Analisis Perbandingan Reduksi Dimensi Principal Component Analysis (pca) Dan Partial Least Square (pls) Untuk Deteksi Kanker Menggunakan Data Microarray
DOI:
https://doi.org/10.34818/eoe.v6i2.9828Abstract
Abstrak Menurut data WHO (World Health Organization) pada tahun 2015, 8.8 juta kematian diakibatkan oleh kanker dimana angka kematian tersebut meningkat dan berkakibat fatal setiap tahunnya bila diagnosa tidak dilakukan lebih dini. Oleh karena itu , tidak heran penelitian dalam bidang kanker menjadi topik utama dalam penelitian di bidang medis dan bioinformatika dan terus berkembang hingga saat ini, termasuk teknologi DNA microarray. Banyak cara untuk mendeteksi kanker, salah satunya adalah teknik microarray. Microarray adalah teknologi yang mampu menyimpan ribuan ekspresi gen yang diambil dari beberapa jaringan manusia sekaligus. Dikarenakan oleh record data microarray yang banyak, komputasi yang dibutuhkan cukup berat. Untuk mengatasi masalah tersebut, dibutuhkan reduksi dimensi. Pada penelitian ini, sistem menggunakan dua ï¬tur ekstrasi: Principal Component Analysis (PCA) dan Partial Least Square (PLS) dengan Support Vector Machine (SVM) sebagai classiï¬er. Hal ini berguna untuk mengurangi attribute yang terlalu banyak. Sistem yang dibangun mampu mengklasiï¬kasi kanker dan memperoleh nilai rata-rata 82% dengan PCA-SVM dan 55.17% untuk PLS-SVM. Kata kunci : kanker, microarray, principal component analysis, partial least square, support vector machine. Abstract According to WHO data in 2015 (World Health Organization), 8.8 million deaths were caused by cancer where the mortality rate increased and was fatal every year if the diagnosis was not made earlier. Therefore, it is not surprising that research in the ï¬eld of cancer has become a major topic in research in the medical and bioinformatics ï¬elds and continues to grow to date, including DNA microarray technology. There are many ways to detect cancer, one of which is the microarray technique. Microarray is a technology that can store thousands of gene expressions taken from several human tissues at once. Due to a large number of microarray data records, the computing required is quite heavy. To overcome this problem, dimension reduction is needed. In this study, the system uses two extraction features: Principal Component Analysis (PCA) and Partial Least Square (PLS) with Support Vector Machine (SVM) as a classiï¬er. This is useful to reduce the large amount of attributes. The accuracy generated from this system averaged 82% with PCA-SVM and 55.17% for PLS-SVM. Keywords: cancer, microarray, principal component analysis, partial least square, support vector machine.
Downloads
References
H. Abdi. Partial Least Square Regression. Encyclopedia of Measurement and Statistic, 2007.
Adiwijaya. Aplikasi Matriks dan Ruang Vektor. Graha Ilmu, 2014.
Adiwijaya. Matematika Diskrit Dan Aplikasinya. alfabeta, 2016.
Adiwijaya. Deteksi kanker berdasarkan klasifikasi microarray data. JURNAL MEDIA INFORMATIKA BUDIDARMA, 2(4):181–186, 2018.
Adiwijaya, U. N. Wisesty, E. Lisnawati, A. Aditsania, and D. S. Kusumo. Dimensionality reduction using principal component analysis for cancer detection based on microarray data classification. Journal of Computer Science, 14(11):1521–1530, Nov. 2018.
H. A. Adiwijaya. A clustering approach for feature selection in microarray data classification using random forest. Journal of Information Processing System, pages 1167–1175, 2018.
A. A. Adiyasa, N; Adiwijaya; Suryani. Cancer Detection Based On Microarray Data Classification Using PCA and Modified Backpropagation. Far East Journal of Electronics and Communications, pages 269–281, 2015.
W. Astuti and Adiwijaya. Principal component analysis sebagai ekstraksi fitur data microarray untuk deteksi kanker berbasis linear discriminant analysis. Media Informatika Budidarma, 2(4):181–186, 2018.
F. Bray, J. Ferlay, I. Soerjomataram, R. L. Siegel, L. A. Torre, and A. Jemal. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 68(6):394–424, Sept. 2018.
C. Campbell. Support Vector Machine and Kernel Methods. 2005.
L. R. D. Dai, J. J.; Lieu. Dimension reduction for classification with gene expression microarray data. Statistical Application in Genetics Molecular Biology, 2006.
P. D. dan Informasi. Stop Kanker. Kementrian Kesehatan RI, 2015.
S. Deegalla and H. Bostr¨om. Classification of microarrays with kNN: Comparison of dimensionality reduction methods. In Intelligent Data Engineering and Automated Learning - IDEAL 2007, pages 800–809. Springer Berlin Heidelberg, 2007.
A. F. B. Firmansyah and S. Pramana. Ensemble based gustafson kessel fuzzy clustering.
I. Guyon and A. Elisseeff. An introduction to variable and feature selection. Journal of machine learning research, 3(Mar):1157–1182, 2003.
S. R. S. K. Kumar, Mukesh; Singh. Classification of Microarray data using Functional Link Neural Network. Procedia Computer Science, pages 727–737, 2015.
G.-Z. Li, X.-Q. Zeng, J. Y. Yang, and M. Q. Yang. Partial least squares based dimension reduction with gene selection for tumor classification. In 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering. IEEE, Oct. 2007.
J. Li. Kent-ridge bio-medical data set repository, School of Computer Engineering Nanyang Technological University, Singapore, 2013.
H. S. B. Lu, Henry Horng-Shing; Zhao. Handbook of Statistical Bioinformatics. Springer, 2011.
A. Manik, D. Q. Utama, et al. Classification of electrocardiogram signals using principal component analysis and levenberg marquardt backpropagation for detection ventricular tachyarrhythmia. Journal of Data Science and Its Applications, 2(1):78–87, 2019.
K. S. Ng. A simple explanation of partial least squares. 2013.
F. Nurfalah, A.; Umbara. Colorectal cancer classification using pca and fisherface feature extraction data from pathology microscopic image. ISICO, 2013.
R. Nurhasanah; Subianto, M; Fitriani. Perbandingan Metode Partial Least Square (pls) dengan Regresi Komponen Utama untuk mengatasi Multikolinearitas. STATISTIKA: Forum Teori dan Aplikasi Statistika, pages 33–42, 2012.
R. Pujianto, A. Adiwijaya, and A. A. Rohmawati. Analisis ekstraksi fitur principle component analysis pada klasifikasi microarray data menggunakan classification and regression trees. eProceedings of Engineering, 6(1), 2019.
P. Stafford. Methods in microarray normalization. CRC Press, 2008.
WHO. Cancer Facts and Tableures. American Cancer Society, 2015.



