Performance Analysis of Artificial Neural Networks Training Algorithms and Transfer Functions for Medium-Term Water Consumption Forecasting
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 4
Abstract
Artificial Neural Network (ANN) is a widely used machine learning pattern recognition technique in predicting water resources based on historical data. ANN has the ability to forecast close to accurate prediction given the appropriate training algorithm and transfer function along with the model’s learning rate and momentum. In this study, using the Neuroph Studio platform, six models having different combination of training algorithms, namely, Backpropagation, Backpropagation with Momentum and Resilient Propagation and transfer functions, namely, Sigmoid and Gaussian were compared. After determining the ANN model’s input, hidden and output neurons from its respective layers, this study compared data normalization techniques and showed that Min-Max normalization yielded better results in terms of Mean Square Error (MSE) compared to Max normalization. Out of the six models tested, Model 1 which was composed of Backpropagation training algorithm and Sigmoid transfer function yielded the lowest MSE. Moreover, learning rate and momentum value for the models of 0.2 and 0.9 respectively resulted to very minimal error in terms of MSE. The results obtained in this research clearly suggest that ANN can be a viable forecasting technique for medium-term water consumption forecasting.
Authors and Affiliations
Lemuel Clark P. Velasco, Angelie Rose B. Granados, Jilly Mae A. Ortega, Kyla Veronica D. Pagtalunan
Keywords
Related Articles
- EP ID EP285904
- DOI 10.14569/IJACSA.2018.090419
- Views 73
- Downloads 0
Prediction by a Hybrid of Wavelet Transform and Long-Short-Term-Memory Neural Network
Data originating from some specific fields, for in-stance tourist arrivals, may exhibit a high degree of fluctuations as well as non-linear characteristics due to time varying behaviors. This paper proposes a new hybrid...
Competitive Representation Based Classification Using Facial Noise Detection
Linear representation based face recognition is hotly studied in recent years. Competitive representation classification is a linear representation based method which uses the most competitive training samples to sparsel...
A Defected Ground based Fractal Antenna for C and S Band Applications
In this paper, a modified ground based rectangular shaped fractal patch antenna will be presented. Since, the research community has witnessed a significant demand of both light weight and small sized micro-chip antenna...
Techniques for Improving the Labelling Process of Sentiment Analysis in the Saudi Stock Market
Sentiment analysis is utilised to assess users’ feedback and comments. Recently, researchers have shown an increased interest in this topic due to the spread and expansion of social networks. Users’ feedback and comments...
FPGA Prototype Implementation of Digital Hearing Aid from Software to Complete Hardware Design
The design and implementation of digital hearing aids requires a detailed knowledge of various digital signal processing techniques used in hearing aids like Wavelet Trans-forms, uniform and non-uniform Filter Banks and...