Identification of Dry Bean Varieties Based on Multiple Attributes Using CatBoost Machine Learning Algorithm

Table 1

Recent research activity on bean variety classification.

Research works	Methodologies	Findings
Hasan et al. [14]	Deep neural network was implemented to identify the various categories of dry beans	93.44 percent accurate and had an F1 score of 94.57 percent when applied to a dataset of seven varieties of dry beans
Koklu and Ozkan [11]	Dry beans with 7 varieties were identified using ML algorithms	Achieved overall classification rates of 91.73 percent, 93.13 percent, 87.92 percent, and 92.52 percent for MLP, SVM, kNN, and DT, respectively
Arboleda et al. [19]	195 training images and 60 testing images coffee bean species were used with ANN	Obtained classification scores of 96.66 percent
De Oliveira et al. [17]	Employed ANN as the transformation model and the Bayes as classifier to identify the coffee beans types such as whitish, cane green, green, and bluish-green	Achieved a generalisation error of 1.15 percent
Kilic et al. [12]	69 samples of beans were used to develop the neural network-based classification system for beans	The system’s overall performance in classifying beans was 90.56 percent