摘要
本文提出一种新的基于KNN分类的半监督学习self-training改进算法,并以多个UCI数据集为实验,对基于KNN的半监督分类模型算法进行改进,充分利用已知类别标签数据的正确知识进行自训练,以得到最终分类结果。实验结果表明,该方法能显著提高分类准确率。
An improved semi-supervised self-training classification learning algorithm is proposed based on K nearest neighbor,and several UCI data sets are used for experiments to improve the KNN-based semi-supervised classification model(self-training model) algorithm.The labeled data which gives the correct knowledge from the training is provided to get the final classification results.And the results show that the method can increase the classification accuracy dramatically.
出处
《广西师范大学学报(自然科学版)》
CAS
北大核心
2012年第1期45-49,共5页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家863计划项目(2012AA011005)
关键词
半监督学习
KNN分类器
自训练
semi-supervised learning
KNN classification
self-training