Predicting the upshot of covid-19 on crude-oil prices in nigeria using mlparima model

Researchers and investors have been paying close attention to the application of Artificial Intelligence models to the economics, agriculture and other fields in recent years. This study uses a Multilayer Perceptron Artificial Neural Network to anticipate the effect of covid-19 on crude-oil prices, continuing the deep learning trend and also applied the use of time series model known as Autoregressive Integrated Moving Average (ARIMA) to validate the result gotten from MLP-ANN. The results produced accurately predicted crude oil prices, and covid-19 data was also analyzed, as well as the association between crude-oil prices and covid-19. Because of the substantial causative association between the coronavirus (number of confirmed cases), crude oil prices, this study is intriguing. Ten years forecast was done using both MLP-ANN and ARIMA and from result gotten, MLP-ANN has accuracy of 96% while ARIMA has 39% accuracy. © 2022 IEEE.

An IOT-Based COVID-19 Detector Using K-Nearest Neighbor

COVID-19 is rampaging the world, increasing medical emergencies, imposing a high cost on every Nation’s expenditure without minding the budget, and causing a continuous rise in the death rate. It has come to stay and live with people in the world. The cure is no longer the case, but how to manage it is now the fact. It is essential to save time, cost of running tests and test kits, cost of purchasing vaccine, create awareness in public places, decongest the isolation centers, save time to get test results, and provide mobility advantage for testing people anywhere and everywhere. This model will quickly detect and report COVID-19 symptoms on patients with cost-effectiveness to bring down the rising curve. It presents an Internet of Things (IOT) based COVID-19 detector that lowers the cost of testing by using machine learning techniques for easy and timely detection of Covid-19 symptoms in a patient. The device integrates an Infrared (IR) camera, Infrared skin thermometer, IR stethoscope, IR sphygmomanometer for blood pressure, a liquid crystal display screen to show the result, a Buzz alarm and its database, hosted in the cloud and connected via the wireless network. The training and test data gives an accuracy of 0.995 and 0.996, respectively, by using the k-nearest neighbor’s classifier. It shows that the model performs well on training and test data without overfitting. Nine patients were further tested with the model, four were reported positive by this model, five returned negative, and the maximum time taken to complete the check was 28 s, while the minimum time was 20.5 s, which shows that the device is time-efficient and can be used where large numbers of people are expected. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.