您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2019, Vol. 49 ›› Issue (1): 36-40.doi: 10.6040/j.issn.1672-3961.0.2017.524

• 机器学习与数据挖掘 • 上一篇    下一篇

基于BP神经网络和多元Taylor级数的混合定位算法

杨亚楠(),夏斌*(),谢楠,袁文浩   

  1. 山东理工大学计算机科学与技术学院, 山东 淄博 255000
  • 收稿日期:2017-10-23 出版日期:2019-02-20 发布日期:2019-03-01
  • 通讯作者: 夏斌 E-mail:yanan_yang@126.com;xiabin@sdut.edu.cn
  • 作者简介:杨亚楠(1992—)，女，山东枣庄人，硕士研究生，主要研究方向为深度学习. E-mail: yanan_yang@126.com
  • 基金资助:
    国家自然科学基金(61701286);山东省自然科学基金(ZR2017MF047)

Hybrid localization algorithm based on BP neural network and multivariable Taylor series

Ya'nan YANG(),Bin XIA*(),Nan XIE,Wenhao YUAN   

  1. School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, Shandong, China
  • Received:2017-10-23 Online:2019-02-20 Published:2019-03-01
  • Contact: Bin XIA E-mail:yanan_yang@126.com;xiabin@sdut.edu.cn
  • Supported by:
    国家自然科学基金(61701286);山东省自然科学基金(ZR2017MF047)

RichHTML

4

PDF (PC)

337

摘要：

针对多元Taylor级数算法定位精度严重依赖初始值的问题,提出一种新的混合定位算法。通过BP神经网络定位算法提供初始值,提高多元Taylor级数展开法的收敛速度;通过多元Taylor级数展开法,充分利用未知节点之间的距离信息,减小测距误差造成的定位误差。仿真结果表明:混合定位算法的精度更高,并且减少了网格间距对定位精度的影响。

关键词: 多元变量泰勒级数展开, 定位模型, BP神经网络, 定位精度, 混合定位

Abstract:

The positioning accuracy of the multivariable Taylor series algorithm depended heavily on the initial values, so a novel hybrid localization algorithm was proposed. The initial values offered by back-bropagation(BP) neural network algorithm could improve the convergence speed of multivariable Taylor series expansion method, and the multivariable Taylor series expansion method could reduce the position error caused by distance measurement error through making full use of the distance information of the unknown nodes. Experimental results indicated that the algorithm could improve positioning accuracy and reduced the influence of mesh spacing on location accuracy.

Key words: multivariable Taylor series expansion, positioning model, back-propagation neural network, positioning accuracy, hybrid localization

中图分类号: 

  • TP393

图1

基于BP神经网络的定位模型"

图2

混合算法的流程图"

表1

仿真参数"

仿真参数 设置
仿真场景 10 m×10 m的矩形定位区域,在该区域的四个角落分别固定放置1个锚节点,未知节点随机分布
未知节点数目 20
仿真次数 1 000
输入层神经元数目K 4
隐含层神经元数目N 9
输出层神经元数目 2
网格间距 1
测距误差 服从均值为0,方差σ2的高斯分布[14-15]

图3

测距误差对定位误差的影响"

图4

σ2=1时,定位误差的累积分布函数曲线图"

图5

σ2=0.5时,定位误差的累积分布函数曲线图"

图6

网格间距对定位误差影响的曲线图"

1 YANG H , WU M , SHA C , et al. A Three-Dimensional localization algorithm based on DV-Hop in wireless sensor networks[M]. Berlin, Germany: Springer, 2014.
2 CHEN M, DING X, WANG X, et al. A novel three-dimensional localization algorithm based on DV-HOP[C]//IEEE International Conference on Signal Processing. Piscataway, USA: IEEE, 2014: 70-73.
3 XIONG X, YAN C. Three-dimensional localization algorithm of APIT based on fermat-point divided for wireless sensor networks[C]//Seventh International Symposium on Computational Intelligence & Design. IEEE Computer Society. Piscataway, USA: IEEE, 2014, 2: 521-524.
4 LIU J , WANG Z , YAO M , et al. VN-APIT: virtual nodes-based range-free APIT localization scheme for WSN[J]. Wireless Networks, 2016, 22 (3): 867- 878.
doi: 10.1007/s11276-015-1007-z
5 HAO Z, WANG R, HUANG Y. Three-dimensional positioning based on weighted centroid algorithm[C]// Proceedings of the 4th International Conference on Electronics, Communications and Networks. Boca Raton, USA: CRC Press/Balkema, 2015, 1: 793-796.
6 XIANG H , ZHANG J , BIN L . A new three-dimension spatial location algorithm of wireless sensor network[J]. International Journal on Smart Sensing & Intelligent Systems, 2016, 9 (1): 233- 255.
7 蔡绍滨, 高振国, 潘海为, 等. 带有罚函数的无线传感器网络粒子群定位算法[J]. 计算机研究与发展, 2012, 49 (6): 1228- 1234.
CAI Shaobin , GAO Zhenguo , PAN Haiwei , et al. Localization based on particle swarm optimization with penalty function for wireless sensor network[J]. Journal of Computer Research and Development, 2012, 49 (6): 1228- 1234.
8 毛科技, 范聪玲, 叶飞, 等. 基于支持向量机的无线传感器网络节点定位算法[J]. 计算机研究与发展, 2014, 51 (11): 2427- 2436.
doi: 10.7544/issn1000-1239.2014.20131071
MAO Keji , FAN Congling , YE Fei , et al. Node localization algorithm in wireless sensor networks based on SVM[J]. Journal of Computer Research and Development, 2014, 51 (11): 2427- 2436.
doi: 10.7544/issn1000-1239.2014.20131071
9 夏斌, 刘承鹏, 孙文珠, 等. 基于多元变量泰勒级数展开模型的定位算法[J]. 电子科技大学学报, 2016, 46 (6): 888- 892.
doi: 10.3969/j.issn.1001-0548.2016.06.002
XIA Bin , LIU Chengpeng , SUN Wenzhu , et al. Localization algorithm based on multivariable Taylor series expansion model[J]. Journal of University of Electronic Science and Technology of China, 2016, 46 (6): 888- 892.
doi: 10.3969/j.issn.1001-0548.2016.06.002
10 李瑞雪.物联网定位算法的研究[D].淄博:山东理工大学, 2015.
LI Ruixue. Localization algorithm research for Internet of things[D]. Zibo: Shandong University of Technology, 2015.
11 LI Y, WANG Y, LI H, et al. Single satellite beam scanning positioning based on neural network BP algorithm[C]//MATEC Web of Conferences. Les Ulis, France: EDP Sciences, 2017, 114.
12 MAO Y , WANG Y . A three-dimension localization algorithm for wireless sensor network mobile nodes based on double-layers BP neural network[J]. Lecture Notes in Electrical Engineering, 2014, 273 (4): 685- 691.
13 CHEN M . An improved BP neural network algorithm and its application[J]. Applied Mechanics and Materials, 2014, 543-547, 2120- 2123.
doi: 10.4028/www.scientific.net/AMM.543-547
14 PATWARI N , ASH J N , KYPEROUNTAS S , et al. Locating the nodes: cooperative localization in wireless sensor networks[J]. IEEE Signal Processing Magazine, 2005, 22 (4): 54- 69.
doi: 10.1109/MSP.2005.1458287
15 ALAVI B , PAHLAVAN K . Modeling of the TOA-based distance measurement error using UWB indoor radio measurements[J]. Communications Letters IEEE, 2006, 10 (4): 275- 277.
doi: 10.1109/LCOMM.2006.1613745
[1] 刘杰, 杨鹏, 吕文生, 刘阿古达木, 刘俊秀. 基于气象因素的PM2.5质量浓度预测模型[J]. 山东大学学报(工学版), 2015, 45(6): 76-83.
[2] 姚福安,庞向坤,焦营营,王忠林,张锡满 . 基于三色法和BP神经网络的回转窑温度检测[J]. 山东大学学报(工学版), 2008, 38(2): 61-65 .
[3] 高小伟,蒋晓芸 . BP神经网络在入侵检测系统中的应用及优化[J]. 山东大学学报(工学版), 2006, 36(6): 107-110 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 夏　斌,张连俊 . DS-CDMA UWB系统中基于能量比较的TOA估计算法[J]. 山东大学学报(工学版), 2007, 37(1): 70 -73 .
[2] 卜德云 张道强. 自适应谱聚类算法研究[J]. 山东大学学报(工学版), 2009, 39(5): 22 -26 .
[3] 赵科军 王新军 刘洋 仇一泓. 基于结构化覆盖网的连续 top-k 联接查询算法[J]. 山东大学学报(工学版), 2009, 39(5): 32 -37 .
[4] 丁万涛 李术才 张庆松. TSP预报倾斜岩层分界面误差规律性探讨[J]. 山东大学学报(工学版), 2009, 39(4): 57 -60 .
[5] 王佰伟,曹升乐 . 工业废水治理效果多目标评价方法研究[J]. 山东大学学报(工学版), 2007, 37(3): 89 -92 .
[6] 丑武胜 王朔. 大刚度环境下力反馈主手自适应算法研究[J]. 山东大学学报(工学版), 2010, 40(1): 1 -5 .
[7] 张辉 王孟夏 韩学山. 电力系统的超前热定值及其应用探讨[J]. 山东大学学报(工学版), 2008, 38(6): 25 -29 .
[8] 闫崇京 廖文和 郭宇 程筱胜. 基于多色图的BOM建模[J]. 山东大学学报(工学版), 2008, 38(6): 70 -75 .
[9] 王建平,王淑华,耿贵立 . InN半导体纳米晶相变活化能的研究[J]. 山东大学学报(工学版), 2008, 38(2): 42 -44 .
[10] 陈斌 陈松灿 潘志松 李斌. 异常检测综述[J]. 山东大学学报(工学版), 2009, 39(6): 13 -23 .
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发