用于ICA的PCA的高效架构实现

2017 International conference of Electronics, Communication and Aerospace Technology (ICECA) Pub Date : 2017-04-01 DOI:10.1109/ICECA.2017.8203637

Parivesh, Ranjan Sharma

{"title":"用于ICA的PCA的高效架构实现","authors":"Parivesh, Ranjan Sharma","doi":"10.1109/ICECA.2017.8203637","DOIUrl":null,"url":null,"abstract":"Independent component analysis (ICA) Algorithm is a popular algorithm for BSS (Blind Source Separation) and Principal component analysis (PCA) works as its preprocessing algorithm. This work proposes time efficient and high precision PCA architecture which operates on 2 channels each with 3000 samples in single precision FP (floating point) format. Architecture uses high speed parallel computations for throughput producing more than 3.5 Gflops and FP units are incorporated for high precision.","PeriodicalId":222768,"journal":{"name":"2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A time efficient architecture implementation of PCA for ICA\",\"authors\":\"Parivesh, Ranjan Sharma\",\"doi\":\"10.1109/ICECA.2017.8203637\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Independent component analysis (ICA) Algorithm is a popular algorithm for BSS (Blind Source Separation) and Principal component analysis (PCA) works as its preprocessing algorithm. This work proposes time efficient and high precision PCA architecture which operates on 2 channels each with 3000 samples in single precision FP (floating point) format. Architecture uses high speed parallel computations for throughput producing more than 3.5 Gflops and FP units are incorporated for high precision.\",\"PeriodicalId\":222768,\"journal\":{\"name\":\"2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)\",\"volume\":\"37 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICECA.2017.8203637\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICECA.2017.8203637","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

独立分量分析(ICA)算法是一种常用的盲源分离算法，主成分分析(PCA)是其预处理算法。本文提出了一种具有时间效率和高精度的PCA架构，该架构以单精度FP(浮点)格式在2个通道上运行，每个通道有3000个样本。架构采用高速并行计算，吞吐量超过3.5 Gflops，并集成FP单元以实现高精度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A time efficient architecture implementation of PCA for ICA

Independent component analysis (ICA) Algorithm is a popular algorithm for BSS (Blind Source Separation) and Principal component analysis (PCA) works as its preprocessing algorithm. This work proposes time efficient and high precision PCA architecture which operates on 2 channels each with 3000 samples in single precision FP (floating point) format. Architecture uses high speed parallel computations for throughput producing more than 3.5 Gflops and FP units are incorporated for high precision.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2017 International conference of Electronics, Communication and Aerospace Technology (ICECA)

自引率

0.00%

发文量