Publication Date: 2023/08/02
Abstract: Worldwide, breast cancer is the leading cause of death among women. Early detection is essential for reducing aggressive treatments and increasing survival rates. Machine learning algorithms have demonstrated their ability to diagnose breast cancer accurately from medical imaging data. However, no individual algorithm can consistently provide optimal results. To address this, researchers have proposed hybrid ensemble learning models that combine multiple approaches. In this study, we have proposed a hybrid ensemble learning model that combines three powerful algorithms, the Random Forest (RF), Multilayer Perceptron (MLP) and the Deep Belief Network (DBN) to diagnose breast cancer accurately.The MLP and DBN algorithm teaches non-linear correlations between features and labels, while the RF algorithm uses a random subset of features to create multiple decision trees and combine their predictions. The proposed hybrid model trains the RF, MLP and DBN models separately on a breast cancer dataset and integrates them using a weighted average method for the final prediction.Cross- validation is used to establish the optimal weights for the RF, MLP and DBN models.Our findings suggest that the hybrid ensemble learning model is a more reliable and accurate tool for breast cancer identification than individual machine learning algorithms. This model has significant potential for early breast cancer identification in clinical settings, leading to better patient outcomes and reduced healthcare costs. Our research demonstrates the effectiveness of hybrid ensemble learning models in improving breast cancer identification accuracy.
Keywords: Breast Cancer, Machine Learning, Random Forest, MLP, DBN, Ensemble Learning, Hybrid Model.
DOI: https://doi.org/10.5281/zenodo.8207264
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23JUL955.pdf
REFERENCES