摘要
针对朴素贝叶斯分类器硬分类的不足,将模糊C-均值聚类与朴素贝叶斯分类相结合,提出一类新的基于模糊聚类的混合朴素贝叶斯分类模型,并给出它的分类误差估计方法。理论分析与实验结果表明,基于模糊聚类的混合朴素贝叶斯分类模型可行,其分类的误差估计方法有效。新的基于模糊聚类的混合朴素贝叶斯分类模型提高了模式分类能力。
A new hYbrid Naive Bayes classification model, which combines fuzzy C-means and naive Bayes classification, is put forward, in view of a shortage of classifications by the naive Bayes classifier, and the method of its classification error estimation is proposed. The theoretical analysis and the experimental result show that the new hybrid Naive Bayes classification model based on fuzzy clustering is feasible, and the method of its classification error estimation is effective, which is used to fuzzy pattern classifications of more sets of objects.
出处
《安徽建筑工业学院学报（自然科学版）》
2009年第3期88-91,共4页
Journal of Anhui Institute of Architecture(Natural Science)
关键词
模糊聚类
朴素贝叶斯分类
错误率
误差估计
fuzzy clustering
naive Bayes classification
error rate
error estimation
