Prediction of Malignant Melanoma using Machine Learning

Kaimoolayil Thomas, Elizabeth (2021) Prediction of Malignant Melanoma using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (762kB) | Preview
Preview	PDF (Configuration manual) Download (797kB) | Preview

Abstract

Tumour is one of the most rapidly spreading and severe diseases that many people are dealing with nowadays. Among this melanoma is most scary skin cancer that affected by many of the people in these days. So early prediction of this malign and benign melanomas better for the early recovery of the patients. Toady machine learning application in health care is highly increasing. So, for the prediction of malign melanoma in this paper we used 3 different machine earning methods. And analysed each model with different evaluation methods. In this study SVM, Logistic regression and random forest are used as the prediction models. Here the random forest predicts the target with that having accuracy of 74% which has the highest accuracy among the 3 models. SVM and Logistic Regression predict the outcome in accuracy of 63 and 65 respectively. The precision, recall, f1score and area under the ROC curve also shows that random forest is the best among these and other two have an average performance.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Machine learning; melanoma; prediction; colour
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	20 Feb 2023 15:15
Last Modified:	02 Mar 2023 11:49
URI:	https://norma.ncirl.ie/id/eprint/6197

Actions (login required)

View Item