multi-class SVM localization algorithm model based on hops is established. According to the idea of "one-to-many" construction, the WSN network region is divided into several meshes. The mesh number of the beacon node and the hop vector of all nodes are taken as the training parameters of the support vector machine, and the mapping model between the training grid number and the hopping vector is proposed. The simulation results show that when the communication radius of nodes is large, the proportion of beacon nodes is higher, and the length of mesh division is small. Compared with the classical DV-Hop algorithm and O-DV-Hop improved algorithm, the multi-class SVM algorithm based on hops has higher positioning accuracy. Finally. In this paper, the multi-class SVM algorithm based on hops is combined with the k-nearest neighbor algorithm in the machine learning algorithm. A semi-supervised SSL location algorithm model based on cooperative training is established, which trains two localization models at the same time and takes the nodes with the same tagging results as the new beacon nodes. The parameters of the beacon node are input into the localization model to train and update the location model until all nodes are located. The simulation results show that compared with the multi-classification SVM algorithm based on hops. The SSL algorithm not only improves the location accuracy, but also reduces the sensitivity of the algorithm to the beacon node ratio.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN929.5;TP212.9

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 吳棟;紀(jì)志成;張彪;;基于無線傳感器網(wǎng)絡(luò)的改進(jìn)APIT定位算法[J];系統(tǒng)仿真學(xué)報(bào);2015年12期

2 盧迪;劉世琦;;無線傳感網(wǎng)絡(luò)改進(jìn)APIT定位算法[J];哈爾濱理工大學(xué)學(xué)報(bào);2014年04期

3 劉桂雄;張曉平;周松斌;;基于最小二乘支持向量回歸機(jī)的無線傳感器網(wǎng)絡(luò)目標(biāo)定位法[J];光學(xué)精密工程;2009年07期

4 馬祖長(zhǎng),孫怡寧;無線傳感器網(wǎng)絡(luò)節(jié)點(diǎn)的定位算法[J];計(jì)算機(jī)工程;2004年07期

，

本文編號(hào)：1432800