Application of Neural Network Variations for Determining the Best Architecture for Data Prediction

  • Mochamad Wahyudi Universitas Bina Sarana Informatika
  • Firmansyah Universitas Nusa Mandiri
  • Lise Pujiastuti STMIK Antara Bangsa
  • Solikhun STIKOM Tunas Bangsa
Keywords: Data Prediction, Backpropagation, Resilent Backpropagation, Conjugate Gradient,, Fletcher Reeves, Powell Beal

Abstract

This study focuses on the application and comparison of the epoch, time, performance/MSE training, and performance/MSE testing of variations of the Backpropagation algorithm. The main problem in this study is that the Backpropagation algorithm tends to be slow to reach convergence in obtaining optimum accuracy, requires extensive training data, and the optimization used is less efficient and has performance/MSE which can still be improved to produce better performance/MSE in this research—data prediction process. Determination of the best model for data prediction is seen from the performance/MSE test. This data prediction uses five variations of the Backpropagation algorithm: standard Backpropagation, Resistant Backpropagation, Conjugate Gradient, Fletcher Reeves, and Powell Beale. The research stage begins with processing the avocado production dataset in Indonesia by province from 2016 to 2021. The dataset is first normalized to a value between 0 to 1. The test in this study was carried out using Matlab 2011a. The dataset is divided into two, namely training data and test data. This research's benefit is producing the best model of the Backpropagation algorithm in predicting data with five methods in the Backpropagation algorithm. The test results show that the Resilient Backpropagation method is the best model with a test performance of 0.00543829, training epochs of 1000, training time of 12 seconds, and training performance of 0.00012667.

Downloads

Download data is not yet available.

References

R. Sistem and M. P. Matematika, “Implementasi Algoritma Backpropagation Prediksi Kegagalan Siswa Pada,” vol. 2, no. 3, pp. 753–759, 2018.

D. Monika, A. Ahmad, S. Wardani, and Solikhun, “Model Jaringan Syaraf Tiruan Dalam Memprediksi Ketersediaan Cabai Berdasarkan Provinsi,” Teknika, vol. 8, no. 1, pp. 17–24, 2019.

B. Yang, M. Pajak, D. Kabupaten, E. Rumapea, and M. R. Lubis, “Penerapan Jaringan Syaraf Tiruan Dalam Memprediksi Jumlah Kendaraan,” pp. 245–248, 2020.

R. Sistem, “Jurnal resti,” vol. 1, no. 10, pp. 1–2, 2021.

I. System, S. Dian, and C. Cendikai, “th,” no. December 2003, pp. 153–163.

C. Florescu and C. Igel, “R Esilient B Ackpropagation ( R Prop ) Learning In T Ensor F Low For B Atch -,” no. 1997, pp. 1–5, 2018.

M. Ayoub and M. Ayoub, “Application of Resilient Back- Propagation Neural Networks for Generating a Universal Pressure Drop Model in Pipe ...”

Y. Sari and U. L. Mangkurat, “Prediksi Harga Emas Menggunakan Metode Neural Network Backropagation Algoritma Conjugate Gradient,” no. January 2018, 2022.

S. S. S, S. Defit, and M. Ramadhan, “Analisis Optimasi Fungsi Pelatihan Machine Learning Neural Network dalam Peramalan,” vol. 7, no. 3, pp. 359–369, 2021.

S. Anam, T. Adriyanto, and M. K. Wuryansari, “Diagnosis Diabetes Mellitus Menggunakan Algoritma Jaringan Syaraf Tiruan Backpropagation dengan Metode Conjugate Gradient Fletcher-Reeves Adaptive Gain,” pp. 47–52, 2017.

S. R. Rusamsi, A. A. Rohmawati, F. Informatika, U. Telkom, and W. Haar, “Deteksi Kanker Berdasarkan Klasifikasi Microarray Data Menggunakan Wavelet Transform dan Backpropagation Termodifikasi dengan Conjugate Gradient Flechter,” vol. 5, no. 1, pp. 1772–1779, 2018.

S. Anam et al., “Predicting the Number of COVID-19 Sufferers in Malang City Using the Backpropagation Neural Network with the Fletcher – Reeves Method,” vol. 2021, 2021.

P. Anggara, “Perbandingan Model Jaringan Syaraf Tiruan Dengan Algoritma Levenberg-Marquadt Dan Powell-Beale Conjugate Gradient Pada Kecepatan Angin Rata-Rata Di Kota Semarang,” vol. 8, no. 2, 2020.

I. L. Sirait, J. M. Gultom, J. Tindaon, R. J. Tampubolon, and W. J. Mawaddah, “Peramalan tingkat produktivitas kedelai di indonesia menggunakan algoritma,” vol. 4, no. 2, pp. 183–192, 2018.

J. Nasional, S. Informasi, and A. Wanto, “Optimasi Prediksi Dengan Algoritma Backpropagation Dan Conjugate Gradient Beale-Powell Restarts,” vol. 03, no. 2017, pp. 370–380, 2018.

H. M. Mushgil, H. A. Alani, and L. E. George, “Comparison between Resilient and Standard Back Propagation Algorithms Efficiency in Pattern Recognition,” no. March 2015, pp. 4–10, 2019.

H. Y. Sari and A. Pendahuluan, “Optimasi Conjugate Gradient Pada Algoritma Backpropagation Neural Network Untuk Prediksi Kurs Time Series,” vol. 5, no. 1, pp. 86–90, 2016.

Riska Yanu Fa’arifah and Z. Busrah, “Backpropagation Neural Network untuk Optimasi Akurasi pada Prediksi Financial Distress Perusahaan,” J. Inf. Sains dan Teknol., vol. 2, no. April, pp. 101–110, 2017.

D. N. I. Muzakkir Irvan, Syukur Abdul, “Backpropagation Dengan Seleksi Fitur Particle Swarm Optimization Dalam Prediksi Pelanggan Telekomunikasi,” J. Pseudocode, vol. 1, no. 1 ISSN 2355 – 5920 PENINGKATAN, pp. 1–10, 2014.

https://www.bps.go.id/

Published
2022-10-08
How to Cite
Wahyudi, M., Firmansyah, Lise Pujiastuti, & Solikhun. (2022). Application of Neural Network Variations for Determining the Best Architecture for Data Prediction. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 6(5), 742 - 748. https://doi.org/10.29207/resti.v6i5.4356
Section
Artikel Rekayasa Sistem Informasi