Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : INDONESIAN JOURNAL OF APPLIED PHYSICS

Klasifikasi Kanker Paru Paru menggunakan Naïve Bayes dengan Variasi Filter dan Ekstraksi Ciri GLCM Mohtar Yunianto; Soeparmi Soeparmi; Cari Cari; Fuad Anwar; Delta Nur Septianingsih; Tonang Dwi Ardyanto; Resta Farits Pradana
INDONESIAN JOURNAL OF APPLIED PHYSICS Vol 11, No 2 (2021): October
Publisher : Department of Physics, Sebelas Maret University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijap.v11i2.53213

Abstract

Telah berhasil dilakukan klasifikasi kanker paru-paru dari 120 data citra CT Scan. Pada penelitian, proses preposisi dimulai dengan variasi filtering yaitu low pass filter, median filter, dan high pass filter. Segmentasi yang digunakan yaitu Otsu Thresholding yang kemudian teksturnya akan diekstraksi menggunakan fitur Gray Level Co-occurrence Matrix (GLCM) dengan variasi arah sudut. Hasil dari ekstraksi GLCM dijadikan database yang akan menjadi dataset untuk pengklasifikasian citra menggunakan klasifikasi naïve bayes. Hasil dari penelitian dengan 12 buah variasi diperoleh hasil variasi terbaik adalah median filter dengan arah sudut GLCM 0° menunjukkan tingkat akurasi yang paling tinggi sebesar 88,33 %.
Pneumonia Classification Based on GLCM Features Extraction using K-Nearest Neighbor Suharyana Suharyana; Fuad Anwar; Armylia Chandra Dewi; Mohtar Yunianto; Umi Salamah; Rifai Chai
INDONESIAN JOURNAL OF APPLIED PHYSICS Vol 13, No 2 (2023): IJAP Volume 13 ISSUE 02 YEAR 2023
Publisher : Department of Physics, Sebelas Maret University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijap.v13i2.77120

Abstract

Pneumonia has been detected using Machine learning. The stages in this study began with preprocessing in 4 stages: resizing, cropping, filtering using a high pass filter, and Adaptive Histogram Equalization. The feature extraction process continued with 22 Gray Level Co-occurrence Matrix (GLCM) features and classification using K-Nearest Neighbor (KNN). The image used was 150 data sets for training on the classification of 3 classes with a ratio of 50:50:50 while training on two classes was 50 bacterial pneumonia and 50 viral pneumonia. The most optimal training data accuracy results were obtained using the angle direction on the GLCM, namely 135o with the KNN classification (k = 3). For the classification of two classes Using 40 data sets, an accuracy of 91% was obtained, while testing for three classes with 60 data sets was 83.3%.