arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.07779cs.LG
收藏

基于监督非参数包围盒方法的高维数据分类

Binary Classification for High Dimensional Data using Supervised Non-Parametric Ensemble Method

Thakur Institute Of Management Studies, Career Development & Research(塔库尔管理研究、职业发展与研究学院);University of Mumbai(孟买大学)

Nandan Kanvinde, Abhishek Gupta, Raunak Joshi, Pinky Gerela

摘要:

用于分类的高维数据确实给机器学习算法带来了许多困难。泛化可以使用集成学习方法来完成,例如基于装袋的监督非参数随机森林算法。本文针对多囊卵巢综合征数据集,采用随机森林方法解决了高维数据的二值分类问题。我们已经执行了实现,并提供了一个详细的可视化数据的一般推理。训练准确率达到95.6%,验证准确率超过91.74%。

英文摘要:

High dimensional data for classification does create many difficulties for machine learning algorithms. The generalization can be done using ensemble learning methods such as bagging based supervised non-parametric random forest algorithm. In this paper we solve the problem of binary classification for high dimensional data using random forest for polycystic ovary syndrome dataset. We have performed the implementation and provided a detailed visualization of the data for general inference. The training accuracy that we have achieved is 95.6% and validation accuracy over 91.74% respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑