期刊名称:Journal of Theoretical and Applied Information Technology
印刷版ISSN:1992-8645
电子版ISSN:1817-3195
出版年度:2014
卷号:61
期号:2
出版社:Journal of Theoretical and Applied
摘要:In this paper, investigations to evaluate various feature extraction and selection methods for classification of lung images are conducted. Widespread screening by CT or MRI is not practical, ensuring that chest radiology is the most common procedure for diagnosis of lung disease. The term lung disease refers to the disorders that affect the lungs such as asthma, COPD and infections like influenza, pneumonia, tuberculosis, lung cancer, and many other breathing problems. This study classifies Lung images automatically as Pleural effusion, Emphysema, Bronchitis and normal lung scan. Features extraction is through Gabor filter, Walsh hadamard transform. Feature selection is through Correlation based Feature Selection (CFS), Principal component analysis (PCA). Classification is through use of Na�ve Bayes, J 48, K- Nearest Neighbour (KNN) and Multi-Layer Perceptron Neural Network. The results of the performance ensure that the PCA with multi layer perceptron provides above 81% of accuracy.