Your browser doesn't support javascript.
Prediction of Covid-19 and post Covid-19 patients with reduced feature extraction using Machine Learning Techniques
18th International Conference on Frontiers of Information Technology (FIT) ; : 37-42, 2021.
Article in English | Web of Science | ID: covidwho-1868539
ABSTRACT
Corona virus has spread the Covid-19 pandemic to the whole world resulting in the loss of about 3.8 million people. Nearly 156.5 million people have recovered from this disease by timely diagnostic using primary symptoms, which include lethargy caused by muscular weakness. Post Covid-19 patients also face myalgia, which is caused by the abnormal neural action potential. Electromyography (EMG) has been used for years to detect the neural communication and the action potential caused by it. Biomedical experts prefer EMG over other methods due to its ability to capture and conserve the data which helps in detecting major muscular disorders. This paper depicts multiple approaches to diagnose current Covid-19 patients or post Covid-19 patients using the EMG data of lower limb using Machine Learning. These approaches vary from each other in the form of the information conserved in the training data. The proposed method achieves the highest accuracy of 93.8% along with increasing the computational efficiency, as compared to the conventional methods. The dataset used is a publically available dataset, provided by University of California, by the name of Irvine (UCI) EMG lower limb dataset.
Keywords

Full text: Available Collection: Databases of international organizations Database: Web of Science Type of study: Prognostic study Topics: Long Covid Language: English Journal: 18th International Conference on Frontiers of Information Technology (FIT) Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Web of Science Type of study: Prognostic study Topics: Long Covid Language: English Journal: 18th International Conference on Frontiers of Information Technology (FIT) Year: 2021 Document Type: Article