Near Optimal Convergence of Back-Propagation Method using Harmony Search Algorithm

Nur, Abdirashid Salad; Radzi, Nor Haizan Mohd; Shamsuddin, Siti Mariyam

doi:10.11591/telkomnika.v14i1.7233

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of BP is to find the optimal weight and bias to get the smallest error or Mean Square Error (MSE). Apart from using BP for training, it is not necessary to determine the exact initial design of the neural network architecture and parameters (Nur et al, 2015). The following equation is used to set the weights using the BP algorithm:…”

Section: Backpropagationmentioning

confidence: 99%

Optimization of Backpropagation Using Harmony Search for Gold Price Forecasting

Kurniawati

Muhajir

2022

Pak.j.stat.oper.res.

View full text Add to dashboard Cite

Gold is a precious metal often used for investment, due to its cash-in ease and yearly value increase. This indicates that price forecasting is used to determine the prospect of future gold prices. Strong gold price forecasting is highly desired by investors to make decisions. That is why technical indicators are very important used for forecasting. By using technical indicators the information obtained can be more informative than using pure gold prices. One of the commonly used methods is Backpropagation (BP). BP has been shown to have good performance in dealing with nonlinear problems. However, due to the random determination of the parameters of neurons in the hidden layer BP requires a number of neurons in the hidden layer to get optimal results. Therefore, this study aims to analyze the optimization of Backpropagation (BP) through the Harmony Search (HS) algorithm by evaluating the use of relevant technical indicators for forecasting gold prices. In the HS-BP model, this method is used to determine input variables and neurons in the hidden layer. HS with the principle of musicians with the aim of finding the best harmony. This technique is used based on the results of the fitness function. In this research, the fitness function used is Mean Square Error (MSE). HS aims to optimize BP in such a way that the forecasting system provides the lowest MSE and improves the forecasting performance of gold prices. Based on this research, the input variables used are Moving Average, Relative Strength Index, and Bollinger Bands. Next, the selected variables and neurons are applied to the BP algorithm. Where the implementation uses gold closing price data for January 2020-2021. The results showed that the proposed method has better results in forecasting accuracy and convergence error. HS-BP provides a better level of gold price forecasting than the regular BP model.

show abstract

Section: Backpropagationmentioning

confidence: 99%

Optimization of Backpropagation Using Harmony Search for Gold Price Forecasting

Kurniawati

Muhajir

2022

Pak.j.stat.oper.res.

View full text Add to dashboard Cite

show abstract

“…The main reason for selecting these data sets among many others is that they have no missing input feature values. In addition, these problems have been used and cited in the neural networks, classification and machine learning literature (Abusnaina et al, 2014;Camargo, Correa Tissot, & Ramirez Pozo, 2012;Kattan & Abdullah, 2013;Nur, 2015;Vazquez & Garro, 2015). The datasets were obtained from the Machine Learning Repository (UCI).…”

Section: Benchmark Datasetsmentioning

confidence: 99%

Neural Network Training Using Hybrid Particlemove Artificial Bee Colony Algorithm for Pattern Classification

Nuaimi

Abdullah

2017

JICT

View full text Add to dashboard Cite

The Artificial Neural Networks Training (ANNT) process is an optimization problem of the weight set which has inspired researchers for a long time. By optimizing the training of the neural networks using optimal weight set, better results can be obtained by the neural networks. Traditional neural networks algorithms such as Back Propagation (BP) were used for ANNT, but they have some drawbacks such as computational complexity and getting trapped in the local minima. Therefore, evolutionary algorithms like the Swarm Intelligence (SI) algorithms have been employed in ANNT to overcome such issues. Artificial Bees Colony (ABC) optimization algorithm is one of the competitive algorithms in the SI algorithms group. However, hybrid algorithms are also a fundamental concern in the optimization field, which aim to cumulate the advantages of different algorithms into one algorithm. In this work, we aimed to highlight the performance of the Hybrid Particle-move Artificial Bee Colony (HPABC) algorithm by applying it on the ANNT application. The performance of the HPABC algorithm was investigated on four benchmark pattern-classification datasets and the results were compared with other algorithms. The results obtained illustrate that HPABC algorithm can efficiently be used for ANNT. HPABC outperformed the original ABC and PSO as well as other state-of-art and hybrid algorithms in terms of time, function evaluation number and recognition accuracy.

show abstract

Near Optimal Convergence of Back-Propagation Method using Harmony Search Algorithm

Cited by 2 publications

References 21 publications

Optimization of Backpropagation Using Harmony Search for Gold Price Forecasting

Optimization of Backpropagation Using Harmony Search for Gold Price Forecasting

Neural Network Training Using Hybrid Particlemove Artificial Bee Colony Algorithm for Pattern Classification

Contact Info

Product

Resources

About