Abstract

This study presents a novel hybrid approach for data mining and classification of colon and pancreatic cancer datasets using machine learning techniques. We employed Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and the JAYA optimization algorithm to develop an efficient and accurate classification model. The datasets, comprising genetic expression profiles and clinical data from colon and pancreatic cancer patients, were preprocessed and normalized. SVM was utilized for initial feature selection and classification, while CNN was applied for deep feature extraction and pattern recognition. The JAYA algorithm was implemented to optimize the hyperparameters of both SVM and CNN, enhancing their performance. Our proposed hybrid algorithm combines the strengths indicate that our hybrid approach outperforms traditional methods in terms of accuracy, sensitivity, and specificity.