基于独立成分分析的超低频电磁探测信号滤波
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
独立成分分析方法引入到超低频电磁探测曲线的滤波中。首先运用模拟数据来探讨运用独立成分分析方法进行滤波的可行性,然后运用实际的观测数据对基于独立成分分析的滤波方法进行了评价和比较。结果表明,运用独立成分分析方法进行探测曲线的噪声滤除是可行的,而且该方法可有效地滤除噪声、突出曲线的特征,有利于曲线的地质解译。同时,对相关问题进行了讨论。
The independent component analysis(ICA)was introduced for the filtering of the ultra-low electromagnetic(ULEM)detection curves.Simulated datasets were first used to validate the effectiveness of ICA in the filtering.The real datasets were then used to evaluate and compare the performance of the proposed filtering method.The results show that filtering of the ULEM signals based on ICA is feasible.Moreover,the proposed filtering method could effectively suppress the noise and enhance the valuable features of the curves,which facilitates geological interpretation of the resulting curves.Some issues are also discussed.
引文
[1]Hyvarinen A,Oja E.Independent component analysis:algorithms and applications.Neural Networks,2000,13(4-5):411-430
    [2]侯贵廷,衣学磊,钱祥麟,等.超长电磁波遥测技术在渤海深部油气勘探中的应用.北京大学学报:自然科学版,2001,37(1):81-86
    [3]曾生根,夏德深.独立分量分析在多光谱遥感图像分类中的应用.计算机工程与应用,2004,40(21):108-110
    [4]宋江红,冯燕.基于独立成分分析和神经网络的高光谱遥感数据分类.遥感技术与应用,2006,21(4):115-119
    [5]翟葵,吴小培.基于独立分量分析的脑电信号消噪.现代制造工程,2006(2):89-91
    [6]彭才,朱仕军,孙建库,等.基于独立成分分析的地震数据去噪.勘探地球物理进展,2007,30(1):30-32
    [7]Hyvarinen A,Karhunen J,Oja E.Independent component analysis.NewYork:John Wiley&Sons,2001

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心