Adaptive fuzzy logic-based framework for handling imprecision and uncertainty in classification of bioinformatics datasets

Classification in the emerging field of bioinformatics is a challenging task, because the information about different diseases is either insufficient or lacking in authenticity as data is collected from different types of medical equipments. In addition, the limitation of human expertise in manual diagnoses leads to incorrect diagnoses. Moreover, the information gathered from various sources is subject to imprecision and uncertainty. Imprecision arises when the data is not validated by experts. This paper presents an adaptive Type-2 Fuzzy Logic System-based (FLS) classification framework for multivariate data to diagnose different types of diseases. This framework is capable of handling imprecision and uncertainty, and its classification accuracy and performance are measured by using University of California Irvine (UCI), well-known medical data sets. The results are compared with the most common existing classifiers in both computer science and statistics literatures. This classification is performed based on the nature of inputs (e.g., singleton or nonsingleton) and on whether uncertainty is present in the system or absent. Empirical results have shown that our proposed FLS classification framework outperforms earlier implemented models with better classification accuracy. In addition, we conducted empirical studies on this classifier regarding the impact of various parameters of FLS such as training algorithms and defuzzification methods.