An Intensive Review Analysis about Fuzzy Logic usage in Smart Medical Care System

This paper presents a novel automated approach to medical data classification using an interval type-2 fuzzy thinking system (IT2FLS) and wavelet transformation (WT). Wavelet coefficients are highly discriminative features that serve as condensed reconstructions of the underlying data. Uncertainty and high-dimensional data provide issues that are addressed by the combination of WT and IT2FLS. With the use of fuzzy c-means (FCM) clustering for unsupervised structure learning and evolutionary algorithms for supervised parameter adjustment, the IT2FLS employs a hybrid learning approach. The use of WT streamlines this computationally demanding learning process, lowering computational load and improving IT2FLS performance. Well-known medical datasets (Cleveland heart disease and Wisconsin breast cancer) from the UCI Collection for machine learning are used for experimental assessments. Computed performance measures include area under the receiver operator characteristic curve, sensitivity, specificity, and accuracy. The findings demonstrate the better efficacy of the wavelet-IT2FLS methodology in comparison to other machine learning techniques, such as adaptive neuro-fuzzy inference system, fuzzy ARTMAP, support vector machine, and probabilistic neural network. The suggested approach has potential to assist clinicians and medical professionals in making decisions.