Abstract: This paper puts forward the principal of K Nearest Neighbor（KNN） classification based on Principal Component Analysis（PCA），and applies it into the research of the Cardiotocograph（CTG） classification.The main idea is to normalize the attribute of the sample for training and testing and to calculate the degree of correlation of different attributes at first，then to build up new attribute sets and apply them to KNN for classification.This paper has tested the model for 2，120 Cardiotocograph data，the results indicate that the classification is steady，the correction of the accuracy is improving，and it can reduce high-dimensional space search of the complexity of the K neighbors，reducing the computational burden.

Key words: Principal Component Analysis（PCA）, K Nearest Neighbor（KNN）, Cardiotocograph（CTG）

摘要： 提出了基于主成分分析（Principal Component Analysis，PCA）的K近邻（K Nearest Neighbor，KNN）分类原理，并将其应用于胎心率与宫缩描记图分类。主要思想是：对训练样本和测试样本进行降维，并对降维后的测试样本使用KNN分类技术分类。选择2 120组胎心率与宫缩描记图数据，使用该方法进行分类测试。实验结果表明，使用该类模型，分类结果稳定，分类准确率高，并且能够降低高维空间搜索K近邻的复杂性，减轻计算负担。

关键词: 主成分分析, K近邻分类, 胎心率与宫缩描记图