北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (1): 134-138.doi: 10.13190/j.jbupt.2017-185

• 研究报告 • 上一篇    下一篇

基于超限学习机的WSNs链路质量评估方法

刘琳岚1, 许江波1, 陈宇斌2, 舒坚2   

  1. 1. 南昌航空大学 信息工程学院, 南昌 330063;
    2. 南昌航空大学 软件学院, 南昌 330063
  • 收稿日期:2017-09-15 出版日期:2018-02-28 发布日期:2018-02-28
  • 作者简介:刘琳岚(1968-),女,教授,硕士生导师,E-mail:liulinlan@nchu.edu.cn.
  • 基金资助:
    国家自然科学基金项目(61363015,61762065,61501218,61501217);江西省自然科学基金重点项目(20171BAB202009,20171ACB20018);江西省研究生创新专项项目(YC2016-S348)

A Link Quality Estimation Method for WSNs Based on Extreme Learning Machine

LIU Lin-lan1, XU Jiang-bo1, CHEN Yu-bin2, SHU Jian2   

  1. 1. School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China;
    2. School of Software, Nanchang Hangkong University, Nanchang 330063, China
  • Received:2017-09-15 Online:2018-02-28 Published:2018-02-28

摘要: 提出基于超限学习机的链路质量评估方法.选择非对称性指标、信噪比变异系数、均值信噪比为链路质量参数,以包接收率为链路质量评价指标,划分链路质量等级;采用粒子群算法优化超限学习机的输入层权重和偏置参数,构建链路质量评估模型.不同场景下的实验结果表明,与支持向量分类机评估方法相比,所提方法具有更高的评估准确率.

关键词: 无线传感器网络, 链路质量评估, 超限学习机, 粒子群优化算法

Abstract: An approach of estimating link quality was proposed which is based on extreme learning machine. The index of link asymmetry, the coefficient of variation of signal to noise ratio and mean signal to noise ratio are chosen as link quality parameters. Link quality level is classified by link packet receive rate which is the evaluation index. Particle swarm optimization algorithm is employed to optimize input weights and offset parameter, so that link quality model is built. In different scenarios, compared with the support vector classification machine estimate methods, the experimental results show that the proposed estimation method achieves better precision.

Key words: wireless sensor networks, link quality estimation, extreme learning machine, particle swarm optimization algorithm

中图分类号: