Distance and Similarity Measures of Intuitionistic Fuzzy Parameterized Intuitionistic Fuzzy Soft Matrices and Their Applications to Data Classification in Supervised Learning

Intuitionistic fuzzy parameterized intuitionistic soft matrices (ifpifs-matrices), proposed by Enginoğlu and Arslan in 2020, are worth utilizing data classification supervised learning due to coming into prominence with their ability model decision-making problems. This study aims define the concepts metrics, quasi-, semi-, pseudo-metrics similarities, pseudo-similarities over ifpifs-matrices; develop a new classifier using them; apply it classification. To this end, develops classifier, i.e., Fuzzy Parameterized Soft Classifier (IFPIFSC), based on six herein. Moreover, performs IFPIFSC’s simulations 20 datasets provided UCI Machine Learning Repository obtains its performance results via five accuracy (Acc), precision (Pre), recall (Rec), macro F-score (MacF), micro (MicF). It also compares aforementioned those of 10 well-known fuzzy-based classifiers 5 non-fuzzy-based classifiers. As result, mean Acc, Pre, Rec, MacF, MicF IFPIFSC, comparison classifiers, 94.45%, 88.21%, 86.11%, 87.98%, 89.62%, best scores, respectively, 94.34%, 88.02%, 85.86%, 87.65%, 89.44%, respectively. Later, conducts statistical evaluations non-parametric test (Friedman) post hoc (Nemenyi). The critical diagrams Nemenyi manifest differences between average rankings IFPIFSC 15 greater than distance (4.0798). Consequently, is convenient method for Finally, present opportunities further research, discusses applications ifpifs-matrices machine how improve IFPIFSC.