English

应用科学学报 >

2017 , Vol. 35 >Issue 6: 685 - 692

DOI: https://doi.org/10.3969/j.issn.0255-8297.2017.06.002

通信工程

一种改进支持向量机的无线定位方法

展开
  • 天津大学 微电子学院, 天津 300072
杨晋生,副教授,研究方向:无线传播理论与技术. Email:jsyang@tju.edu.cn

收稿日期: 2016-09-12

  修回日期: 2016-11-27

  网络出版日期: 2017-11-30

收起

Modified Support Vector Machine for Wireless Localization

Expand
  • School of Microelectronics, Tianjin University, Tianjin 300072, China

Received date: 2016-09-12

  Revised date: 2016-11-27

  Online published: 2017-11-30

Fold

摘要

针对利用支持向量机无线定位过程中参数对定位准确度有较大影响的问题，提出一种模拟退火改进的支持向量机（simulated annealing-support vector machine，SA-SVM）参数的定位方法.根据蜂窝通信系统模型仿真数据训练支持向量机，利用模拟退火算法迭代寻找SVM最优参数，然后用得到的最优参数进行支持向量机定位.仿真结果表明，相对于原来的SVM定位，SA-SVM有效提高了定位精度，具有很好的应用价值.

关键词： 支持向量机; 无线定位; 模拟退火算法; 参数选择

本文引用格式

杨晋生, 林振军 . 一种改进支持向量机的无线定位方法[J]. 应用科学学报, 2017 , 35(6) : 685 -692 . DOI: 10.3969/j.issn.0255-8297.2017.06.002

Abstract

Using support vector machine (SVM) for wireless localization suffers from instability of accuracy as the parameters are generally chosen based on experience. To solve the problem, we use simulated annealing (SA) to modify support vector machine (SA-SVM) to improve positioning accuracy. We obtain the training samples from simulation of the cellular communication system model to the SVM, and find the optimal SVM parameters in an iterative search based on SA. The obtained optimal parameters are then used in the positioning. Simulations show that, compared with the original SVM positioning method, SA-SVM method effectively improves localization accuracy, and therefore has application values.

Key words： simulated annealing (SA); parameter selection; wireless localization; support vector machine (SVM)

参考文献

[1] 朱宇佳,邓中亮,刘文龙,徐连明,方灵. 基于支持向量机多分类的室内定位系统[J]. 计算机科学,2012, 39(4):32-35. Zhu Y J, Deng Z L, Liu W L, Xu L M, Fang L. Multi-classification algorithm for indoor positioning based on support vector machine[J]. Computer Science, 2012, 39(4):32-35. (in Chinese)
[2] Van N T, Jeong Y, Shin H, Moe Z W. Machine learning for wideband localization[J]. IEEE Journal on Selected Areas in Communications, 2015, 33(7):1357-1380.
[3] Vo Q D, De P. A survey of fingerprint-based outdoor localization[J]. IEEE Communications Surveys & Tutorials, 2016, 18(1):491-506.
[4] Komai Y, Sasaki Y, Hara T, Shojiro N. K nearest neighbor search for location-dependent sensor data in MANETs[J]. Access IEEE, 2015(3):942-954.
[5] Sun G, Guo W. Robust mobile geo-location algorithm based on LS-SVM[J]. IEEE Transactions on Vehicular Technology, 2005, 54(3):1037-1041.
[6] 徐小卜,王勇,陶晓玲. 基于支持向量机分类的WSN节点定位算法[J]. 计算机工程,2010, 36(24):90-92. Xu X B, Wang Y, Tao X L. WSN node positioning algorithm based on support vector classification[J]. Computer Engineering, 2010,36(24):90-92. (in Chinese)
[7] Wu Z L, Li C H, Ng K Y, Leung K R P H. Location estimation via support vector regression[J]. IEEE Transactions on Mobile Computing, 2007, 6(3):311-321.
[8] Brunato M, Battiti R. Statistical learning theory for location fingerprinting in wireless LANs[J]. Computer Networks, 2002, 47(6):825-845.
[9] Chen Y G, Ma G. Electricity price forecasting based on support vector machine trained by genetic algorithm[C]//International Symposium on Intelligent Information Technology Application. IEEE, 2009:292-295.
[10] Gharghan S K, Nordin R, Ismail M, Jamal A A. Accurate wireless sensor localization technique based on hybrid PSO-ANN algorithm for indoor and outdoor track cycling[J]. IEEE Sensors Journal, 2015, 16(2):529-541.
[11] 田孝华,廖桂生,王少龙. 利用GDOP对蜂窝移动通信系统移动台定位的方法[J]. 系统工程与电子技术,2002, 24(11):104-107. Tian X H, Liao G S, Wang S L. A mobile station locating method for a cellular communication system based on GDOP[J]. Systems Engineering & Electronics, 2002, 24(11):104-107. (in Chinese)

Options
文章导航

/

〈 〉