Application of kernel-based multiple gene selection method and extreme learning machine in microarray analysis

YANG Qin; DONG Hong-wei; XUE Yan-na

doi:10.13873/J.1000-9787(2016)05-0146-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Application of kernel-based multiple gene selection method and extreme learning machine in microarray analysis

更新时间：2025-09-11

- Application of kernel-based multiple gene selection method and extreme learning machine in microarray analysis
- Vol. 35, Issue 5, Pages: 146-148+153(2016)
- 作者机构：
  
  江南大学物联网工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2016)05-0146-03
  CLC： Q811.4
- Published：2016
- 稿件说明：
移动端阅览
[1]杨勤,董洪伟,薛燕娜.核多元基因选择和极限学习机在微阵列分析中的应用[J].传感器与微系统,2016,35(05):146-148+153.

YANG Qin, DONG Hong-wei, XUE Yan-na. Application of kernel-based multiple gene selection method and extreme learning machine in microarray analysis[J]. 2016, 35(5): 146-148+153.
[1]杨勤,董洪伟,薛燕娜.核多元基因选择和极限学习机在微阵列分析中的应用[J].传感器与微系统,2016,35(05):146-148+153. DOI： 10.13873/J.1000-9787(2016)05-0146-03.

YANG Qin, DONG Hong-wei, XUE Yan-na. Application of kernel-based multiple gene selection method and extreme learning machine in microarray analysis[J]. 2016, 35(5): 146-148+153. DOI： 10.13873/J.1000-9787(2016)05-0146-03.

摘要

针对微阵列数据样本量少、维度高的特点

结合当前数据降维方法中没有考虑特征与特征之间相关性的缺点

提出一种核最小二乘的特征基因选择方法。将解释变量空间通过非线性映射转换到高维空间上

再在高维空间上进行最小二乘回归

并采用极限学习机进行训练和预测。结果表明:对三种经典数据集的分类精度分别达到90.47%

88.89%

88.23%

高于传统的机器学习算法

充分表明本方法的优越性。

Abstract

As quantity of microarray data sample is little and dimension of each sample is high

combined with disadvantages that in current data dimension reduction methods

correlation between features is not considered

put forward a kind of kernel-based least squares method for feature gene selection. Map explaining variable space to high dimension space

via nonlinear mapping transformation

and then carry out least-squares regression in high dimensional space; use extreme learning machine for training and predicting. The results show that classification precision of the three kinds of classic data set is 90. 47 %

88. 89 %

88. 23 %

which is higher than traditional machine learning algorithms

which fully demonstrates superiority of this method.

关键词

Keywords

references

一种微阵列数据降维新方法 [J]. 王刚,张禹瑄,李颖,陈慧灵,胡玮通,秦磊. 吉林大学学报(工学版) . 2014(05)

核主成分分析与典型相关分析相融合的人脸识别 [J]. 金益,姜真杰. 计算机应用与软件 . 2014(01)

基于流形学习的基因微阵列数据分类方法 [J]. 李强,石陆魁,刘恩海,王歌. 郑州大学学报(工学版) . 2012(05)

基于过采样技术和随机森林的不平衡微阵列数据分类方法研究 [J]. 于化龙,高尚,赵靖,秦斌. 计算机科学 . 2012(05)

微阵列数据癌症分类问题中的基因选择 [J]. 张丽娟,李舟军. 计算机研究与发展 . 2009(05)

极限学习机及其在无线频谱预测中的应用研究 [D]. 吕娜. 兰州大学 2014

Handwritten character recognition using wavelet energy and extreme learning machine [J] . Binu Chacko,V. Vimal Krishnan,G. Raju,P. Babu Anto. International Journal of Machine Learning and Cybernetics . 2012 (2)

Extreme learning machine: Theory and applications [J] . Guang-Bin Huang,Qin-Yu Zhu,Chee-Kheong Siew. Neurocomputing . 2006 (1)

Gene-expression profiles to predict distant metastasis of lymph-node-negative primary breast cancer [J] . Yixin Wang,Jan GM Klijn,Yi Zhang,Anieta M Sieuwerts,Maxime P Look,Fei Yang,Dmitri Talantov,Mieke Timmermans,Marion E Meijer-van Gelder,Jack Yu,Tim Jatkoe,Els MJJ Berns,David Atkins,John A Foekens. The Lancet . 2005 (9460)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on recognition of voltage sag source based on GA-ELM

Network intrusion detection method based on CPS system

Extreme learning machine optimized by improved ABC

Related Author

LU Caixia

WANG Xinhuan

WANG Quanyi

ZHANG Yu

CAO Jiangtao

KAN Zhe

JI Xiaofei

MAO Yu

Related Institution

School of Electrical Engineering and Automation, Henan Polytechnic University

School of Information and Control Engineering,Liaoning Shihua University

School of Automation,Shenyang Aerospace University

Key Laboratory of Advanced Process Control for Light Industry,Ministry of Education,School of Internet of Things Engineering,Jiangnan University

Freshwater Fisheries Research Center,Chinese Academy of Fishery Science

⁰