Feature Selection using Improved Slime Mould Algorithm for Classification of Medical Datasets

Due to the high dimensions of the biological data and presence of irrelevant information, finding relevant information from the medical datasets is a critical issue for the diagnosis of diseases. Hence, feature selection technique is used as a pre-processing stage to find the significant features from the given dataset. Slime Mould Algorithm is an algorithm inspired from the foraging behaviour of the slime mould. An Improved Slime Mould Algorithm (ISMA) is proposed for feature selection and the performance of the ISMA is validated on ten medical datasets. The proposed algorithm provided better results compared to the benchmark algorithms in terms of fitness values, classification accuracies and feature size.