Prediction of Abalone Age Using Regression-Based Neural Network

Artificial neural networks (ANN) has been widely used to speed up data prediction operations with over thousands of features available. In this paper, we propose a regression-based ANN model with three hidden layers to predict the age of abalones. It is salient to predict abalone age as it helps farmers and sellers to determine the market price of abalones. The economic value of abalone is positively correlated with their respective ages. The age of the abalone can be estimated by measuring the number of layers of shell rings The model was built based on a dataset obtained from the UCI Machine Learning Repository. Before developing and training the model, a pre-processing methodology was applied to the dataset. Parameters tuning, which involves modifications in the number of hidden layers as well as the number of epochs, were done to obtain the best result. The finalised results were analysed and the results show that physical measurements of abalone can predict its respective age with less time consumption. This study has shown a result of low root mean-squared error, obtained from the proposed model in comparison with other methods stated in this study. Finally, the proposed model was validated using test dataset, and the results reveal a lower root-mean-squared error value in contrast to the value obtained during model training.