DIAGNOSIS KANKER PAYUDARA MENGGUNAKAN NEURAL NETWORK BERBASIS ALGORITMA GENETIKA

Evy Priyanti - AMIK BSI Jakarta

Abstract


Abstract - Breast cancer is one type of cancer that continues to increase every year, especially in developing countries. Breast cancer there are two classes of benign and malignant cancer. Class cancer can be predicted by using a genetic algorithm-based neural network. Very high accuracy rate if breast cancer dataset is tested with algorithm of genetic algorithm based on genetic algorithm that is accurate equal to 96.85% compared with only neural network which get accurate value 95.42%, because neuron which has been chosen by neural network algorithm will next be done The process of chromosomal selection. These chromosomes will evolve in a sustainable manner called a generation. In each generation the chromosomes evaluated the success rate of the solution to the problem to be solved using a measure of fitness. To select a chromosome that is maintained for the next generation is a process called selection. The process of chromosome selection using Darwin's previously mentioned concept of Darwinian rule of thumb is that chromosomes with high fitness values will have a greater chance of being selected again in the next generation.

 

Keyword: Neural Network, Genetic Algorithm, Breast Cancer

 

Abstrak - Kanker payudara merupakan salah satu jenis kanker yang terus meningkat setiap tahunnya, terutama di negara berkembang. Kanker payudara ada dua golongan kanker jinak dan ganas. Kanker kelas dapat diprediksi dengan menggunakan jaringan syaraf berbasis algoritma genetika. Tingkat akurasi yang sangat tinggi jika dataset kanker payudara diuji dengan algoritma algoritma genetika berdasarkan algoritma genetika yang akurat sebesar 96,85% dibandingkan dengan hanya jaringan syaraf tiruan yang mendapat nilai akurat 95,42%, karena neuron yang telah dipilih oleh algoritma jaringan syaraf tiruan selanjutnya Proses seleksi kromosom dilakukan. Kromosom ini akan berkembang secara berkelanjutan yang disebut generasi. Pada setiap generasi, kromosom mengevaluasi tingkat keberhasilan pemecahan masalah yang harus diselesaikan dengan menggunakan ukuran kebugaran. Untuk memilih kromosom yang dipertahankan untuk generasi berikutnya adalah proses yang disebut seleksi. Proses pemilihan kromosom dengan menggunakan konsep Darwin yang sebelumnya telah disebutkan sebelumnya adalah bahwa kromosom dengan nilai fitness tinggi akan memiliki kesempatan lebih besar untuk dipilih lagi pada generasi berikutnya.

 

Kata Kunci: Neural Network, Algoritma Genetika, Kanker Payudara


Full Text:

PDF

References


Alpaydin, Ethem. (2010). Introduction to Machine Learning. London: The MIT Press.

Bramer, Max. (2007). Principles of Data Mining. London: Springer.

Fadli, Ari.Konsep Data Minning. Lisensi Dokumen : Copyright: 2003-2011 Ilmu Komputer.com

Gorunescu, F.(2011). Data Mining Concepts, Models and Techniques. Berlin Heidelberg: Springer Verlag.

Handayani, Sri & Sudarmiati, Sari. (2012). Pengetahuan Remaja Putri tentang Cara Melakukan

Han,J&Kamber (2007), “Data Mining Concepts, Models and Techniques ”, Second Edition, Morgan Kaufmann Publisher, Elsevier.

Haupt,R.L&Haupt (2004), “Practical Genetic Algorithm”, John Wiley&Sons.Inc, New Jersey.

http://www.depkes.go.id/index.php/berita/press-release/1060-jika-tidak-dikendalikan-26-juta-orang-di-dunia-menderita-kanker-.html

Sadari. Jurnal Nursing Studies, Volume 1, Nomor 1 Tahun 2012.

Han, J., & Kember, M. (2006). Data Mining Concepts and Techniques. San Fransisco: Morgan Kauffman.

Haykin, S. (1999). Neural networks a comprehensive foundation, Second Edition, Upper Saddle River, N.J.:Prentice-Hall International, Inc.

Kusrini, & Luthfi, E. T. (2009). Algoritma Data Mining. Yogyakarta: Andi Publishing.

Larose, D.T. (2005). Discovering Knowledge in Data. New Jersey : John Willey & Sons, Inc.

Liao. (2007). Recent Advances in Data Mining of Enterprise Data: Algorithms and Application. Singapore: World Scientific Publishing.

Maimon, Oded&Rokach, Lior (2010). Data Mining and Knowledge Discovey Handbook. New York:Springer.

Pusdatin. (2015). Situasi Penyakit Kanker. http://www.depkes.go.id/resources/download/pusdatin/infodatin/infodatin-kanker.pdf.

Rani, U.K. (2010). Parallel Approach for Diagnosis of Breast Cancer Using Neural Network Technique. International Journal of Computer Applications (0975-8887) Volume 10 No. 3, November 2010.

Ritthipravat, P. (2009). Artificial Neural Networks in Cancer Recurrence Prediction. International Conference on Computer Engineering and Technology.

Sugiyono. (2009). Metode Penelitian Kuantitatif Kualitatif Dan R & D. Bandung:ALFABETA. ISBN:979-8433-64-0

Shukla (2010), “Real Life Application of soft computing”, Taylor and Francis Group, LLC.

Vercellis, C. (2009). Business Intelligent: Data Mining and Optimizzation for Decision Making. Southern Gate, Chichester, West Sussex, United Kingdom : John Wiley & Sons Ltd.

Witten, I. H., Frank, E., & Hall, M. A. (2011). Data Mining : Practical Machine Learning and Tools. Burlington: Morgan Kaufmann Publisher.

Wu, X., & Kumar, V. (2009). The Top Ten Algorithms in Data Mining. Boca Raton, London, New York : Taylor & Francis Group, LLC.

Zukri, Zainudin (2014), “AlgoritmaGenetika, Metode komputasi evolusioner untuk menyelesaikan masalah optimasi”,PenerbitAndi,Yogyakarta




DOI: https://doi.org/10.31294/evolusi.v5i2.2596

Published By LPPM Universitas Bina Sarana Informatika

Kampus Kabupaten Banyumas

Jalan HR. Bunyamin 106, Pabuaran, Kec. Purwokerto Utara,
Kabupaten Banyumas, Jawa Tengah 53124, Telp. (0281) 642848
Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License