The Use of Artificial Neural Networks Optimized with Fire Fly Algorithm in Cancer Diagnosis

Abstract

Today, the amount of biological data types obtained are increasing every day. Among these datatypes are micro arrays that play an important role in cancer diagnosis. The data analysis that arecarried out through traditional approaches have proven unsuccessful in delivering efficientresults on data types where data complexity is high and where sampling is low. For this reason,using a hybrid algorithm by merging the effective features of two distinct algorithms will yieldeffective results. In this study, a classification process was performed firstly by dimensionreduction on micro array data that were obtained from the tissues from patients with a tumor intheir central nervous system and then by using an artificial neural network algorithm that wasoptimized through Fire Fly Algorithm (FF), a hybrid approach. The data obtained werecompared to K Nearest Neighbors (KNN), Support Vector Machine (SVM) and ArtificialNeural Networks (ANN) classification algorithms, which are frequently used in the literature.Also, the results were compared to the findings that were obtained from artificial neuralnetworks, which are reinforced by Genetic Algorithm (GA), another hybrid approach. Then theresults were shared. The performance results obtained show that hybrid approaches present ahighly precise and more efficient classification process but they show a slower performancethan basic classification algorithms.