Shu-Mei Guo, J. Tsai, Chin-Yu Chen, Tzu-Cheng Yang
{"title":"An Improved Empirical Mode Decomposition Based on Time Scale Allocation Method and the 2D Mode Mixing Phenomenon Judgement","authors":"Shu-Mei Guo, J. Tsai, Chin-Yu Chen, Tzu-Cheng Yang","doi":"10.1142/S2424922X17500024","DOIUrl":null,"url":null,"abstract":"In the sifting process of the traditional empirical mode decomposition (EMD), intermittence causes mode mixing phenomenon. The intrinsic mode function (IMF) with the mode mixing phenomenon loses its original real physical meaning. An improved EMD based on time scale allocation method and the two-dimensional (2D) version of our method has been extended to improve the decomposition of the mode mixing phenomenon in 2D image data. Experimental results show that the method not only improves the phenomenon correctly both for 1D signal and 2D image, but also exhibits great performance in quality and computation time.","PeriodicalId":47145,"journal":{"name":"Advances in Data Science and Adaptive Analysis","volume":"360 ","pages":"1750002:1-1750002:46"},"PeriodicalIF":0.5000,"publicationDate":"2017-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1142/S2424922X17500024","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Data Science and Adaptive Analysis","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/S2424922X17500024","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 1
Abstract
In the sifting process of the traditional empirical mode decomposition (EMD), intermittence causes mode mixing phenomenon. The intrinsic mode function (IMF) with the mode mixing phenomenon loses its original real physical meaning. An improved EMD based on time scale allocation method and the two-dimensional (2D) version of our method has been extended to improve the decomposition of the mode mixing phenomenon in 2D image data. Experimental results show that the method not only improves the phenomenon correctly both for 1D signal and 2D image, but also exhibits great performance in quality and computation time.