OPTIMASI JARINGAN SARAF TIRUAN UNTUK DIAGNOSIS PENYAKIT DIABETES INDIAN PIMA
DOI:
https://doi.org/10.26594/teknologi.v6i1.560Abstract
ABSTRAK
Untuk mengetahui kondisi seseorang menderita diabetes harus dengan melakukan beberapa tes pada labolatorium, US National Institute of Diabetes telah melakukan uji untuk penyakit Diabetes sesuai dengan kriteria Organisasi Kesehatan Dunia yang dilakukan pada sejumlah perempuan yang berusia 21 tahun, dari warisan Pima India dan tinggal di dekat Phoenix, Arizona sebanyak 768 objek. Jumlah data Diabetes Indian Pima yaitu sebanyak 768 data. Untuk percobaan ini, data tersebut dibagi menjadi dua yaitu 80% sebagai data training dan 20% sebagai data testing. Dengan menggunakan jaringan saraf tiruan Backpropagation, data tersebut dikembangkan untuk diagnosa penyakit Diabetes. Hal ini diharapkan dapat digunakan untuk memprediksi potensi seseorang terserang Diabetes. Klasifikasi jaringan saraf tiruan Backpropagation ini dioptimasi menggunakan metode Nguyen Widrow agar rule yang dihasilkan lebih signifikan atau rule yang dihasilkan dapat meningkatkan akurasi. Pengujian menggunakan data testing Diabetes dan inisialisasi Nguyen Widrow, maka dihasilkan tingkat akurasi sebesar 100%. Sedangkan jika menggunakan inisialisasi bobot random, maka dihasilkan tingkat akurasi sebesar 50%.
Kata Kunci: Backpropagation ,Diabetes, Jaringan Saraf Tiruan, Nguyen Widrow.
ABSTRACT
To determine the condition of a person suffering from diabetes need to do some tests in laboratories, the US National Institute of Diabetes has been test for Diabetes in accordance with the criteria of the World Health Organization conducted a number of women aged 21 years, from the legacy of Pima Indians and stay near Phoenix , Arizona as many as 768 objects. The amount of data Pima Indian Diabetes as many as 768 data. For this experiment, the data is divided into two: 80% as training data and 20% as a data testing. By using a neural network Backpropagation, the data developed for the diagnosis of Diabetes. It is expected-kan can be used to predict the potential of a person develops diabetes. Classification neural network Backpropagation is optimized using methods Nguyen Widrow that produced more significant rule or rule produced can improve accuracy. Diabetes testing using testing and initialization of data Nguyen Widrow, then the resulting accuracy rate of 100%. Whereas if you use random weight initialization, then produced a 50% accuracy rate.
Keywords: Backpropagation ,Diabetes, Neural Network, Nguyen Widrow
References
K. V. Narayan, J. P. Boyle, T. J. Thompson, S. W. Sorensen and D. F. Williamson, "Lifetime Risk for Diabetes Mellitus in the United States," JAMA, vol. 290, no. 14, pp. 1884-1890, 2003.
M. Kharola and D. Kumar, "Efficient Weather Prediction By Back-Propagation Algorithm," IOSR Journal of Computer Engineering (IOSR-JCE), vol. 16, no. 3, pp. 55-58, 2014.
A. M. Zamani, B. Amaliah dan A. Munif, “Implementasi Algoritma Genetika pada Struktur Backpropagation Neural Network untuk Klasifikasi Kanker Payudara,” JURNAL TEKNIK ITS , vol. 1, pp. A-222 - A-227, 2012.
M. P. M and D. W. Aha, UCI Repository of Machine Learning Databases (Machine Readable Data Depository), California: Department of Information and Computer Science. University of California. Irvine. CA., 1995.
W. C. Knowler, P. H. Bennett, R. F. Hamman And M. Miller, "Diabetes Incidence And Prevalence In Pima Indians: A 19-Fold Greater Incidence Than In Rochester, MINNESOTA," American Journal of Epidemiology, vol. 108, no. 6, pp. 497-505, 1978.
B. R. Valluru and V. R. Hayagriva, C++ Neural Networks And Fuzzy Logic, MIS, 1995.
A. Hermawan, Jaringan Saraf Tiruan Teori dan Aplikasi, Yogyakarta: Andi, 2006.
P. Diyah, Pengantar Jaringan Syaraf Tiruan, Yogyakarta: Andi, 2006.
Downloads
Published
Issue
Section
License
Please find the rights and licenses in Teknologi: Jurnal Ilmiah Sistem Informasi. By submitting the article/manuscript of the article, the author(s) agree with this policy. No specific document sign-off is required.
1. License
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
2. Author(s)' Warranties
The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).
3. User/Public Rights
Register's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, Register permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and Register on distributing works in the journal and other media of publications. Unless otherwise stated, the authors are public entities as soon as their articles got published.
4. Rights of Authors
Authors retain all their rights to the published works, such as (but not limited to) the following rights;
Copyright and other proprietary rights relating to the article, such as patent rights,
The right to use the substance of the article in own future works, including lectures and books,
The right to reproduce the article for own purposes,
The right to self-archive the article (please read out deposit policy),
The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (Register: Jurnal Ilmiah Teknologi Sistem Informasi).
5. Co-Authorship
If the article was jointly prepared by more than one author, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. Register will not be held liable for anything that may arise due to the author(s) internal dispute. Register will only communicate with the corresponding author.
6. Royalties
Being an open accessed journal and disseminating articles for free under the Creative Commons license term mentioned, author(s) aware that Register entitles the author(s) to no royalties or other fees.
7. Miscellaneous
Register will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. Register's editors may modify the article to a style of punctuation, spelling, capitalization, referencing and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.