Application of Ant Colony Algorithm and Principal Components Analysis in the Diagnosis of Lung Cancer

This paper presents a new method for diagnosing lung cancer by combination of ant colony algorithm, fuzzy logic and principal component analysis (PCA). In this method, PCA method is used to reduce the size of data sets, the fuzzy logic is used to create fuzzy rules that make it possible to be interpreted by experts. Finally, these fuzzy rules are optimized by ant colony algorithm (ACO). Evaluation and comparing the proposed method with other methods have been proposed to implement this approach, leading to lung cancer dataset with criteria such as speed, reliability, and the ability to interpret the show.