A Holistic Approach to Identify and Classify COVID-19 from Chest Radiographs, ECG, and CT-Scan Images Using ShuffleNet Convolutional Neural Network

Keyphrases

• Computed Tomography 100%
• COVID-19 100%
• Convolutional Neural Network 100%
• Scanned Image 100%
• ShuffleNet 100%
• Chest Radiograph 100%
• COVID-19 Detection 57%
• Class Classification 57%
• Classification Performance 42%
• Granularity Level 28%
• Three-class 28%
• Optimal Accuracy 28%
• Classification Scheme 28%
• Early Discovery 14%
• COVID-19 Spread 14%
• Abnormal Pattern 14%
• Chest X-ray Radiographs 14%
• Virus 14%
• COVID-19 Patients 14%
• Radiograph 14%
• AlexNet 14%
• Contemporary Methods 14%
• Classification Approach 14%
• Image Data 14%
• Radiography 14%
• SqueezeNet 14%
• COVID Positive 14%
• Deep Learning Methods 14%
• One Data 14%
• Deep Learning Framework 14%
• Contemporary Models 14%
• Prediction Rate 14%
• Detection Method 14%
• COVID-19 Analysis 14%
• COVID-19 Positive 14%
• COVID-19 Identification 14%
• COVID-19 Classification 14%
• Binary Classification 14%
• COVID-19 Severity 14%
• Medical Imaging Techniques 14%
• Three-class Classification 14%
• Darknet-19 14%

Computer Science

• Class Classification 100%
• Convolutional Neural Network 100%
• Deep Learning Method 40%
• Data Type 40%
• Granularity 40%
• Classification Scheme 40%
• Average Accuracy 40%
• Learning Framework 20%
• classification approach 20%
• Medical Imaging 20%
• Binary Classification 20%
• Learning Approach 20%