Publications

Abstract : Throughout the world, cancer is the top cause of mortality in women. Whatever improvement in cancer ailment identification and prognosis is vital to living a healthy life. As a consequence, excellent cancer prediction accuracy is crucial for maintaining treatment and survival criteria current for patients. Machine learning techniques, which have been found to have a major impact on the identification and early treatment of breast cancer, have emerged as a hotspot for study and have been demonstrated to be a potent methodology. We used five machine learning algorithms in this research. There have been various empirical investigations employing machine learning and soft computing techniques to treat breast cancer. This article provides an overview of the available technologies for advanced treatment of breast cancer, as well as an introduction to the concepts and current achievements in personalised medicine that depend on technology. The many kinds of breast cancer are addressed, as well as their worldwide occurrence. It is discussed the importance of recognising irregularities and distinguishing between benign and malignant breast cancer. Levenberg-Marquardt (LM) and Sparse Representation (SR) have been combined to model a new approach for diagnosing breast cancer. With LM’s training accuracy and SR’s robustness in identifying small deformations, an impressive performance was achieved in terms of accuracy and mean square error. Data has been acquired from the Wisconsin Dataset (WD). This model proves the combination of several classification algorithms could enhance the model in a significant manner and can be used for pre-clinical diagnosis.