MultiArchFusionV16Ensemble: A Novel Neural Network Based Ensemble Model for Enhanced Cervical Cancer Detection

Among the world's leading health risks for women is cervical cancer.The condition is characterized by cervical anomalies that may be detected, and decreasing death rates and increasing treatment outcomes depend on early discovery.With modern technology's improvements, cancer is diagnosed using different Artificial Techniques.The purpose of this study is to use the Mendeley LBC dataset to identify cervical cancer.We applied data augmentation techniques to maintain the dataset diversity in our research, increasing the data samples.We proposed a Nobel Ensemble model called MultiArchFusionV16Ensemble (CNN, DNN, LSTM, VGG-16) that combines many base and meta-learners, such as the CNN, DNN, LSTM, and VGG16 architecture, to improve accuracy in cervical cancer diagnosis.By harnessing the diversity of these models, we aim to enhance our detection system's robustness and generalization capabilities.Our proposed ensemble model demonstrates promising result in evaluation, with an acccuracy of 98%.When the suggested model is compared to other models, indicating that it has been improved upon from prior studies.Robustness and generalization are shown by our new MultiArchFusionV16Ensemble model, which has been rigorously evaluated across various criteria to confirm its effectiveness and superiority.