Register: Jurnal Ilmiah Teknologi Sistem Informasi
Vol 2, No 1 (2016): Januari-Juni

Deteksi Kanker Kulit Melanoma dengan Linear Discriminant Analysis-Fuzzy k-Nearest Neigbhour Lp-Norm

Mentari, Mustika (Unknown)
Sari, Yuita Arum (Unknown)
Dewi, Ratih Kartika (Unknown)



Article Info

Publish Date
01 Jan 2016

Abstract

Seiring perkembangan teknologi dilakukan otomatisasi deteksi kanker kulit melalui citra dermoscopy. Pengambilan informasi fitur citra dermoscopy terganggu dengan outlier dan overfitting, karena faktor jenis kulit, penyebaran kanker yang tidak merata atau kesalahan sampling. Penelitian ini mengusulkan deteksi kanker kulit melanoma dengan mengintegrasikan metode fuzzy K-Nearest Neighbour (FuzzykNN), Lp-norm dan Linear Discriminant Analysis (LDA) untuk mengurangi outlier dan overfitting. Masukan berupa citra warna RGB yang dinormalisasi menjadi RGBr. Reduksi dimensi dengan LDA menghasilkan fitur dengan nilai eigen paling menonjol. LDA pada penelitian ini menghasilkan dua fitur paling menonjol dari 141 jenis fitur, yaitu wilayah tumor dan minimum wilayah tumor channel R. Kemudian dilakukan klasifikasi FuzzykNN dan metode pengukur jarak Lp-norm. Penggunaan metode LDA dan Lp-norm dalam proses klasifikasi ini mengatasi terjadinya overfitting. Akurasi yang dihasilkan metode LDA-fuzzykNN Lp Norm, yaitu 72% saat masing-masing nilai p dan k = 25. Metode gabungan ini terbukti cukup baik dari pada metode yang dijalankan terpisah. Kata kunci: melanoma, fuzzy, KNN, Lp-norm, LDA. As the advancement of technology skin cancer detection need to be automated with the use of dermoscopy image. Outlier and overfitting are the problem in feature extraction of dermoscopy image, this can be caused by skin type, uneven cancer distribution or sampling error. This study proposed melanoma skin cancer detection by fuzzy K-Nearest Neighbour (FuzzykNN) with Lp-norm integrated with Linear Discriminant Analysis (LDA) to reduce the problem of outlier and overfitting. Input used in this study are images with RGB channel, then it adapted to RGBr. Dimensional reduction with LDA result in features with highest eigen value. LDA in this research select 2 discriminant, they are tumor area and minimum tumor area in R channel. This features then classified by fuzzykNN with Lp-Norm. Integration of LDA and Lp-norm in classification can reduce the problem of overfitting. This study results in 72% accuracy when the value of p and k are 25. Integration of LDA and fuzzykNN with Lp-norm has better result than unintegrated method. Keywords: melanoma, fuzzy, KNN, Lp-norm, LDA.

Copyrights © 2016






Journal Info

Abbrev

register

Publisher

Subject

Computer Science & IT

Description

Register: Jurnal Ilmiah Teknologi Sistem Informasi published by the Department of Information Systems Unipdu Jombang. Register published twice a year, in January and July, Registerincludes research in the field of Information Technology, Information Systems Engineering, Intelligent Business Systems, ...