Frontiers of Information Technology (2013)
Islamabad, Pakistan Pakistan
Dec. 16, 2013 to Dec. 18, 2013
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FIT.2013.17
Demand for automatic classification of Brain MRI (Magnetic Resonance Imaging) in the field of Diagnostic Medicine is rising. Feature Selection of Brain MRI is critical and it has a great influence on the classification outcomes, however selecting optimal Brain MRI features is difficult. Particle Swarm Optimization (PSO) is an evolutionary meta-heuristic approach that has shown great potential in solving NP-hard optimization problems. In this paper MRI feature selection is achieved using Discrete Binary Particle Swarm Optimization (DBPSO). Classification of normal and abnormal Brain MRI is carried out using two different classifiers i.e. Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Experimental results show that the proposed approach reduces the number of features and at the same time it achieves high accuracy level. PSO-SVM is observed to achieve high accuracy level using minimum number of selected features.
Feature extraction, Magnetic resonance imaging, Support vector machines, Accuracy, Wavelet transforms, Polynomials, Particle swarm optimization,Classifier, Feature Selection, Brain Magnetic Resonance Imaging, Particle Swarm Optimization, Support Vector Machine, K-Nearest Neighbor
Atiq ur Rehman, Aasia Khanum, Arslan Shaukat, "Hybrid Feature Selection and Tumor Identification in Brain MRI Using Swarm Intelligence", Frontiers of Information Technology, vol. 00, no. , pp. 49-54, 2013, doi:10.1109/FIT.2013.17