Details

Autor(en) / Beteiligte

• Pawar, Suvarna
• Futane, Pravin
• Uke, Nilesh
• Bhise, Rasika
• Mandal, Priyanka
• Khopade, Tejas
• Rasane, Tejas
• Chaudhary, Aryan
• Islam (Naz), Sardar M. N.
• Islam (Naz), Sardar M. N

Titel

Coronavirus Outbreak Prediction Analysis and Coronavirus Detection Through X-Ray Using Machine Learning

Ist Teil von

• Computational Health Informatics for Biomedical Applications, 2023, p.135-152

Auflage

1

Ort / Verlag

United Kingdom: Apple Academic Press

Erscheinungsjahr

2023

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Corona, generally referred to as COVID-19, is the biggest trouble for society as it hampers human lives in all aspects. This SARS-CoV-2 has caused havoc on people to a large extent all over the world. In real-time, it is hampered in a cumulative manner as it is growing at a faster rate day by day. Machine learning (ML) might be used to track the disease, predict its progress, and design tactics and legislation to control it. Predictive analysis has become a critical component for future prediction as the science of ML has progressed. As the COVID-19 pandemic unfolds, it would be beneficial to forecast the number of positive cases in the future so that stronger measures and control may be implemented. In this work, two supervised learning models experimented to anticipate the future using the COVID-19 time-series dataset during the second pandemic wave from January 20 to 136March 20. To look at the performance for prediction of COVID-19 disease, the dataset used is completely linear; hence Support vector Regression and Linear regression (LR) are perfectly analyzing and predicting the situations in early times. This leads to the eventual spread of coronavirus disease (COVID-19) to some extent. In the first scenario of COVID-19, we use imaging procedures as X-rays for the chest to know how this disease has damaged the lungs. This makes doctors understand the criticalness grading of COVID-19. This is to employ radiological imaging to emphasize the results of chest X-rays. According to new research, COVID-19 has been discovered in patients with aberrant chest X-ray results. There is a slew of reports on the subject that employ ML techniques such as support vector machine (SVM), LR, etc. Results obtained from SVM and LR are compared with Support Vector Regression for different categories like affected cases. Death cases and recovered cases. While detecting and predicting coronavirus disease, the accuracy achieved is 97.8% using chest X-rays. Machine learning (ML) might be used to track the disease, predict its progress, and design tactics and legislation to control it. Predictive analysis has become a critical component for future prediction as the science of ML has progressed. COVID-19 is a highly contagious virus that causes severe chronic respiratory infections. ML algorithms aid in the discovery of epidemic tendencies in the context of massive epidemic data, allowing for early intervention to prevent the virus from spreading. Doctors in developing countries would benefit greatly from a model that can diagnose COVID-19 infection from chest radiography images. Positive cases are prioritized, quantified, and tracked. Although this approach does not entirely replace current testing techniques, it can help to minimize the number of situations that require immediate testing or additional expert assessment.