计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (22): 228-232.

• 工程与应用 • 上一篇    下一篇

WSNs中基于隐马尔科夫模型的目标识别问题研究

杨明霞1,3,王万良1,2,邵鹏飞1,4   

  1. 1.浙江工业大学 信息学院,杭州 310023
    2.浙江工业大学 计算机学院,杭州 310023
    3.衢州学院 电气与信息工程学院,浙江 衢州 324000
    4.浙江万里学院 电子信息学院,浙江 宁波 315100
  • 出版日期:2015-11-15 发布日期:2015-11-16

Target classification based on hidden Markov model in Wireless Sensor Networks

YANG Mingxia1,3, WANG Wanliang1,2, SHAO Pengfei1,4   

  1. 1.College of Information, Zhejiang University of Technology, Hangzhou 310023, China
    2.College of Computer Science, Zhejiang University of Technology, Hangzhou 310023, China
    3.Quzhou University, Quzhou, Zhejiang 324000, China
    4.Zhejiang Wanli University, Ningbo, Zhejiang 315100, China
  • Online:2015-11-15 Published:2015-11-16

摘要: 由于无线传感器网络(Wireless Sensor Networks,WSNs)资源受限,如何有效利用资源,提高目标辨别的准确度,是WSNs中目标识别系统的研究难题。以隐马尔科夫模型为分类框架,对一个声音传感器阵列节点簇内的目标识别问题进行建模;基于节点信号的空间关联性,改进了子节点Viterbi最大似然序列的计算状态,设置了子节点报送间隔,从而有效地判别局部状态。实验证明,改进后的算法在维持判别正确率的同时降低信息传输量10%以上。

关键词: 目标识别, 无线传感器网络, 隐马尔可夫模型, 维特比算法

Abstract: It is challenging to classify multiple targets in wireless sensor networks based on the time-varying and continuous signals. In this paper, Hidden Markov Model is utilized as a framework for classification. The states in the HMM represent various combinations of vehicles of different types. With a sequence of observations, Viterbi algorithm is used at each sensor node to estimate the most likely sequence of states. Simulation results show that it reduce transmission more than 10% while maintaining identification rate.

Key words: target classification, wireless sensor networks, hidden Markov models, Viterbi