An Efficient Covid-19 Prediction Using Dynamic Parameter Based Artificial Fish Swarm Algorithm with Ensemble Learning

Abstract

Corona virus infection spreads quickly. COVID-19 is a serious pneumonia virus that is projected to have a major influence on the healthcare industry. Prenatal recognition is essential for proper behavior, which relieves burden on the health-care system. Recently, the various Machines Learning (ML) techniques are used to predict the cases of daily increase Covid-19. The previous system designed an Improved Coefficient based Chicken Swarm Optimization (ICCSO) with Exponential Distribution based Long Short-Term Memory (EDLSTM) approach for covid-19 prediction. However, the ensemble models produce better prediction accuracy compared to single model. For successful COVID -19 prediction, the suggested system constructed a Dynamic Parameter based Artificial Fish Swarm Algorithm (DPAFSA) with Ensemble Learning (EL). The COVID-19 case dataset is used as a starting point, and it is standardised using Z-score normalisation. Then Independent Component Analysis(ICA) is used to diminish the dimensions. The Dynamic Parameter based Artificial Fish Swarm Algorithm (DPAFSA) is used to find the best attributes to increase classification accuracy. Ensemble Learning (EL) with Exponential Distribution based Long Short-Term Memory (EDLSTM), Intuitionistic Fuzzy Gaussian Function based Adaptive-Neuro Fuzzy Inference System (IFGF-ANFIS), and Support Vector Machine (SVM) classifier is used to predict COVID-19 based on the specified attributes. An actual data set would be used to carry out the experiment. The suggested system outperforms the existing system in terms of accuracy, precision, recall, and f-measure, according to the results.