Analisis Penurunan Gradien dengan Kombinasi Fungsi Aktivasi pada Algoritma JST untuk Pencarian Akurasi Terbaik

 (*)Anjar Wanto Mail (STIKOM Tunas Bangsa, Pematangsiantar, Indonesia)
 Jufriadif Na`am (Universitas Putera Indonesia "YPTK" Padang, Padang, Indonesia)
 Yuhandri Yuhandri (Universitas Putera Indonesia "YPTK" Padang, Padang, Indonesia)
 Agus Perdana Windarto (STIKOM Tunas Bangsa, Pematangsiantar, Indonesia)
 Mesran Mesran (STMIK Budi Darma, Indonesia)

(*) Corresponding Author

Submitted: September 25, 2020; Published: October 20, 2020

DOI: http://dx.doi.org/10.30865/mib.v4i4.2509

Abstract

There are many training function methods for gradient descent (gradient descent) and activation functions (transfer functions) that can be used in the ANN algorithm, especially the backpropagation algorithm. Therefore the aim of this paper is to analyze the best gradient descent that can be used as a reference for use in the ANN algorithm, especially the backpropagation algorithm in data prediction, classification and pattern management problems. The gradient descent methods to be analyzed include; Gradient descent backpropagation (traingd), Gradient descent with momentum backpropagation (traingdm), Gradient descent with adaptive learning rate backpropagation (traingda), and Gradient descent with momentum and adaptive learning rate backpropagation (traingdx). The training function will be combined with the activation function (transfer function) of bipolar sigmoid (tansig), linear transfer (purelin) and binary sigmoid (logsig). The sample data used for the analysis process is the time-series data for the Human Development Index in Indonesia, which is obtained from the Central Bureau of Statistics (BPS). Architectural models used for gradient descent analysis include: 6-10-15-1, 6-15-20-1, 6-20-25-1 and 6-25-30-1. Based on the analysis results, the best training function is traingda with an architectural model of 6-15-20-1 which produces an accuracy rate of 91% and MSE testing is 0.000731529 (smaller than other methods)

Keywords


Gradient Descent, Activation Functions, ANN, Backpropagation, Accuracy

Full Text:

PDF


Article Metrics

Abstract View: 74 times | PDF View: 14 times

References

J. J. Siang, Jaringan Syaraf Tiruan dan Pemrogramannya Menggunakan Matlab. Penerbit Andi Yogyakarta, 2005.

M. Megawati and R. M. Candra, “Diagnosa Hama Dan Penyakit Pada Tanaman Jeruk Dengan Menerapkan Jaringan Syaraf Tiruan Learning Vector Quantization,” Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi, vol. 3, no. 2, pp. 59–62, 2018.

Y. Ayyappa and A. Krishna, “Enhanced and Effective Computerized Multi Layered Perceptron based Back Propagation Brain Tumor Detection with Gaussian Filtering,” in Proceedings of the Second International Conference on Inventive Research in Computing Applications (ICIRCA-2020). IEEE Xplore Part Number: CFP20N67-ART; ISBN: 978-1-7281-5374-2, 2020, pp. 58–62.

B. T. Pham, M. D. Nguyen, K. T. T. Bui, I. Prakash, K. Chapi, and D. T. Bui, “A novel artificial intelligence approach based on Multi-layer Perceptron Neural Network and Biogeography-based Optimization for predicting coefficient of consolidation of soil,” Catena, vol. 173, no. September 2018, pp. 302–311, 2019.

A. Wanto, “Prediksi Produktivitas Jagung Di Indonesia Sebagai Upaya Antisipasi Impor Menggunakan Jaringan Saraf Tiruan Backpropagation,” SINTECH (Science and Information Technology) Journal, vol. 2, no. 1, pp. 53–62, 2019.

A. Wanto, “Optimasi Prediksi Dengan Algoritma Backpropagation Dan Conjugate Gradient Beale-Powell Restarts,” Jurnal Teknologi dan Sistem Informasi, vol. 3, no. 3, pp. 370–380, Jan. 2017.

A. P. Windarto et al., Jaringan Saraf Tiruan: Algoritma Prediksi dan Implementasi. Yayasan Kita Menulis, 2020.

V. Ranganathan and S. Natarajan, “A New Backpropagation Algorithm without Gradient Descent,” pp. 1–15, 2018.

F. A. Ruslan, A. M. Samad, and R. Adnan, “4 Hours NNARX flood prediction model using ‘traingd’ and ‘trainoss’ training function: A comparative study,” Proceedings - 2018 IEEE 14th International Colloquium on Signal Processing and its Application, CSPA 2018, no. March, pp. 77–81, 2018.

M. Haryati and O. W. Arsani, “JurnalRiset Teknologi dan InovasiPendidikan Analisis Tingkat Akurasi Model Backpropagation Dalam Prediksi Indeks Pembangunan Manusia ( IPM ) di NTB Pendahuluan Peramalan ( Forecasting ) adalah kegiatan mengestimasi apa yang semakin berkembang dengan meman,” (JARTIKA) Jurnal Riset Teknologi dan Inovasi Pendidikan, vol. 2, no. 2, pp. 94–102, 2019.

A. Pamungkas, R. Zulkarnain, K. Adiyana, Waryanto, H. Nugroho, and A. S. Saragih, “Application of Artificial Neural Networks to forecast Litopenaeus vannamei and Penaeus monodon harvests in Indramayu Regency, Indonesia,” IOP Conference Series: Earth and Environmental Science, vol. 521, no. 1, pp. 1–9, 2020.

BPS, “[Metode Baru] Indeks Pembangunan Manusia menurut Provinsi,” 2020. [Online]. Available: https://www.bps.go.id/indicator/26/494/1/-metode-baru-indeks-pembangunan-manusia-menurut-provinsi.html. [Accessed: 20-Sep-2020].

S. Setti and A. Wanto, “Analysis of Backpropagation Algorithm in Predicting the Most Number of Internet Users in the World,” JOIN (Jurnal Online Informatika), vol. 3, no. 2, pp. 110–115, 2018.

T. Afriliansyah and Z. Zulfahmi, “Prediction of Life Expectancy in Aceh Province by District City Using the Cyclical Order Algorithm,” International Journal of Information System & Technology, vol. 3, no. 2, pp. 268–275, 2020.

T. Afriliansyah et al., “Implementation of Bayesian Regulation Algorithm for Estimation of Production Index Level Micro and Small Industry,” Journal of Physics: Conference Series, vol. 1255, no. 1, pp. 1–6, 2019.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Analisis Penurunan Gradien dengan Kombinasi Fungsi Aktivasi pada Algoritma JST untuk Pencarian Akurasi Terbaik

Refbacks

  • There are currently no refbacks.


Copyright (c) 2020 JURNAL MEDIA INFORMATIKA BUDIDARMA

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.



JURNAL MEDIA INFORMATIKA BUDIDARMA
STMIK Budi Darma
Sekretariat : Jln. Sisingamangaraja No. 338 Telp 061-7875998
email : mib.stmikbd@gmail.com

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.