Methodology of Microarray Breast Cancer Classification

Citation

Mohd Ali, Nursabillilah and Besar, Rosli and Ab Aziz, Nor Azlina (2022) Methodology of Microarray Breast Cancer Classification. In: 2nd FET PG Engineering Colloquium Proceedings 2022, 1-15 December 2022, Multimedia University, Malaysia. (Unpublished)

[img] Text
17_Nursabilillah_PPM Extended Abstract_Second Half 2022.pdf
Restricted to Registered users only

Download (62kB)

Abstract

Background - Breast cancer is one of the main causes of death and the most commonly diagnosed cancer in women. Every year, about 500,000 people die from breast cancer. Purpose – Machine learning is a subfield of artificial intelligence (AI) and computer science that uses data and algorithms to replicate how humans learn, gradually improving its accuracy Design/methodology/approach – This paper discusses the methodology of classifying microarray breast carcinoma. The method comprises of feature selection and categorization utilizing a machine learning approach. Findings – . Pre-processing of the dataset is required to remove noise and undesirable characteristics. The feature selection strategy was able to reduce the large amount of breast cancer features. A grid search strategy is necessary for the machine learning model to adjust the selected feature and classify the relevant characteristics. Research limitations– However, the data should be tested and runs using more than 500 epoch to ensure the good classification rate are achieved. Originality/value – The feature selection method discussed in the study is a contribution to new study

Item Type: Conference or Workshop Item (Other)
Uncontrolled Keywords: Microarray, breast cancer, feature selection, optimization and machine learning
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 16 Feb 2023 07:04
Last Modified: 16 Feb 2023 07:04
URII: http://shdl.mmu.edu.my/id/eprint/10841

Downloads

Downloads per month over past year

View ItemEdit (login required)