Initial Optimal Parameters of Artificial Neural Network and Support Vector Regression

Abstract

This paper presents architecture of backpropagation Artificial Neural Network (ANN) and Support Vector Regression (SVR) models in supervised learning process for cement demand dataset. This study aims to identify the effectiveness of each parameter of mean square error (MSE) indicators for time series dataset. The study varies different random sample in each demand parameter in the network of ANN and support vector function as well. The variations of percent datasets from activation function, learning rate of sigmoid and purelin, hidden layer, neurons, and training function should be applied for ANN. Furthermore, SVR is varied in kernel function, lost function and insensitivity to obtain the best result from its simulation. The best results of this study for ANN activation function is Sigmoid. The amount of data input is 100% or 96 of data, 150 learning rates, one hidden layer, trinlm training function, 15 neurons and 3 total layers. The best results for SVR are six variables that run in optimal condition, kernel function is linear, loss function is ౬-insensitive, and insensitivity was 1. The better results for both methods are six variables. The contribution of this study is to obtain the optimal parameters for specific variables of ANN and SVR.

Optimalisasi Tempat Tidur Menggunakan Model Sistem Dinamik Di Rumah Sakit Zainal Abidin Kota Banda Aceh

“…Terdapat dua jenis simulasi yaitu diskrit dan kontinu. Salah satu pendekatan simulasi yang akhir-akhir ini banyak dipakai adalah dengan sistem dinamik (Fradinata,et al, 2018).…”

“…Pendiri sistem dinamik yaitu Jay Forrester pada tahun 1950-an mengkarakteristikkan sistem dinamik sebagai metodologi dalam penyelidikan, analisis, dan pemodelan suatu perilaku sistem yang kompleks secara menyeluruh, di mana loop umpan balik sangat penting dalam memahami hubungan timbal balik antara variabel-variabel (Moran, 2007). Pemodelan sistem dinamik memiliki tahapan yang diawali dan diakhiri dengan pemahaman sistem dan permasalahannya sehingga membentuk suatu lingkaran tertutup (Fradinata, Suthummanon, & Suntiamorntut, 2018). Tahapan dalam proses pemodelan sistem dinamik dapat dilihat pada Gambar 1.…”

Design of Fishing Smoke (saltization) Equipment and Its Process for Improving the Economy Community in Lampulo Banda Aceh

“…The market demand of these products tends to increase every month in the area of Banda Aceh and other sub-districts. The market demand can be predicted with some methods of forecasting to determine more accurate to the market products (Fradinata, Suthummanon, & Suntiamorntut, 2018).…”

Proposed study on evaluating and forecasting the resident property value based on specific determinants by case base reasoning and artificial neural network approach

“…There were numerous number of machine learning methods and approaches are applicable for property appraisal and valuation and it is reported in the literature"s. Researchers have designed intelligent systems for commercial property price predictions. Intelligent systems were designed using hybrid Multi-Layer Perceptron[MLP] ANN and rule-based system, which achieves an accuracy of 80% [13,14]. The study conducted by Guan et al [15] have explained on design and development of Adaptive Neuro-Fuzzy Inference System [ANFIS] approach which is useful to determine the residential property prices.…”