Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

TL-LASSO-Net: a hybrid transfer learning and LASSO-based framework for robust colon cancer histopathology classification on LC25000 and GlaS datasets.

Scientific reports·2026
Same author

An AI-based approach in determining the effect of meteorological factors on incidence of malaria

Frontiers in bioscience (Landmark edition)·2020
Same author

An automatic estimation of the ridge parameter for extreme learning machine.

Chaos (Woodbury, N.Y.)·2020
Same author

Cancer data classification using binary bat optimization and extreme learning machine with a novel fitness function.

Medical & biological engineering & computing·2019
Same author

A new backpropagation neural network classification model for prediction of incidence of malaria.

Frontiers in bioscience (Landmark edition)·2019
Same author

EIQ: EEG based IQ test using wavelet packet transform and hierarchical extreme learning machine.

Journal of neuroscience methods·2019

相关实验视频

Updated: Jul 10, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K

一种基于通用分类器神经网络的嵌入式特征选择方法,用于癌症分类.

Akshata K Naik1, Venkatanareshbabu Kuppili1

  • 1Department of Computer Science and Engineering, National Institute of Technology, Farmagudi, Ponda, Goa, India.

Computers in biology and medicine
|November 21, 2023
PubMed
概括

这项研究引入了加权通用分类器神经网络 (WGCNN),用于在高维数据中进行基因选择. WGCNN有效地捕获非线性相互作用,并在二进制和多类分类任务中表现良好.

科学领域:

  • 生物信息学是一种生物信息学.
  • 计算生物学 计算生物学
  • 机器学习 机器学习

背景情况:

  • 基因选择对于高维微阵列数据分类至关重要.
  • 现有的线性稀疏学习模型与非线性基因相互作用和多类问题作斗争.
  • 当前的方法往往会创建重叠的组,增加数据的维度.

研究的目的:

  • 为基因表达数据提出一种基于神经网络的新嵌入式特征选择方法.
  • 解决线性模型在捕捉非线性基因相互作用方面的局限性.
  • 为二进制和多类问题开发一种可解释和有效的特征选择方法.

主要方法:

  • 为了其可解释的架构,采用了通用分类器神经网络 (GCNN).
  • 开发了一个加权GCNN (WGCNN) 方法,将特征加权整合到神经网络训练中.
  • 在输入层实施了统计指导性丢失,以防止过度适应高维数据.

主要成果:

  • 在基因表达数据中,WGCNN在表示非线性关系方面表现出有效性.
  • 该方法在七个微阵列数据集中表现出强的性能,用于二进制和多类分类.
  • 实验验证证了WGCNN在F1得分和特征选择效率方面的优势,与最先进的方法相比.
关键词:
嵌入式功能选择选项嵌入式功能选择选项可以解释的模型.一般化分类器神经网络

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

768

相关实验视频

Last Updated: Jul 10, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.5K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

768

结论:

  • 在高维微阵列数据中,WGCNN为基因选择提供了有效和可解释的解决方案.
  • 拟议的方法通过捕捉非线性相互作用来克服线性模型的局限性.
  • WGCNN为生物信息学中的二进制和多类分类任务提供了一个强大的方法.