Rosadi, Muhammad Imron (2016) Klasifikasi Massa Pada Citra Mammogram Menggunakan Kombinasi Seleksi Fitur F-Score Dan LS-SVM. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
5113201024-Master_Thesis.pdf - Accepted Version Download (1MB) | Preview |
Abstract
Kanker payudara adalah penyakit yang paling umum diderita oleh perempuan
pada banyak negara. Pemeriksaan kanker payudara dapat dilakukan menggunakan
citra mammogram. Sistem Computer-aided detection (CAD). Analisis CAD yang telah
dikembangkan adalah Ekstraksi Ftur GLCM, reduksi/seleksi fitur dan SVM. Pada
SVM (Support vector Machine) maupun LS-SVM (least Square Support vector
Machine) terdapat tiga masalah yang muncul, yaitu; bagaimana memilih fungsi kernel,
berapa jumlah fitur input yang optimal, dan bagaimana menentukan parameter kernel
terbaik. Jumlah fitur dan nilai parameter kernel yang diperlukan saling
mempengaruhi, sehingga seleksi fitur diperlukan dalam membangun sistem klasifikasi.
Pada penelitian ini bertujuan untuk mengklasifikasi massa pada citra
mammogram berdasarkan dua kelas yaitu kelas kanker jinak dan kelas kanker ganas.
Ekstraksi fitur menggunakan gray level co-occurrence matrix (GLCM). Hasil proses
ekstraksi fitur tersebut kemudian diseleksi mengunakan metode F-Score. F-Score
diperoleh dengan menghitung nilai diskriminan data hasil ekstraksi fitur di antara data
dua kelas pada data training.Nilai F-Score masing-masing fitur kemudian diurutkan
secara descending. Hasil pengurutan tersebut digunakan untuk membuat kombinasi
fitur. Kombinasi fitur tersebut digunakan sebagai input LS-SVM.
Dari hasil ujicoba bahwa menggunakan kombinasi seleksi fitur sangat berpengaruh
terhadap tingkat akurasi. Akurasi terbaik didapat menggunakan LS-SVM RBF dan
SVM RBF dengan kombinasi seleksi fitur maupun tanpa kombinasi seleksi fitur dengan
nilai akurasi yaitu 97,5%. Selain itu juga seleksi fitur mampu mengurasi waktu
komputasi
===================================================================================================
Breast cancer is the most common disease suffered by women in many countries. Breast
cancer screening can be done using a mammogram image. Computer-aided detection
system (CAD). CAD analysis that has been developed is GLCM efficient feature
extraction, reduction / feature selection and SVM. In SVM (Support Vector Machine)
and LS-SVM (Support Vector Machine Square least) there are three problems that
arise, namely; how to choose the kernel function, how many input features are optimal,
and how to determine the best kernel parameters. The number of features and value
required kernel parameters affect each other, so that the selection of the features
needed to build a system of classification.
In this study aims to classify image of masses on digital mammography based on two
classes benign cancer and malignant cancer. Feature extraction using gray level cooccurrence matrix (GLCM). The results of the feature extraction process then selected
using the method F-Score. F-Score is obtained by calculating the value of the
discriminant feature extraction results data between two classes of data in the data
training. Value F-Score of each feature and then sorted in descending order. The
sequencing results are used to make the combination of features. The combination of
these features are used as input LS-SVM.
From the experiments that use a combination of feature selection affects the accuracy
ting-kat. Best accuracy obtained using LS-SVM and SVM RBF RBF with combination
or without the combination of feature selection with accuracy value is 97.5%. It also
features a selection able to curate the computation time
| Item Type: | Thesis (Masters) |
|---|---|
| Additional Information: | RTIf 618.190 757 Ros k |
| Uncontrolled Keywords: | Kanker payudara, GLCM, F-Score, LS-SV |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Mr. Tondo Indra Nyata |
| Date Deposited: | 14 Apr 2020 00:57 |
| Last Modified: | 14 Apr 2020 00:59 |
| URI: | http://repository.its.ac.id/id/eprint/75771 |
Actions (login required)
 |
View Item |