CGO-ensemble: Chaos game optimization algorithm-based fusion of deep neural networks for accurate Mpox detection

Sohaib Asif, Ming Zhao, Yangfan Li, Fengxiao Tang, Yusen Zhu

Abstract: Highlights•Our ensemble combines five transfer learning-based models to enhance disease detection capabilities.•We enhance the base models by incorporating feature integration layers and residual blocks, allowing them to extract intricate features and patterns effectively.•We employ the chaos game optimization algorithm to optimize base model weights efficiently, resulting in improved ensemble performance.•Our evaluation, conducted on both benchmark and newly curated datasets, highlights CGO's superiority in terms of accuracy and ensemble effectiveness.•Our approach presents a robust solution for the detection of monkeypox from skin images, significantly enhancing accuracy in disease diagnosis.