2023
DOI: 10.1016/j.bbe.2023.01.005
|View full text |Cite
|
Sign up to set email alerts
|

SCovNet: A skip connection-based feature union deep learning technique with statistical approach analysis for the detection of COVID-19

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 25 publications
(6 citation statements)
references
References 60 publications
0
6
0
Order By: Relevance
“…Besides this, Patro et al developed a custom SCovNet based on CNN, which achieved the highest accuracy of 97.99% among the other SOTA models. In contrast, the proposed CNN-PCC-ELM achieved a satisfactory accuracy of 99.55%, almost 2% higher than their model [73] . Azam et al had the best precision and recall results out of all the SOTA models, coming in at 99.02% and 98.26%, respectively [79] .…”
Section: Performance Comparison and Discussionmentioning
confidence: 72%
“…Besides this, Patro et al developed a custom SCovNet based on CNN, which achieved the highest accuracy of 97.99% among the other SOTA models. In contrast, the proposed CNN-PCC-ELM achieved a satisfactory accuracy of 99.55%, almost 2% higher than their model [73] . Azam et al had the best precision and recall results out of all the SOTA models, coming in at 99.02% and 98.26%, respectively [79] .…”
Section: Performance Comparison and Discussionmentioning
confidence: 72%
“…A review in [23] indicates that machine learning is robust enough to aid doctors in predicting the likelihood of future type 2 diabetes development. Machine learning (ML) was employed in a study [24] to conduct a comprehensive evaluation of predicting methods for diabetes. The Prediction Model Risk of Bias Assessment Tool (PROBAST) evaluated bias in machine learning models, whereas Meta-DiSc measured variability in a systematic review, demonstrating the greater effectiveness of machine learning compared to traditional methods.…”
Section: Literature Studymentioning
confidence: 99%
“…Deep learning is a rapidly growing subfield of artificial intelligence that has shown a remarkable ability to learn from vast amounts of data and can solve complex problems with high accuracy [3,4]. However, this often requires access to powerful computing resources and significant data storage, making it challenging to deploy deep-learning algorithms in resource-limited environments [5,6].…”
Section: Introductionmentioning
confidence: 99%