Design A Hybrid Model For Lung Cancer Classification By Applying Svm Classifier With Ffbpnn On Computed Tomography Images

Abstract

The Current Study elaborates the classification of Lung Cancer by traversing the potential consumption of a Hybrid Model in which ROI (Region of interest) is recognised through different segmentation techniques by extracting key points through different features extraction and optimization techniques are implemented to the dataset of CT scan images of 800 pictures. A total of 800 patients were included in this retrospective study and divided into the training set and test set with a ratio of 8:2 randomly. The research work developed a Hybrid Model by using distinct Optimization techniques i.e. Particle Swarm Optimization (PSO). Artificial BEE colony (ABC) and features extraction method namely SIFT (Scale Invariant Feature Transform, Speed Up Robust Feature (SURF), in context of the least execution time with least mean square error rate with support vector machine (SVM) classifier. Additionally, working of the Hybrid Model has been gauged in respect of parameter Accuracy, Error rate, Precision, Recall, and Execution Time. The overall Accuracy of the hybrid model is 99.56% while recall value is 89%, F-measure 93.44% have been obtained for the Hybrid Model.