A Binary Approximate Naive Bayesian Classification Algorithm Based on SOM Neural Network Clustering

Abstract

Although the classification performance of Naive Bayesian algorithm is relatively good, the time complexity and spatial complexity of the algorithm are linearly increasing with the increase of data volume. In order to reduce the complexity of Naive Bayesian algorithm, a two - point approach naive Bayesian algorithm combining SOM neural network clustering is proposed. Firstly, the SOM neural network clustering algorithm is used to reduce the number of classes in the original data set, and the spatial complexity of the Naive Bayesian classification algorithm is reduced. Then, by using the dichotomy approach, Conditional probability approximation operation, the time complexity of the classification algorithm is reduced. The experimental results show that the proposed algorithm can reduce the time complexity and spatial complexity of the algorithm under the premise of ensuring the classification accuracy of the algorithm, and improve the classification performance of Naive Bayesian algorithm.