Comparative Analysis of Gradient Descent Learning Algorithms in Artificial Neural Networks for Forecasting Indonesian Rice Prices
Abstract
Artificial Neural Networks (ANN) are a field of computer science that mimics the way the human brain processes data. ANNs can be used to classify, estimate, predict, or simulate new data from similar sources. The commonly used algorithm for prediction in ANN is Backpropagation, which yields high accuracy but tends to be slow during the training process and is prone to local minima. To address these issues, appropriate parameters are needed in the Backpropagation training process, such as an optimal learning function. The aim of this study is to evaluate and compare various learning functions within the Backpropagation algorithm to determine the best one for prediction cases. The learning functions evaluated include Gradient Descent Backpropagation (traingd), Gradient Descent with Adaptive Learning Rate (traingda), and Gradient Descent with Momentum and Adaptive Learning Rate (traingdx). The dataset used is the average wholesale rice price in Indonesia, obtained from the Central Statistics Agency (BPS) website. The evaluation results show that the traingdx learning function with a 5-5-1 architecture model achieves the highest accuracy of 83.33%, representing an 8.3% improvement over the traingd and traingda learning functions, which both achieved a maximum accuracy of 75%. Based on this study, it can be concluded that using various learning functions in Backpropagation yields better accuracy compared to standard Backpropagation.
Downloads
References
M. Yanto, L. Mayola, and M. Hafizh, “Neural Network Backprogation Identifikasi Pola Harga Saham Jakarta Islamic Index (JII),” J. RESTI (Rekayasa Sist. Dan Teknol. Informasi), vol. 4, no. 1, pp. 90–94, 2020, doi: https://doi.org/10.29207/resti.v4i1.1266.
A. A. Mahmudi, “Optimasi Conjugate Gradient Pada Backpropagation Neural Network Untuk Prediksi Hasil Tangkap Ikan,” Saintekbu, vol. 12, no. 2, pp. 29–39, 2020, doi: 10.32764/saintekbu.v12i2.1031.
R. N. Singarimbun, O. E. Putra, N. L. W. S. R. Ginantra, and M. P. Dewi, “Backpropagation Artificial Neural Network Enhancement using Beale-Powell Approach Technique,” J. Phys. Conf. Ser., vol. 2394, no. 1, 2022, doi: 10.1088/1742-6596/2394/1/012007.
S. Bhardwaj, A. Tarafdar, M. Baghel, T. Dutt, and G. K. Gaur, “Determining Point of Economic Cattle Milk Production through Machine Learning and Evolutionary Algorithm for Enhancing Food Security,” J. Food Qual., vol. 2023, 2023, doi: 10.1155/2023/7568139.
H. Mustafidah and I. F. Syarifah, “Tingkat Eror Jaringan Backpropagation pada Model Neuron 15-26-1 dan 15-29-1,” in Seminar Nasional CORISINDO, 2022, pp. 481–485. [Online]. Available: https://corisindo.stikom-bali.ac.id/penelitian/index.php/semnas/article/view/99
R. Maiyuriska, “Penerapan Jaringan Syaraf Tiruan dengan Algoritma Backpropagation dalam Memprediksi Hasil Panen Gabah Padi,” J. Inform. Ekon. Bisnis, vol. 4, no. 1, pp. 28–33, 2022, doi: 10.37034/infeb.v4i1.115.
A. Wanto, J. Na’am, Yuhandri, A. P. Windarto, and Mesran, “Analisis Penurunan Gradien dengan Kombinasi Fungsi Aktivasi pada Algoritma JST untuk Pencarian Akurasi Terbaik,” J. Media Inform. Budidarma, vol. 4, no. 4, pp. 1197–1205, 2020, doi: 10.30865/mib.v4i4.2509.
Putrama Alkhairi and A. P. Windarto, “Classification Analysis of Back propagation-Optimized CNN Performance in Image Processing,” J. Syst. Eng. Inf. Technol., vol. 2, no. 1, pp. 8–15, 2023, doi: 10.29207/joseit.v2i1.5015.
F. Damayanti and R. Rismayanti, “Optimasi Fungsi Pembelajaran Backpropagation dalam Mengklasifikasikan Pasien Kanker Paru Pasca Operasi,” J. Unitek, vol. 15, no. 1, pp. 49–58, 2022, doi: 10.52072/unitek.v15i1.335.
I. I. Ridho, A. A. G. B. Ariana, and A. P. Windarto, “Optimasi Fungsi Pembelajaran Jaringan Saraf Tiruan dalam Meningkatkan Akurasi pada Prediksi Ekspor Kopi Menurut Negara Tujuan Utama,” Build. Informatics, Technol. Sci., vol. 4, no. 4, 2023, doi: 10.47065/bits.v4i4.3240.
S. H. Haji and A. M. Abdulazeez, “Comparison Of Optimization Techniques Based on Gradient Descent Algorithm: A Review,” J. Archaeol. Egypt/Egyptology, vol. 18, no. 4, pp. 2715–2743, 2021.
Dwira Azi Pragana, D. W. Manurung, and Agus Perdana Windarto, “Analisa Metode Backpropagation Pada Prediksi Rata-rata Harga Beras Bulanan Di Tingkat Penggilingan Menurut Kualitas,” J. Comput. Informatics Res., vol. 2, no. 3, pp. 77–84, 2023, doi: 10.47065/comforch.v2i3.855.
Rika Setiana, Razalfa Aindi Siregar, Fahry Husaini, and Agus Perdana Windarto, “Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing di Indonesia,” J. Informatics, Electr. Electron. Eng., vol. 2, no. 4, pp. 113–123, 2023, doi: 10.47065/jieee.v2i4.1177.
Natasya, S. Musdalifah, and Andri, “Prediksi Harga Beras Di Tingkat Perdagangan Besar Indonesia Menggunakan Algoritma Backpropagation,” J. Ilm. Mat. Dan Terap., vol. 18, no. 2, pp. 148–159, 2021, doi: 10.22487/2540766x.2021.v18.i2.15688.
D. W. Kim, M. S. Kim, J. Lee, and P. Park, “Adaptive learning-rate backpropagation neural network algorithm based on the minimization of mean-square deviation for impulsive noises,” IEEE Access, vol. 8, pp. 98018–98026, 2020, doi: 10.1109/ACCESS.2020.2997010.
M. Thoriq, “Peramalan Jumlah Permintaan Produksi Menggunakan Jaringan Saraf Tiruan Algoritma Backpropagation,” J. Inf. dan Teknol., vol. 4, no. 1, pp. 27–32, 2022, doi: 10.37034/jidt.v4i1.178.
Mesran, S. R. Yahya, F. Nugroho, and A. P. Windarto, “Investigating the Impact of ReLU and Sigmoid Activation Functions on Animal Classification Using CNN Models,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 8, no. 1, pp. 111–118, 2024, doi: https://doi.org/10.29207/resti.v8i1.5367.
N. M. Nawi, F. Hamzah, N. A. Hamid, M. Z. Rehman, M. Aamir, and A. A. Ramli, “An optimized back propagation learning algorithm with adaptive learning rate,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 7, no. 5, pp. 1693–1700, 2017, doi: 10.18517/ijaseit.7.5.2972.
A. R. Bohari, “Meningkatkan Kinerja Backpropagation Neural Network Menggunakan Algoritma Adaptif,” IMTechno J. Ind. Manag. Technol., vol. 3, no. 1, pp. 58–63, 2022, doi: 10.31294/imtechno.v3i1.1043.
M. Dasuki, “Optimasi Nilai Bobot Algoritma Backpropagation Neural Network Dengan Algoritma Genetika,” JUSTINDO (Jurnal Sist. dan Teknol. Inf. Indones., vol. 6, no. 1, pp. 38–44, 2021, doi: 10.32528/justindo.v6i1.5280.
W. Saputra, A. P. Windarto, and A. Wanto, “Analysis of the Resilient Method in Training and Accuracy in the Backpropagation Method,” IJICS (International J. Informatics Comput. Sci., vol. 5, no. 1, p. 52, 2021, doi: 10.30865/ijics.v5i1.2922.
A. Wanto et al., “Analysis Of Standard Gradient Descent With GD Momentum And Adaptive LR For SPR Prediction,” Int. Conf. Comput. Environ. Agric. Soc. Sci. Heal. Sci. Eng. Technol., no. 1, pp. 1–9, 2018.
J. Jepkoech, D. M. Mugo, B. K. Kenduiywo, and E. C. Too, “The Effect of Adaptive Learning Rate on the Accuracy of Neural Networks,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 8, pp. 736–751, 2021, doi: 10.14569/IJACSA.2021.0120885.
S. Syaharuddin, F. Fatmawati, and H. Suprajitno, “Best Architecture Recommendations of ANN Backpropagation Based on Combination of Learning Rate, Momentum, and Number of Hidden Layers,” JTAM (Jurnal Teor. dan Apl. Mat., vol. 6, no. 3, p. 629, 2022, doi: 10.31764/jtam.v6i3.8524.
Badan Pusat Statistik, “Rata-Rata Harga Beras di Tingkat Perdagangan Besar (Grosir) Indonesia,” 2024. https://www.bps.go.id/id/statistics-table/2/Mjk1IzI=/rata-rata-harga-beras-di-tingkat-perdagangan-besar--grosir--indonesia.html (accessed Mar. 10, 2024).
Copyright (c) 2024 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
