Abstract
Abstract The rapid pace of development over the last few decades in the domain of machine learning mirrors the advances made in the field of quantum computing. It is natural to ask whether the conventional machine learning algorithms could be optimized using the present-day noisy intermediate-scale quantum technology. There are certain computational limitations while training a machine learning model on a classical computer. Using quantum computation, it is possible to surpass these limitations and carry out such calculations in an optimized manner. This study illustrates the working of the quantum support vector machine classification model which guarantees an exponential speed-up over its typical alternatives. This research uses the quantum SVM model to solve the classification task of a malignant breast cancer diagnosis. This study also demonstrates a comparative analysis of distinct forms of SVM algorithms concerning their time complexity and performances on standard evaluation metrics, namely accuracy, precision, recall, and F1-score, to exemplify the supremacy of quantum SVM over its conventional variants.
Highlights
Breast cancer disease remains the second most common form of cancer diagnosed in women in the United States of America
Out of the three tuned support vector machine (SVM) classifiers, the performance of the nonlinear and quantum SVM classifiers was significantly improved as compared to the linear SVM classifier
The proposed quantum SVM model in this study was successful in solving the task of binary classification of a malignant breast cancer diagnosis
Summary
Breast cancer disease remains the second most common form of cancer diagnosed in women in the United States of America. This cancer matures in breast cells, typically in the ducts or lobules of the breast. Within the domain of computer science, after an exponential increase in the amount of data available and upgraded computational hardware coming into the picture, researchers are able to implement various data mining [2] and machine learning [3] techniques to perform accurate classification on real-life data. The task of diagnosing breast cancer primarily remains as a binary classification problem that consists of the malignant tumor that is cancerous in nature and the other being the non-cancerous benign tumor. With an increase in the number of deciding factors, i.e., features
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have