JIITA, vol.5 no.2, p.453-461, 2021, DOI: 10.22664/ISITA.2021.5.2.453
Phuc Hong Ngo 1), Donghwoon Kwon 2)
1) Department of Mathematics and Computer Science, Beloit College, Beloit, USA
2) Department of Mathematics, Computer Science, and Physics, Rockford University, Rockford, USA
Abstract: Machine learning is widely used for classification in various fields. In this research, we compared and analyzed the performance of three popular machine learning classifiers such as KNN, SVM, and ANN, using the leaf dataset. The original dataset was preprocessed, and the feature selection technique was used to divide the preprocessed dataset into two different types of the dataset. According to experiments, the ANN classifier showed 76.18% of accuracy when all the features were employed, and it outperformed other classifiers. However, when partial features were employed, the SVM classifier showed 73.31% of accuracy that outperformed other classifiers.
Keywords: Machine Learning; KNN; SVM; ANN
Fullpaper: