Kamaruddin, Mohammad Nurhaqim (2020) Design and development of breast cancer diagnosis system using machine learning. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)
![]() |
Text (24 Pages)
Design and development of breast cancer diagnosis system using machine learning.pdf - Submitted Version Download (509kB) |
![]() |
Text (Full Text)
Design and development of breast cancer diagnosis system using machine learning.pdf - Submitted Version Restricted to Repository staff only Download (2MB) |
Abstract
This research deals with the design and development of machine learning for diagnosis of cancer, which is then used for prognosis. It acts as an alternative to assist the pathologist in analyzing the cell physical characteristics under a microscope and determining whether the tissue removed is benign (non-cancerous) or malignant ( cancerous) in the early detection. The initiative focuses primarily on early breast cancer screening, and aims to classify patients on the basis of tests. While the traditional method is good, early diagnosis of breast cancer can significantly improve the prognosis and the chance of survival, as it can help the clinical treatment of patients. The importance of cancer patients has inspired many biomedical and bioinformatics investigative teams to study the use of machine learning approaches. Variation of methods in this machine-learning, such as Decision-Tree Classifier, Logistic Regression, SVM, Gaussian-NB and Random Forest Classifier, which are widely used in cancer research in predictive models for efficient and accurate decision-making, can be crucial since we can choose the best model. Furthermore, it is important that machine learning algorithms are able to identify core features from very large datasets
Item Type: | Final Year Project (Project Report) |
---|---|
Uncontrolled Keywords: | Breast cancer, Cancer diagnosis, Machine learning, Benign, Malignant |
Divisions: | Library > Final Year Project > FTKEE |
Depositing User: | Norfaradilla Idayu Ab. Ghafar |
Date Deposited: | 15 Aug 2022 04:15 |
Last Modified: | 19 Aug 2022 05:15 |
URI: | http://digitalcollection.utem.edu.my/id/eprint/26632 |
Actions (login required)
![]() |
View Item |