Maximum Mutual Information Feature Extraction Method Based on the Cloud Platform

Shasha Wei; Huijuan Lu; Wei Jin; Chao Li

doi:10.3969/j.issn.1000-0801.2013.10.008

您当前的位置：

首页 >

文章列表页 >

Maximum Mutual Information Feature Extraction Method Based on the Cloud Platform

Cloud computing column | 更新时间：2024-06-05

- Maximum Mutual Information Feature Extraction Method Based on the Cloud Platform
- Telecommunications Science Vol. 29, Issue 10, Pages: 38-42(2013)
- 作者机构：
  
  1. 中国计量学院信息工程学院杭州310018
  2. 中国计量学院机电工程学院杭州310018
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1000-0801.2013.10.008
  CLC：
- Published Online：2013-10，
  
  Published：20 October 2013
- 稿件说明：
移动端阅览
Shasha Wei, Huijuan Lu, Wei Jin, et al. Maximum Mutual Information Feature Extraction Method Based on the Cloud Platform[J]. Telecommunications science, 2013, 29(10): 38-42.
DOI：

Shasha Wei, Huijuan Lu, Wei Jin, et al. Maximum Mutual Information Feature Extraction Method Based on the Cloud Platform[J]. Telecommunications science, 2013, 29(10): 38-42. DOI： 10.3969/j.issn.1000-0801.2013.10.008.

摘要

随着大规模基因芯片的应用，针对高维度的基因表达数据存在大量无关和冗余特征可能降低分类器性能的问题，提出了一种基于云平台的互信息最大化特征提取（CMI-Selection）方法。Hadoop云计算平台对基因表达数据划分后进行并行计算，同时结合互信息最大化方法对特征进行提取，实现了云计算平台上的特征过滤模型。实验结果表明，基于云平台的互信息最大化特征提取方法能够在保证较高分类精度的情况下，快速提取特征，节省大量时间资源，是一种高效的基因特征提取系统。

Abstract

With the large-scale application of gene chip

gene expression data with high dimension which exists a large number of irrelevant and redundant features may reduce classifier performance problem.A maximum mutual information feature extraction method based on cloud platforms was proposed.Hadoop cloud computing platform could be a parallel computing after gene expression data segmentation

features was extracted at the same time combined with the maximum mutual information method and the characteristics of cloud computing platform filter model was realized.Simulation experiments show that the maximum mutual information feature extraction method based on the cloud platform can rapid extraction of features in a higher classification accuracy which save a lot of time resources to make a highly efficient gene feature extraction system.

关键词

Keywords

references

Kang H N , Chen I M , Wilson C S . Gene expression classifiers for relapse-free survival and minimal residual disease improve risk classification and outcome prediction in pediatric B-precursor acute lymphoblastic leukemia . Blood , 2010 ,（ 115 ）: 1394 ～ 1405

任江涛，黄焕宇，孙婧昊 . 基于相关性分析及遗传算法的高维数据特征选择 . 计算机应用， 2006 ， 26 （ 6 ）: 1403 ～ 1405

裘国永，王娜，汪万紫 . 基于互信息和遗传算法的两阶段特征选择方法 . 计算机应用， 2012 ， 29 （ 8 ）: 2903 ～ 2905

Peng H H , Long F H , Ding C . Feature selection based on mutual information:criteria of max-dependency,max-relevance,and min-redundancy . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2005 , 27 （ 8 ）: 1226 ～ 1238

Ding C , Peng H . Minimum redundancy feature selection from microarray gene expression data . Journals of Bioinformatics and Computational Biology , 2005 , 3 （ 2 ）: 185 ～ 205

王凌，陈震，危水根等 . 基于改进最大互信息法的MR 切片图像配准 . 生物医学工程学杂志， 2012 ， 29 （ 2 ）: 201 ～ 205

杨虎，马斌荣，任海萍等 . 基于最大互信息的人脑MR-PET 图像配准方法 . 北京生物医学工程， 2001 ， 20 （ 4 ）: 246 ～ 251

张彾卫，万文强 . 基于云计算平台的代价敏感集成学习算法研究 . 山东大学学报（工学版）， 2012 , 42 （ 4 ）: 19 ～ 23

Vouk M A . Cloud computing-issues,research and implem entations . Proceedings of ITI 2008 , Dubrovnik , 2008 : 79 ～ 120

朱杰 . 云计算在基于贝叶斯分类的垃圾短信过滤中的研究与应用 . 电子科技大学硕士学位论文， 2010

王明怡 . 微阵列数据挖掘技术的研究 . 浙江大学博士学位论文， 2004

刘庆和，梁正友 . 一种基于信息增益的特征优化选择方法 . 计算机工程与应用， 2011 ， 47 （ 12 ）

Hu Y , Loizou P C . Speech enhancement based on wavelet thresholding the multitaper spectrum . IEEE Transactions on Speech and Audio Processing , 2004 , 12 （ 1 ）: 59 ～ 67

戴元顺 . 云计算技术简述 . 信息通信技术， 2010 （ 2 ）

Views

477

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Technical evolution and development trend of quantum computing cloud platform

A hybrid model for smart grid theft detection based on deep learning

Optimal active defense decision model of wireless communication network under APT attack

Damage toughness assessment method of power backbone communication network based on power big data

Virtual machine scheduling model based on Shapley value modified genetic algorithm in cloud computing

Related Author

HAO Yuanchen

XIE Yuheng

TANG Jianjun

Yinling LIAO

Jincan LI

Bing WANG

Jun ZHANG

Yaoyuan LIANG

Related Institution

Research Institute of China Telecom Co., Ltd.

Wuzhou Power Supply Bureau of Guangxi Power Grid Co., Ltd.

Guangxi Power Grid Co., Ltd.

Jiaxing Key Laboratory of Industrial Internet Security

Jiaxing Branch of China Telecom Co., Ltd.

⁰