|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Breast cancer is the most prevalent cancer among women in most countries. It has been found through research that early and accurate detection of breast cancer can reduce the risk of death among women. It is therefore imperative to detect breast cancer at initial stages. Machine learning techniques is one of the most trending tools of the 21st century for solving problems and it also beneficial in most applications of use since it has the capability of making predictions and helps to make better decisions. There are several Machine Learning Techniques for identification of breast cancer through training and testing datasets. This paper presents a conceptual approach of a hybrid Machine Learning Techniques for breast cancer prediction. This method employed six different machine learning algorithms respectively, Support Vector Machine (SVM), Linear Regression (LR), K Nearest Neighbor (KNN), K-means, Naïve Bayes (NB) and Hierarchical clustering. The proposed concept combines both bagging and boosting with unsupervised Machine Learning Algorithms and clustering with unsupervised Machine learning algorithms. This is very essential to combine a hybrid Machine Learning Techniques to detect this disease at the early stage to increase the saving lives of women.
Keyword
Machine Learning, Model, Concept, Breast, cancer, Dataset.
PDF Download (click here)
|
|
|
|
|