Classification and Feature Selection Method for Medical Datasets by Brain Storm Optimization Algorithm and Support Vector Machine

• Published in: Procedia computer science Vol. 162; pp. 307 - 315
• Main Authors: Tuba, Eva, Strumberger, Ivana, Bezdan, Timea, Bacanin, Nebojsa, Tuba, Milan
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 2019
• Subjects: brain storm optimization algorithm; classification; feature selection; medical datasets; optimization; support vector machine; swarm intelligence; brain storm optimization algorithm; support vector machine; optimization; medical datasets; classification; feature selection; swarm intelligence
• ISSN: 1877-0509; 1877-0509
• DOI: 10.1016/j.procs.2019.11.289

Medicine is one of the sciences where development of computer science enables a lot of improvements. Usage of computers in medicine increases the accuracy and speeds up processes of data analysis and setting the diagnoses. Nowadays, numerous computer aided diagnostic systems exist and machine learning algorithms have significant role in them. Faster and more accurate systems are necessary. Common machine learning task that is part of computer aided diagnostic systems and different medical data analytic software packages is classification. In order to obtain better classification accuracy it is important to choose feature set and proper parameters for the classification model. Medical datasets often have large feature sets where many features are in correlation with others thus it is important to reduce the feature set. In this paper we propose adjusted brain storm optimization algorithm for feature selection in medical datasets. Classification was done by support vector machine where its parameters are optimized also by brain storm optimization algorithm. The proposed method is tested on standard publicly available medical datasets and compared to other state-of-the-art methods. By analyzing the obtained results it was shown that the proposed method achieves higher accuracy and reduce the number of feature needed.