GUI BASED PREDICTION OF BREAST CANCER STAGES USING ENSEMBLE LEARNING METHOD

Abstract

Breast cancer (BC) is one of the most prevalent forms of cancer among women all over the world,
accounting for the series of new infections and tumor-related deaths according to statistical data.
Machine learning has indeed been commonly used in the identification of benign and cancerous cells of
various diseases and has produced successful results. Our research provides a comprehensive guide for
the sensitivity analysis of model output parameters in breast cancer detection. It is important to have an
early diagnosis of cancer. The survey collected through an intrusive procedure can be conveniently
digitalized and treated depending on simulation. With machine learning techniques for medical imaging
the processing speed can improve considerably and treatment can be considerably less expensive on a
large scale. Data processing by a supervised learning method can be carried out with the processes like
feature detection, uni-variate analysis, and bi-variate and multivariate analysis, etc. The main goal is to
detect breast cancer phases in clients by machine learning systems. In fact, the assessment rating study
describes the results one by one from data set of the medical centre and defines the uncertainty index.
Recognition, cleaning / preparation of data and simulation of data will be performed on the whole set of
data. The goal to categorize target data and the outcome thus reveals that the performance of the
suggested machine learning system can be correlated with the best possible precision, exactness, retrieval
and F1 ranking.[3]