PENERAPAN ALGORITMA BAYESIAN REGULARIZATION BACKPROPAGATION UNTUK MEMPREDIKSI PENYAKIT DIABETES
(1) Universitas Bina Nusantara
(2) Politeknik Negeri Jakarta
Abstract
Pada tahun 2015, penderita diabetes di Indonesia sebanyak 10 juta jiwa. Banyaknya penderita diabetes ini semakin bertambah dari tahun ke tahun. Berdasarkan data International Diabetes Federation, diperkirakan pada tahun 2040 banyaknya penduduk Indonesia yang terkena penyakit diabates akan meningkat menjadi 16.2 juta jiwa penduduk. Upaya pendeteksian sejak dini penyakit diabetes perlu dilakukan. Hal ini untuk mengurangi komplikasi penyakit pada penderita pada masa yang akan datang. Neural network merupakan salah satu metode klasifikasi yang dapat digunakan untuk memprediksi penyakit diabetes. Penelitian ini bertujuan membuat sistem prediksi penyakit diabetes. Kinerja diagnostik sistem Jaringan syaraf tiruan dievaluasi menggunakan analisis Receiver Operating Characteristic (ROC) untuk mengetahui tingkat accuracy, sensitivity, dan specificity. Hasil evaluasi menunjukkan klasifikasi menggunakan sistem jaringan syaraf tiruan backpropagation masuk ke dalam kriteria good classification. Artinya, hasil klasifikasi ini dapat digunakan untuk membuat sistem prediksi penyakit diabates.
As 2015, an estimated 10 million people had diabetes in Indonesia. Trends suggested the rate would continue to rise year by year. According to the latest International Diabetes Federation, people living with diabetes is expected to rise to 16.2 million by 2040. Early detection of diabetes is needed to reduce number of people living with diabetes. Neural network classification is one method that can be used to predict diabetes. This research aims to make diabetes disease prediction systems. Artificial neural network diagnostic system performance was evaluated using analysis of Receiver Operating Characteristic (ROC) to determine the level of accuracy, sensitivity, and specificity. The results of the evaluation showed that the classification system using backpropagation neural network is good. The results of the classification is used to make diabetes disease prediction systems.
Keywords
Full Text:
PDFReferences
Abdillah, Abdul A. & Suwarno. 2016. Diagnosis of Diabetes Using Support Vector Machines with Radial Basis Function Kernels. International Journal of Technology (2016) 5: 849-858.
Ayodele A., Adebiyi, Charles K., Ayo, Marion O., Adebiyi, & Sunday O., Otokiti. 2012. Stock Price Prediction using Neural Network with Hybridized Market Indicators. Journal of Emerging Trends in Computing and Information Sciences Vol.3, No.1, January 2012.
Gorunescu, F. 2011. Data mining: concepts and techniques. German: Springer. http://doi.org/10.1007/978-3-642-19721-5
International Diabetes Federation. 2015. IDF Diabetes Atlas (Seventh Edit). United Kingdom: IDF Press.
Pan X, Lee B, Zhang C. 2013. A comparison of neural network backpropagation algorithm for electricity load forecasting. Intelligent Energy System (IWIES). IEEE International Workshop on, vol., no., pp 22, 27, 14-14 Nov. 2013.
Sapon, Muhammad A., Ismail, Khadijah, & Zainudin, Suehazlyn. 2011. Prediction of Diabetes by using Artificial Neural Network. International Conference on Circuit, System and Simulation IPCSIT vol.7 (2011) IACSIT Press, Singapore.
Soares, FM & Souza, AMF. 2016. Neural network programming with Java : unleash the power of neural networks by implementing professional Java code (First Edit). United Kingdom: Packt.
World Health Organization. 1999. Definition, Diagnosis and Classification of Diabetes Mellitus and its Complication. Geneva: WHO Press.
Yue Z, Songzheng Z & Tianshi T. 2011. Bayesian regularization BP Neural Network model for predicting oil-gas drilling cost. Bussiness Management and Electronic Information (BMEI), International Conference on, vol. 2, no., pp. 483, 487, 13-15 May 2011.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 4.0 International License.