Machine Learning and Neural Network based Early Prediction of Corona Virus and Diagnosing the Status of heart diseases

The prediction of several viruses and biomedical signal classifications in recent times have evolved tremendously with the help of machine learning models and neural networks. This paper studies coronavirus, and ECG datasets which are further trained and tested by machine learning algorithms and neural networks such as Linear Regression (LR), Logistic Regression, Extreme Gradient Boosting (XGBoost), Random Forest (RF) Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN) to predict the possibility of confirmed, cured and death cases including the symptoms related to virus attack, heart and brain disease falling under each subject post training and validation. This paper demonstrates a comparative analysis among our work and parallel research work using machine learning models and neural networks with respect to accuracy. An accuracy of (90-95)% has been achieved by machine learning algorithms during the prediction of various diseases with an error rate of approximately 6%. Furthermore, neural networks produced an accuracy of (90-92)% for the same datasets with an error rate of nearly 3%. The resultant model produces high accuracy and may be used to in embedded and IoT devices to improvise the outcome for intended diseases.