模糊集合下多传感器信息融合算法仿真
Simulation of Multi-Sensor Information Fusion Algorithm under Fuzzy Set
靳双燕 1李浩亮2
作者信息
- 1. 郑州工商学院信息工程学院,河南 郑州 450000
- 2. 郑州大学电气与信息工程学院,河南 郑州 450000
- 折叠
摘要
多传感器数据融合通常涉及大量数据,受到噪声、不完整性、不准确性等因素的影响,导致融合结果的不确定性增加.为此,提出一种基于模糊集合的多传感器信息融合算法.利用局部保持投影(Locality Preserving Projection,LPP)处理多传感器信息,采用主成分分析(Principal Component Analysis,PCA)分离特征值较大的反射信号,删除特征值较小的随机噪声.利用隶属函数得到不同传感器提供的可信度,将支持度以及可信度转换为基本概率分配函数,引入证据理论(Dempster-Shafer,D-S),实现多传感器信息融合优化.仿真分析表明,所提方法可以得到高精度和高效率的多传感器信息融合结果,峰值信噪比达60dB以上,信噪比一直处于12dB以上,融合最长耗时仅为 2.01ms,使其融合性能得到有效优化.
Abstract
Typically,the data fusion from multiple sensors involves a large amount of data.Affected by factors such as noise,incompleteness and inaccuracy,the uncertainty of the fusion result also increases.To address this,a multi-sensor information fusion algorithm based on fuzzy sets was proposed.Firstly,Locality Preserving Projection(LPP)was utilized to process multi-sensor information.Then,Principal Component Analysis(PCA)was employed to separate reflection signals with larger eigenvalues and remove random noise with smaller eigenvalues.Next,the mem-bership function was used to calculate the credibility provided by different sensors.Moreover,both the support and credibility were converted into basic probability assignment functions.Finally,the Dempster-Shafer(D-S)theory was introduced to achieve the optimization of multi-sensor information fusion.Simulation analysis results show that the proposed method can obtain high-precision and efficient fusion results.The peak signal-to-noise ratio reaches over 60dB,and the signal-to-noise ratio remains above 12dB.The longest fusion time is only 2.01ms.Therefore,the fusion performance is effectively optimized.
关键词
模糊集合/多传感器/信息融合/优化Key words
Fuzzy sets/Multiple sensors/Information fusion/Optimization引用本文复制引用
基金项目
河南省高等学校重点科研项目计划(22B510014)
出版年
2024
NETL
NSTL
万方数据