Fuzzy Inference of the Effectiveness Factors of The Computational Model for the Diagnosis of Breast Cancer
И. В. Гермашев, Victoria Dubovskaya, Alexander Georgievich Losev, Illarion Popov · 2021 3rd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA) · 2021
This work is devoted to building the foundations of a new method for modifying machine learning algorithms. At the first stage, a factorial model of highly informative breast cancer diagnostic features was built. About factor loads, Mamdani's fuzzy conclusion was applied to establish the level of features' influence on the classification result. Changing the function of calculating the error of the method by this new knowledge will make it possible to more accurately and adequately set the machine learning model.