Breast Cancer Data Classification Using Cluster Based Ensemble Machine Learning
- Resource Type
- Conference
- Authors
- Tasneem, Rayeesa; Jyothi, B N; Anuhya, K; Jabbar, M. A.
- Source
- 2024 IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE) Women in Innovation, Technology & Entrepreneurship (ICWITE), 2024 IEEE International Conference for. :710-716 Feb, 2024
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Measurement
Machine learning algorithms
Clustering algorithms
Lung cancer
Prediction algorithms
Breast cancer
Data models
Machine learning
Ensemble learning
Random Forest
Radial Basis Function
Accuracy
- Language
Breast cancer (BC) is the most prevalent type of cancer among women throughout the world and it is recorded as the second most life-threatening disease after lung cancer. Early prediction and diagnosis of this cancer is the only method to control and decrease the death rates worldwide. Breast cancer can be diagnosed and predicted using many tools and techniques based on Machine Learning (ML) algorithms. In recent times, ML techniques have been getting greater attention in medicine. This paper uses a cluster-based ensemble model to classify the Breast Cancer (BC) data. The Single classifier is not capable of obtaining high accuracy. Base classifiers cannot detect the BC accurately. So, the ensemble classifier is built using base classifiers. The proposed cluster-based ensemble model uses a Random Forest (RF) algorithm and Radial Basis Function (RBF). The k-means clustering technique is applied in the process. This experimental analysis uses the Wisconsin Breast Cancer Dataset (WBCD). We have used nine different metrics to test the proposed model. According to the experimental results obtained, the proposed cluster-based ensemble model recorded a remarkable accuracy of 99.28% which has outperformed the existing methods.