Application of Automated Machine Learning and Bagging Techniques to Classify Rice Varieties

We have witnessed increased research investigating digitalisation in the agricultural sector in recent years. In particular, machine learning and artificial intelligence find applications in agricultural product classification, quality control and species identification. The fast-processing times, high accuracy levels and cost-effectiveness offered by digital solutions for quality control and classification accelerate these studies. This study proposes a collaborative learning model utilising Automated Machine Learning and Bagging techniques for rice species detection and classification. The model uses a dataset from the UCI Irvine Machine Learning Repository, which contains characteristics specific to the Osmancık and Cammeo rice varieties grown in Turkey. The data set consists of 3810 data points, 2180 of which belong to Osmancık rice and 1630 to Cammeo rice. During the analysis, MLBox, an Automated Machine Learning library, was used to determine the optimal algorithm (Light Gradient Boosting Machine - LGBM) and its hyperparameters. Later, by applying the Bagging technique within the developed learning model, an accuracy rate of 93.54% was achieved in rice-type classification.