面向水质分类的分组降维核朴素贝叶斯模型

Study on Naive Bayes Model of Grouping Dimensionality Reduction Kernel for Water Quality Classification

为提高贝叶斯模型在实际数据中处理相关性维度时的效率、精度,并保持其可解释性,本文提出一种改进的核朴素贝叶斯模型。首先通过关联规则挖掘相关维度子集,然后对这些子集进行降维处理,利用降维后的数据构建核朴素贝叶斯模型。实际应用的结果显示,该模型减少了降维对数据的影响,在保留有效信息的同时,提高了模型的可解释性。

To improve the efficiency and accuracy of Bayesian models in handling correlation dimensions in actual data,and maintain their interpretability,this paper proposes an improved kernel naive Bayesian model.Firstly,relevant dimension subsets are mined through association rules,and then these subsets are subjected to dimensionality reduction processing to construct a kernel naive Bayesian model using the reduced data.The practical application results show that the model reduces the impact of dimensionality reduction on data,while retaining effective information and improving the interpretability of the model.