Coronavirus disease situation analysis and prediction using machine learning: a study on Bangladeshi population

Abstract

During a pandemic, early prognostication of patient infected rates can reduce the death by ensuring treatment facility and proper resource allocation. In recent months, the number of death and infected rates has increased more distinguished than before in Bangladesh. The country is struggling to provide moderate medical treatment to many patients. This study distinguishes machine learning models and creates a prediction system to anticipate the infected and death rate for the coming days. Equipping a dataset with data from March 1, 2020, to August 10, 2021, a multi-layer perceptron (MLP) model was trained. The data was managed from a trusted government website and concocted manually for training purposes. Several test cases determine the model's accuracy and prediction capability. The comparison between specific models assumes that the MLP model has more reliable prediction capability than the support vector regression (SVR) and linear regression model. The model presents a report about the risky situation and impending coronavirus disease (COVID-19) attack. According to the prediction produced by the model, Bangladesh may suffer another COVID-19 attack, where the number of infected cases can be between 929 to 2443 and death cases between 19 to 57.

Blockchain associated machine learning and IoT based hypoglycemia detection system with auto-injection feature

“…Here a third party is needed to measure the blood glucose level and give the patient some sugar [2]. In recent years, machine learning and IoT-based technologies have shown promising results in health [3]- [5], agriculture [6], [7], and other sectors [8] in making automated decisions and treatments.…”

A network analysis and support vector regression approaches for visualising and predicting the COVID-19 outbreak in Malaysia

“…The SVR is a well-known and influential supervised machine learning technique from a support vector machine (SVM) that finds the best-fitted line for linear and non-linear regressions in predicting COVID-19-related cases [18] . A study of COVID-19 in Bangladesh showed an excellent regression value of 0.8230 and 0.8322 for infected and death cases, respectively, using the radial basis function (RBF) kernel of SVR [19] . Also, a study of COVID-19 on the Turkish population showed that the SVR performed an excellent regression value at 94% with a low root mean square error (RMSE 0.034) and mean absolute error (MAE 0.036) compared to linear regression (LR), bagged tree (BT) and fine tree (FT) algorithms [20] .…”