Optimizing SVM Hyperparameters For Accurate Cancer Cell Classification

This research paper presents an optimized Support Vector Machine (SVM) algorithm for accurate cancer cell classification. This algorithm utilizes the projection of data to higher dimensions and classification using a kernel function, which can be selected from a set of options including linear, polynomial, RBF, and sigmoid. The algorithm is specifically tailored to handle the data set, which is not very large. The accuracy of this model has been verified using F1 score, Jaccard index, and confusion matrix. The results indicate that this SVM algorithm can predict which cell is cancerous with 96% accuracy. This research demonstrates the importance of hyperparameter optimization for machine learning algorithms, particularly for cancer cell classification. By optimizing the hyperparameters of the SVM algorithm, a high level of accuracy in detecting cancer cells could be achieved. The findings suggest that this approach can be applied to other medical imaging applications to improve the accuracy and efficiency of diagnosis.