An Optimized Framework Development of ABC Algorithm Along with SVMP Algorithm for Lung Cancer Detection

In medicine, early detection of lung cancer is essential for successful treatment regimens. Despite the small sample size, cancer databases often include gene expression levels as attributes. Therefore, in order to increase the convergence speed of the classification algorithm, redundant features should be eliminated. In this work, we present a unique hybrid method for cancer classification called artificial bee colony with support vector machine selection. This approach for early search of a subset of genes for cancer prognosis optimizes feature selection by combining cuckoo search algorithm (CSA) and Spider-Monkey optimization (SMO) algorithm In order with increased accuracy of artificial bee colony method, we perform Minimum Redundancy Maximum Relevance (mRMR).) method, we reduce the redundancy in gene expression data from the cancer dataset and then these selected gene subsets are efficiently classified into different cancer clusters or groups using deep learning (DL) techniques. We evaluate the effectiveness of our proposed method against eight reference microarray gene expression data sets of various cancers. Classification performance is evaluated using measures such as confusion matrix, F1-score, recall, and accuracy. Our findings show that, when applied to large gene expression datasets linked to cancer, the suggested gene selection strategy in conjunction with DL provides improved classification accuracy compared to other existing DL and machine learning methods.