Analisis Perbandingan KNN dengan SVM untuk Klasifikasi Penyakit Diabetes Retinopati berdasarkan Citra Eksudat dan Mikroaneurisma
Journal: Jurnal Elkomika (Vol.3, No. 1)Publication Date: 2015-01-05
Authors : SUCI AULIA; SUGONDO HADIYOSO; DADAN NUR RAMADAN;
Page : 75-90
Keywords : Diabetic Retinopathy; KNN; SVM; Wavelet.;
Abstract
Research based on severity classification of the disease diabetic retinopathy by using image processing method is still hotly debated, the image is used to detect the type of this disease is an optical image of the disk, microaneurysm, exudates, and bleeding of the image of the fundus. This study was performed to compare SVM method with KNN method for classification of diabetic retinopathy disease (mild, moderate, severe) based on exudate and microaneurysm image. For feature extraction uses wavelet method, and each of the two methods. This study made use of 160 test data, each of 40 images for normal class, mild class, moderate class, severe class. The accuracy obtained by KNN higher than SVM, with 65% and 62%. KNN classification method achieved the best results with the parameters K = 9, cityblock. While the classification with SVM method obtained the best results with parameters One agains all .
Other Latest Articles
- Implementasi Sistem Bel Rumah Otomatis berbasis Sensor Ultrasonik
- Implementasi Regulator Oksigen Otomatis berdasarkan Tingkat Pernapasan menggunakan Logika Fuzzy
- Perancangan dan Realisasi Generator Ozon menggunakan Metoda Pembangkitan Tegangan Tinggi Bolak ? Balik (AC)
- Pendeteksi Sikap pada Model Wahana Terbang menggunakan Inertial Measurement Unit
- Perancangan dan Realisasi Web-Based Data Logging System menggunakan ATmega16 melalui Hypertext Transfer Protocol (HTTP)
Last modified: 2016-03-15 16:46:38