Particle Swarm Optimization Based Feature Selection on Diagnostic of Lung Cancer Disease

Cancer is the disease that occurs when cells in any organ or tissue are divided and multiplied in an irregular manner. This disease which is one of the most important health problems of today can be treated successfully with various techniques that have emerged in recent years. Diagnosis of cancer diseases with the help of numerical data obtained from microarray data sets requires a lot of processing power due to the high dimensionality of the data sets. In this study; The data set for lung cancer was reduced with Principal Component Analysis (PCA) and Particle Swarm Optimization (PSO) methods and classified with k-Nearest Neighbor (kNN) and Sequential Minimal Optimization (SMO) algorithms. Classification results obtained after the size reduction process are compared with various performance analysis data.