Multiclass Classification of Dry Beans using Artificial Neural Network

Abstract

An Artificial Neuron Network (ANN) is a computational model that mimics the way neurons in the human brain work. In agriculture, ANN can be used for various tasks, such as disease and insect detection, crop yield forecasting, soil fertility management, seed categorization, and quality evaluation. Marketing and development of sustainable agricultural systems rely on accurate seed classification. One major goal of this research is to create an ANN model that can reliably classify different types of dried bean seeds based on their shared characteristics. Data from the UC Irvine machine learning repository was used for this study. With the use of principal component analysis (PCA), the most informative characteristics of a dataset are isolated. Using the proposed approach, we intend to categorise seven distinct types of dry bean seeds. The suggested ANN model is then trained using the optimally tuned hyperparameters. The ANN model's effectiveness is measured by its confusion matrix, accuracy, precision, Recall, and F1-Score. After extensive testing, it was determined that the ANN with PCA model had the highest classification accuracy for dried bean seeds (94%) and the highest F1-score (95%).