Towards Improving Breast Cancer Detection Cancer Classification Using an Adaptive Voting Ensemble Learning Algorithm

Towards Improving Breast Cancer Detection Cancer Classification Using an Adaptive Voting Ensemble Learning Algorithm

Mrs. Ashwini R1, Chaithanya R2, Kavya V3 , Anushree SN3 , Ankitha HR3
1 Assistant Professor, Dept of ISE, East West Institute Of Technology, Bengaluru

2,3,4,5 Student, Dept of ISE, East West Institute Of Technology, Bengaluru

Abstract - Breast Cancer has been the most common form of cancer among women in history. The history of cancer detection such as mammograms shows that various techniques were put forward for screening ordering it into88370 malignant or Benign tumors.

The use of single classifiers (like logistic and decision trees) suffers from the ignorance of the complexity and variability of medical data, and as a result the resulting classification performance is poor.

As a result, the aim is to increase the accuracy of breast cancer detection through the utilization of an adaptive voting ensemble learning algorithm based on the dynamic integration of several classifiers according to their performance.

In order increase the efficiency of identifying and diagnosing breast cancer, it makes use of a special approach for universal voting ensemble classifiers, which takes into account the effectiveness of individual classifiers, and modifies their weights dynamically.

KeyWords: Mammography, Ultrasound , MRI, Histopathology Tumour Classification , Model Diversity , Adaptive Weights