An image processing technique extracted four features of green coffee beans of different species which are the liberica, robusta, and excelsa. The acquired datasets were subjected to the Classification Learner App of MATLAB 2017. Among the 22 classifiers included in the Classification Learner App, 94.1 percent is the highest accuracy, obtained by the Coarse Tree Algorithm, while the lowest classification percentage was obtained by Boosted Tree Algorithm with 28.2% accuracy. Out of the 22 algorithms, only 4 got a classification accuracy that is lower than 90 percent and 18 algorithms got an accuracy of more than 90 percent. It can be concluded that the combined image processing and classification using data mining algorithms can be used in classifying green coffee bean species.
CITATION STYLE
Arboleda, E. R. (2019). Comparing performances of data mining algorithms for classification of green coffee beans. International Journal of Engineering and Advanced Technology, 8(5), 1563–1567.
Mendeley helps you to discover research relevant for your work.