<![CDATA[This study uses convolutional neural networks (CNNs) and meta-learning techniques to create an accurate and efficient model for classifying the risk factors of cervical cancer. The dataset includes four types of cervical lesions, and the main objective is to categorize these lesions as either benign or malignant. This classification is essential for early and succesfull treatment of cervical cancer. The challenge arises from the complexity and variations in the images, resulting in the inability of conventional machine learning and deep learning approaches to provide correct classifications. Meta ensemble learning approaches are employed to improve the model's classification accuracy. The dataset of cervical cancer risk factors is preprocessed before being used to train and evaluate numerous CNNs utilizing pre-trained models and various architectures. Subsequently, a meta-learning is employed to optimize the learning process, and used to aggregate the outputs of the multiple CNNs. Moreover, the assessment findings show the model achieves high accuracy and effectiveness. Finally, the suggested model's accuracy score will be contrasted against the current cutting-edge methods used by other existing systems.]]>
Copyrights © 2023
