Simplified artificial neural network configuration in R programming for predictive modelling

• Main Authors: Razak, Tajul Rosli, Jarimi, Hasila, Ahmad, Emy Zairah
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Online Access: http://eprints.utem.edu.my/id/eprint/28004/1/Simplified%20artificial%20neural%20network%20configuration%20in%20R%20programming%20for%20predictive%20modelling.pdf; http://eprints.utem.edu.my/id/eprint/28004/; https://ieeexplore.ieee.org/document/10468195

The configuration of Artificial Neural Networks (ANNs) in the context of predictive modelling can provide considerable difficulty owing to the complex nature of their arrangements and the need for meticulous hyperparameter adjustment the present study addresses the issue by proposing a more straightforward methodology for configuring Artificial Neural Networks (ANNs) through the R programming language the methodology presented in this study offers a systematic and comprehensive framework, ensuring accessibility and simplicity of implementation. This approach aims to enhance the usability of Artificial Neural Networks (ANNs) for practitioners who need advanced machine learning knowledge. In order to demonstrate the applicability of the proposed methodology, a series of experiments were conducted on a case study in sustainable energy research. This study makes a valuable contribution to academic discipline by establishing a connection between artificial neural network (ANN) theory and its practical application. This study aims to enhance the accessibility of artificial neural network (ANN) setup and provide significant insights to further progress predictive modelling, specifically focusing on sustainable energy research.