{"title":"盲源分离的多层广义平均神经元模型","authors":"Meenakshi Singh, Deepak Singh, P. Kalra","doi":"10.1109/ISIC.2007.4450947","DOIUrl":null,"url":null,"abstract":"The fundamental issue in blind source separation (BSS) is to find a set of independent signals from the output of the mixing system, without the aid of information about the nature of the mixing system, for which most of the BSS algorithms use the concept of Independent component analysis. This paper proposes a new neuron model for independent component analysis (ICA) which can be used for separation of non-linear and noisy mixtures of signals. The technique proposed here utilizes generalized mean neuron (GMN) model, consisting of an aggregation function which is based on the generalized mean of all the inputs applied to signal mixtures. The proposed technique results in faster convergence, and is highly efficient for underdetermined system, with low CPU time.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"98 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Multilayer Generalized Mean Neuron model for Blind Source Separation\",\"authors\":\"Meenakshi Singh, Deepak Singh, P. Kalra\",\"doi\":\"10.1109/ISIC.2007.4450947\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The fundamental issue in blind source separation (BSS) is to find a set of independent signals from the output of the mixing system, without the aid of information about the nature of the mixing system, for which most of the BSS algorithms use the concept of Independent component analysis. This paper proposes a new neuron model for independent component analysis (ICA) which can be used for separation of non-linear and noisy mixtures of signals. The technique proposed here utilizes generalized mean neuron (GMN) model, consisting of an aggregation function which is based on the generalized mean of all the inputs applied to signal mixtures. The proposed technique results in faster convergence, and is highly efficient for underdetermined system, with low CPU time.\",\"PeriodicalId\":184867,\"journal\":{\"name\":\"2007 IEEE 22nd International Symposium on Intelligent Control\",\"volume\":\"98 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 IEEE 22nd International Symposium on Intelligent Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISIC.2007.4450947\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE 22nd International Symposium on Intelligent Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISIC.2007.4450947","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Multilayer Generalized Mean Neuron model for Blind Source Separation
The fundamental issue in blind source separation (BSS) is to find a set of independent signals from the output of the mixing system, without the aid of information about the nature of the mixing system, for which most of the BSS algorithms use the concept of Independent component analysis. This paper proposes a new neuron model for independent component analysis (ICA) which can be used for separation of non-linear and noisy mixtures of signals. The technique proposed here utilizes generalized mean neuron (GMN) model, consisting of an aggregation function which is based on the generalized mean of all the inputs applied to signal mixtures. The proposed technique results in faster convergence, and is highly efficient for underdetermined system, with low CPU time.