Performance of Non-Monotone Versus T-Norms Fuzzy Measures in Fuzzy Logic using Covid-19 Chest X-ray images Data

Abstract

Covid-19 declared by WHO as a global pandemic leading to millions of deaths. In this paper Choquet integral with non-monotone fuzzy measure is compared with the various t -norms fuzzy measures. Here the ensemble model is used to distinguish chest X ray images as Covid infected, Pneumonia infected and Normal patients. Transfer learning technique is used to train four very powerful CNN’s namely Vgg16, Restnet50, InceptionV3 and Densenet121. These pretrained CNN models were finely tuned and then used as classifiers for the chest X-ray images. After that the prediction results of the individual models are aggregated using Choquet integral with non-monotone and t-norm fuzzy measures and the final labels are predicted. Choquet Integral with t-norm fuzzy measure outperforms Choquet Integral with non-monotone fuzzy measure. In order to evaluate the proposed model , chest X- ray images from public repositories like IEEE and Kaggle were used. Choquet Integral with t-norms provides 92.08% accuracy. The results of t-norms fuzzy measures are better than the results of the Choquet integral with non- monotone fuzzy measure..