Klasifikasi Dan Pengenalan Citra Lawo Dan Sapu Lue Menggunakan Metode Tree

OME, Florantina (2024) Klasifikasi Dan Pengenalan Citra Lawo Dan Sapu Lue Menggunakan Metode Tree. Undergraduate thesis, Universitas Katolik Widya Mandira Kupang.

	Text ABSTRAK.pdf Download (430kB)
	Text BAB I.pdf Download (408kB)
	Text BAB ll.pdf Restricted to Repository staff only Download (601kB)
	Text BAB III.pdf Restricted to Repository staff only Download (980kB)
	Text BAB IV.pdf Restricted to Repository staff only Download (1MB)
	Text BAB V.pdf Restricted to Repository staff only Download (502kB)
	Text BAB VI.pdf Download (326kB)
	Text DAFTAR PUSTAKA.pdf Download (473kB)

Abstract

Classifying images into "Sapu Lue" and "Lawo" categories has significant relevance in the context of pattern recognition and image processing applications. In this study, we investigate the use of tree-based classification algorithms to differentiate between these two categories. A 20-fold cross-validation method was applied to test the model performance, focusing on evaluating classification accuracy, area under the ROC curve (AUC), and other metrics. The test results show that the model has a good ability to differentiate between the two classes, with an AUC value of 0.891 and classification accuracy of 89.8%. However, the test results also revealed a tendency for the model to be better at predicting the negative class than the positive class. Further analysis of the classification results showed that there were examples that were misclassified, especially in predicting the "Lawo" class. Based on these findings, it is recommended to conduct further research to improve the model performance. Improvement efforts that can be made include expanding attributes, dealing with classimbalance, and experimenting with various other classification algorithms. It is hoped that this can improve themodel's ability to better identify and differentiate images between the two categories.

Actions (login required)

View Item