Naïve Bayes Classifier Based On Optimized Harmony Search Algorithm

Abstract

Abstract Naïve Bayes classifiers have made a big splash in the field of data mining and supervised learning. However, the assumption of "conditional independence of attributes" is difficult to realize in reality, which affects the final classification results. To address this problem, this paper introduces a dynamic weighting mechanism to assign corresponding weights to each attribute according to its influence on the classification result, and constructs a weight-based naïve Bayes classifier. The classifier takes the classification error rate as the objective function, uses the Harmony Search Algorithm to calculate the global optimal weights, and assigns the weights to each attribute after normalization. To improve the optimal-seeking ability of the Harmony Search Algorithm, this paper optimizes its new solution generation method and reduces the probability of falling into a local optimum by using an optimization scheme that accepts worse solutions with a certain probability. Experimental results demonstrate that the algorithm proposed in this paper has some improvement in classification indicators such as correct rate and F1-Score compared with the classical naïve Bayes classifier and other optimized naïve Bayes classifiers.