|
| 判别分析多类Fisher线性判别分析法 |
| Hu Chunyan1,Liu Huigang2,Hu Liangping1,3*(1.Graduate School, Academy of Military Sciences PLA China, Beijing 100850, China; |
| 投稿时间：2025-04-25 修订日期：2025-04-25 |
| DOI： |
| 中文关键词: 类线性判别分析 类内协方差矩阵 概率密度函数 多元正态分布 投影方向 |
| 英文关键词:Multi-class Linear Discriminant Analysis Within-class Covariance Matrix Probability Density Function Multivariate Normal Distribution Projection Direction |
| 基金项目: |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 【】本文目的是介绍与多类Fisher线性判别分析有关的基本概念、计算方法、两个实例及其用SAS实现计算的方法。基本概念包括类内协方差矩阵、类间协方差矩阵、概率密度函数、多元正态分布、投影和投影方向。计算方法涉及问题设定、判别准则、构建多类线性判别函数、分类规则。两个实例中的资料是相同的,都是“66条康乔水蛇的有关数据”。借助SAS软件,对两个实例中的数据进行了多类Fisher线性判别分析,对SAS输出结果给出了解释。 |
| 英文摘要: |
| 【】The purpose of this paper was to introduce the fundamental concepts, computational methods, two examples, and the implementation of these calculations using SAS software related to multi-class Fisher Linear Discriminant Analysis (LDA). The basic concepts included within-class covariance matrix, between-class covariance matrix, probability density function, multivariate normal distribution, projection, and projection direction. The computational methods involved problem setting, discriminant criteria, construction of multi-class linear discriminant functions, and classification rules. The data used in both examples were the same, specifically "data on 66 Kangqiao water snakes". Using SAS software, multi-class Fisher Linear Discriminant Analysis was performed on the data from both examples, and the SAS output results were interpreted. |
| 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|