通信干扰下无线传感器网络中微弱信号检测
Detection of Weak Signals in Wireless Sensor Networks under Communication Interference
张燕 1曹婷 1侯兆阳2
作者信息
- 1. 南阳理工学院信息工程学院,河南 南阳 473004
- 2. 长安大学理学院,陕西 西安 710064
- 折叠
摘要
微弱信号检测是保证无线传感器网络高效使用的重要环节,但检测过程易受噪声信号、传感器性能、虚拟信号等因素的干扰,从而导致误检.为了解决上述问题,提出一种通信干扰下无线传感器网络微弱信号检测方法.通过局部投影降噪法剔除信号中的噪声,避免噪声对检测过程产生影响.采用主分量分析算法提取去噪信号的特征,并根据遗传算法优化支持向量参数,将提取的特征输入到向量机中,通过特征的分类完成通信干扰下无线传感器网络微弱信号的检测.实验结果表明,所提方法的信号检测结果与实际结果基本一致,检测时间在 30ms内,且抗噪性能强.
Abstract
Weak signal detection is an important link to ensure the efficient use of wireless sensor networks,but the detection process is vulnerable to noise signals,sensor performance,virtual signals and other factors,which lead to false detection.In order to solve these problems,a weak signal detection method for wireless sensor networks under communication interference is proposed.By using local projection denoising method to remove noise from the signal and avoid the impact of noise on the detection process.The principal component analysis algorithm is used to extract the features of the denoised signal,and the support vector parameters are optimized according to the genetic algorithm.The extracted features are input into the vector machine,and the weak signal detection of wireless sensor network un-der communication interference is completed through the classification of features.The experimental results show that the signal detection results of the proposed method are basically consistent with the actual results,with a detection time of within 30ms and strong noise resistance.
关键词
局部投影降噪/主分量分析法/累积方差贡献率/特征的分类预测/支持向量机参数优化Key words
Local projection noise reduction/Principal component analysis/Cumulative variance contribution rate/Classification and prediction of features/Optimization of Support Vector Machine Parameters引用本文复制引用
基金项目
河南省科技攻关计划(222102210206)
出版年
2024
NETL
NSTL
万方数据