IMPLEMENTASI METODE HSV, DAN ALGORITMA K-NEAREST NEIGHBORS (KNN) TERHADAP DETEKSI KANKER MELANOMA

NURLAELAH (2023) IMPLEMENTASI METODE HSV, DAN ALGORITMA K-NEAREST NEIGHBORS (KNN) TERHADAP DETEKSI KANKER MELANOMA. Undergraduate Theses thesis, Universitas Tadulako.

Full text not available from this repository.

Abstract

Deteksi permasalahan tahi lalat ini bertujuan untuk mengenali permasalahan atau penyakit tahi lalat secara dini. Adapun penyakit yang dapat dideteksi yaitu melanoma maligma dan nevus melanositi. Sistem deteksi ini memanfaatkan ciri warna dari citra digital tahi lalat. Ciri warna akan membedakan setiap permasalahan tahi lalat berdasarkan tingkat keparahannya. Metode yang digunakan adalah Hue Saturation Value (HSV), dengan metode klasifikasi K-Nearest Neighbors (KNN). Data citra tahi lalat yang digunakan sebanyak 150 citra digital tahi lalat yang dibagi menjadi 60?ta latih dan 40?ta uji. Penelitian ini menghasilkan akurasi sebesar 98,51?n error rate 1,49?tection of mole problems aims to recognize mole problems or diseases early. The diseases that can be detected are maligma melanoma and melanositi nevus. This detection system utilizes the color characteristics of the digital image of the mole. Color characteristics will distinguish each mole problem based on its severity. The method used is Hue Saturation Value (HSV), with the classification method K-Nearest Neighbors (KNN). The mole image data used was as many as 150 digital images of moles divided into 60% training data and 40% test data. This study resulted in an accuracy of 98.51% and an error rate of 1.49%.

Item Type: Thesis (Undergraduate Theses)
Subjects: University Structure > Faculty of Engineering > Informatics Engineering
S1 - Undergraduate Thesis > Faculty of Engineering > Informatics Engineering
Divisions: Faculty of Engineering > Informatics Engineering
Tadulako Subject Areas > S1 - Undergraduate Thesis > Faculty of Engineering > Informatics Engineering
Depositing User: system estd estd
Date Deposited: 01 Feb 2023 07:03
Last Modified: 01 Feb 2023 06:35
URI: http://repository.untad.ac.id/id/eprint/14006

Actions (login required)

View Item View Item