Comparative Analysis of Different Machine Learning Algorithms in Classification
Weiwen Xu, Zhenghao Zhu, Lincong Wang · 2022 International Conference on Big Data, Information and Computer Network (BDICN) · 2022
This paper aims to find a relatively better method to deal with the classification problems of different data sets by exploring other different machine learning methods. The main research direction is to analyze the performance difference of the machine learning method in the data classification of Gaussian Distribution, Images, Voice, Text, and Excel to find the better classification method for the corresponding data set. This study mainly used three machine learning methods: k-nearest neighbors algorithm (KNN), Support-vector machine (SVM), and neural network. The final test results show that for relatively simple discrete data, such as Excel, KNN has the best effect. In addition, the SVM and KNN methods for Images data are inferior to neural networks. For the remaining two data classifications, these three machine learning methods have reasonable accuracy rates.