Random Forests: Validation of an unsupervised machine learning algorithm, with application to genomic signatures

随机森林：验证无监督机器学习算法，并应用于基因组签名

• 批准号: 453960-2013
• 负责人: Dean, Charmaine
• 金额: $ 1.82万
• 依托单位: University of Western Ontario
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2013
• 资助国家: 加拿大
• 起止时间: 2013-01-01 至 2014-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=541751
• 关键词: Random; Forests; Validation; unsupervised; machine

Random forests is an ensemble learning method that integrates the decisions of a multitude of decision processes. It has become one of the most popular methods for many applications in ecology and the environmental sciences, in marketing, and insurance. For the analysis of microarray gene expression data such as considered here, it is a particularly useful tool because of its excellent performance in the situation where the data are sparse compared to the number of questions to be simultaneously addressed. This project develops and employs tools for validation of tests for identifying disease based on such data on the expression of genetic markers using random forests.

随机森林是一种集成多种决策过程决策的集成学习方法。它已经成为生态学和环境科学、市场营销和保险等领域中最受欢迎的方法之一。对于像这里考虑的微阵列基因表达数据的分析，它是一个特别有用的工具，因为它在与要同时解决的问题的数量相比数据稀疏的情况下具有优异的性能。该项目开发和使用工具，根据使用随机森林的遗传标记表达的这种数据，验证用于识别疾病的测试。