 We have recently seen signs of recovery from the effects of COVID-19. Economic, social and cultural impacts of a pandemic cannot be ignored and we must be prepared to handle similar situations in the future. Recent cases of monkeypox have raised concerns about potential pandemics, requiring proper protocols and methods to deal with them effectively. Early detection and treatment are essential to prevent further spread of the disease. To address this issue, we propose an ensemble learning-based framework to detect the presence of the monkeypox virus from skin lesion images. First, we use three pre-trained base learners, inception V3, inception and dense net 169, to fine-tune on a target monkeypox dataset. Then, we extract probabilities from these deep models and feed them into the ensemble framework. Finally, we combine the results using a beta-function-based normalization scheme and a sum rule-based ensemble. Our proposed framework was evaluated on a publicly available monkeypox skin lesion dataset using a five-fold cross-validation setup. The results show that it achieved an average of 93.39%, 88.91%, 96%. This article was authored by Reshav Pramannik, Bihann Banerjee, George Fomenko, and others. We are article.tv, links in the description below.