ПОСТРОЕНИЕ МОДЕЛИ СУГЕНО ДЛЯ РЕШЕНИЯ ЗАДАЧ ДИАГНОСТИКИ РАКА ГРУДИ

Abstract

This paper investigates the application of the Sugeno fuzzy logic model to solve a diagnosis problem based on medical data. The diagnosis problem is a key one in medical practice, especially in the field of early detection of diseases such as cancer. As an example of a diagnosis problem, we consider the diagnosis of breast cancer based on medical images and cell characteristics. For this purpose, the classic breast_cancer dataset containing information on various cell characteristics from breast biopsies is used. The Sugeno model is an extension of the Mamdani fuzzy logic model, which uses fuzzy rules for decision making and has an output function shape that depends on the values ​​of the input variables. In this paper, the Sugeno model is adapted to solve the problem of breast cancer diagnosis based on cell characteristics. To build the model, pre-processing and data analysis, including normalization and feature selection, are performed. Then, fuzzy rules are defined based on expert knowledge or data mining. The model is trained on a training set and evaluated on a test set using classification quality metrics. The experimental results demonstrate the effectiveness of the Sugeno model in solving the problem of breast cancer diagnosis based on medical data. The resulting model is capable of classifying cell samples with high accuracy, which could be useful for the early detection and treatment of breast cancer and other types of cancer.