Abstract
Summary: The progression of organizing and classifying data components based on pre‐established criteria is known as data classification. In data classification problems, machine learning methods are frequently used. Although the ability of an algorithm to learn is essential, the recognition quality of algorithms is undoubtedly a key indicator. However, the error made in the beginning is significant, and if it is not rectified then, it causes chaos in data classification. In this research, a fractional hybrid optimization is created with a feed‐forward neural network (FFNN) for the data classification. The pre‐processing of the medical data involves the imputation of missing values and the log transformation. In the feature selection process, the chord distance and the Jaro‐Winkler distance are both employed to choose the important features. The FFNN classifier is used to classify the data, which is trained using the hybrid optimization method, namely the developed Fractional Cuckoo search Invasive Weed Optimization algorithm (FCSIWO). The fractional concept, Invasive Weed Optimization (IWO) algorithm, and Cuckoo search (CS) algorithm are combined to create the FCSIWO. When compared to existing data classification models, the developed technique achieved an optimal sensitivity of 0.9463, an optimal accuracy of 0.9440, and an optimal specificity of 0.9422.

This publication has 21 references indexed in Scilit: