Ensemble of Deep Neural Networks based on Condorcet's Jury Theorem for screening Covid-19 and Pneumonia from radiograph images

Gaurav Srivastava, Nitesh Pradhan, Yashwin Saini

Abstract: Highlights•A voting ensemble of deep learning models for Covid-19 and Pneumonia Detection.•A novel Domain Extended Transfer Learning-based soft voting ensemble method is proposed.•A novel approach of Hard voting, i.e., Majority voting based on Condorcet’s Jury Theorem, is proposed.•A faster training algorithm has been proposed to save computational efforts.•Condorcet’s Jury Theorem has been demonstrated in neural networks for the first time.