Development of a fuzzy logical model of Sugeno for the classification of grain varieties

Abstract

Ambiguity and fuzziness are characteristic of many real-life situations, including the classification of objects based on their characteristics. In this context, fuzzy logic is a powerful tool for modeling uncertainty and making decisions under fuzzy conditions. The Sugeno model, a subset of fuzzy logic, offers a simple and effective approach to constructing rule-based control and classification systems based on linguistic variables. This paper explores the application of the Sugeno model to classify grain varieties based on their characteristics. For this purpose, a data set containing information about the parameters of grains from three different varieties of wheat is used. The study develops a fuzzy logic model that can effectively and accurately classify grain varieties based on their size and shape. To build the model, the scikit-fuzzy library is used, which provides tools for working with fuzzy logic in the Python programming language. Experiments are conducted with different variants of classification rules, optimizing the model to achieve the highest classification accuracy and reliability. The results obtained allow us to evaluate the effectiveness and applicability of the Sugeno model for the classification problems of grain varieties. The developed model can be useful for agronomists and agricultural specialists to automate the process of identifying wheat varieties based on their characteristics.