• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

相似文献

1
Determination of the number of clusters through logistic regression analysis.通过逻辑回归分析确定聚类数量。
J Appl Stat. 2023 Nov 20;51(12):2344-2363. doi: 10.1080/02664763.2023.2283687. eCollection 2024.
2
Folic acid supplementation and malaria susceptibility and severity among people taking antifolate antimalarial drugs in endemic areas.在流行地区，服用抗叶酸抗疟药物的人群中，叶酸补充剂与疟疾易感性和严重程度的关系。
Cochrane Database Syst Rev. 2022 Feb 1;2(2022):CD014217. doi: 10.1002/14651858.CD014217.
3
An overview on parametric quantile regression models and their computational implementation with applications to biomedical problems including COVID-19 data.参数分位数回归模型概述及其在包括 COVID-19 数据在内的生物医学问题中的计算实现。
Comput Methods Programs Biomed. 2022 Jun;221:106816. doi: 10.1016/j.cmpb.2022.106816. Epub 2022 Apr 25.
4
Erratum: High-Throughput Identification of Resistance to Pseudomonas syringae pv. Tomato in Tomato using Seedling Flood Assay.勘误：利用幼苗浸没法高通量鉴定番茄对丁香假单胞菌 pv.番茄的抗性。
J Vis Exp. 2023 Oct 18(200). doi: 10.3791/6576.
5
Modified fuzzy gap statistic for estimating preferable number of clusters in fuzzy k-means clustering.用于估计模糊k均值聚类中最优聚类数的改进模糊间隙统计量
J Biosci Bioeng. 2008 Mar;105(3):273-81. doi: 10.1263/jbb.105.273.
6
Optimal Subsampling for Large Sample Logistic Regression.大样本逻辑回归的最优子采样
J Am Stat Assoc. 2018;113(522):829-844. doi: 10.1080/01621459.2017.1292914. Epub 2018 Jun 6.
7
Cluster-level statistical inference in fMRI datasets: The unexpected behavior of random fields in high dimensions.功能磁共振成像数据集的簇水平统计推断：高维随机字段的意外行为
Magn Reson Imaging. 2018 Jun;49:101-115. doi: 10.1016/j.mri.2018.01.004. Epub 2018 Feb 3.
8
9
Visual MRI: merging information visualization and non-parametric clustering techniques for MRI dataset analysis.可视化磁共振成像：融合信息可视化与非参数聚类技术用于磁共振成像数据集分析。
Artif Intell Med. 2008 Nov;44(3):183-99. doi: 10.1016/j.artmed.2008.06.006. Epub 2008 Sep 4.
10
A non-parametric mixture model for genome-enabled prediction of genetic value for a quantitative trait.一种用于基于基因组预测数量性状遗传值的非参数混合模型。
Genetica. 2010 Oct;138(9-10):959-77. doi: 10.1007/s10709-010-9478-4. Epub 2010 Aug 25.

本文引用的文献

1
MulticlusterKDE: a new algorithm for clustering based on multivariate kernel density estimation.多聚类核密度估计：一种基于多元核密度估计的聚类新算法。
J Appl Stat. 2020 Jul 30;49(1):98-121. doi: 10.1080/02664763.2020.1799958. eCollection 2022.
2
Unsupervised classification of eclipsing binary light curves through -medoids clustering.通过类中位数聚类对食双星光变曲线进行无监督分类。
J Appl Stat. 2019 Jun 27;47(2):376-392. doi: 10.1080/02664763.2019.1635574. eCollection 2020.
3
Computational cluster validation in post-genomic data analysis.后基因组数据分析中的计算聚类验证
Bioinformatics. 2005 Aug 1;21(15):3201-12. doi: 10.1093/bioinformatics/bti517. Epub 2005 May 24.

通过逻辑回归分析确定聚类数量。

Determination of the number of clusters through logistic regression analysis.

作者信息

Modak Soumita

机构信息

Faculty, Department of Statistics, University of Calcutta, Basanti Devi College, Kolkata, India.

出版信息

J Appl Stat. 2023 Nov 20;51(12):2344-2363. doi: 10.1080/02664763.2023.2283687. eCollection 2024.

DOI:10.1080/02664763.2023.2283687
PMID:39267708
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11389630/
Abstract

We advise a novel measure to determine the unknown number of clusters underlying a designated sample through implementation of the parametric logistic regression model. The regression analysis is carried out to estimate the probabilities of inclusion for every individual member from data, irrespective of its parent distribution, to each of the clusters under existence. The proposed one is shown to be superior to its well-known rivals by means of both synthetic and real-world data sets, while designed to significantly reduce the computational burden serving our desired purpose.

摘要

我们建议采用一种新方法，通过实施参数逻辑回归模型来确定指定样本背后未知的聚类数量。进行回归分析是为了从数据中估计每个个体成员属于现有每个聚类的包含概率，而不考虑其母体分布。通过合成数据集和真实数据集表明，所提出的方法优于其著名的竞争对手，同时旨在显著减轻计算负担以满足我们的预期目的。