| [86] |
COVID-19 |
Deep Transfer Learning-based Binary Class classifier (DTL-BC) |
X-rays and CT scans of alive COVID-19 patients, cough sound |
1838 Cough sounds and 3597 non-coughs |
91.14% |
94.57% |
92.97% |
92.85% |
| [3] |
COVID-19 |
Cross-correlation adaptive algorithm |
Cough sound and the movement during cough recording |
10000 Coughs |
– |
– |
– |
– |
| [55] |
SARS and COVID-19 |
RNN |
Cough sound |
5971 Coughs |
– |
– |
– |
78% |
| [78] |
COVID-19 |
SVM |
Cough sound |
570 Coughs |
– |
94% |
– |
– |
| [50] |
COVID-19 |
LR, SVM, multilayer perceptron (MLP), CNN, LSTM, and a residual-based neural network architecture (ResNet-50) |
Cough sound, questionnaire |
Sample 1(92 COVID-19 positive and 1079 healthy subjects) Sample 2 (8 COVID-19 positive and 13 COVID-19 negative subjects) |
96% |
91% |
– |
92.91% |
| [51] |
COVID-19 |
DNN |
Cough sound |
30000 audio segments, 328 cough sounds from 150 patients with |
95.04% |
90.1% |
– |
96.83% |
| [35] |
COVID-19 |
CNN |
Cough sound |
5,320 Coughs |
94.2% |
98.5% |
– |
97% |
| [21] |
COVID-19 |
CNN |
Cough sound |
1811 Coughs |
89% |
98% |
70% |
84% |
| [81] |
COVID-19 |
AI |
Cough sound |
3621 coughs |
– |
– |
– |
– |
| [89] |
COVID-19 |
SVM |
Cough sound |
828 samples from 343 participants |
82% |
68% |
– |
– |
