2022
DOI: 10.1016/j.bspc.2021.103333
|View full text |Cite
|
Sign up to set email alerts
|

Covid-19 recognition from cough sounds using lightweight separable-quadratic convolutional network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
13
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2

Relationship

0
6

Authors

Journals

citations
Cited by 15 publications
(13 citation statements)
references
References 30 publications
0
13
0
Order By: Relevance
“…For the evaluation and validation of the performances of the models, a few strategies have been established. As a baseline, Soltanian and Borna [ 28 ] used classical machine learning (SVM, random forest, KNN), Coppock et al [ 29 ] used a classical SVM binary classifier without pre-processing, and Andreu-Perez et al [ 30 ] applied Auto-ML. Meanwhile, Chaudhari et al [ 31 ] presented a multi-branch ensemble architecture of ResNet-50, a simple feedforward network, and DNN against the ResNet-50 model performance.…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…For the evaluation and validation of the performances of the models, a few strategies have been established. As a baseline, Soltanian and Borna [ 28 ] used classical machine learning (SVM, random forest, KNN), Coppock et al [ 29 ] used a classical SVM binary classifier without pre-processing, and Andreu-Perez et al [ 30 ] applied Auto-ML. Meanwhile, Chaudhari et al [ 31 ] presented a multi-branch ensemble architecture of ResNet-50, a simple feedforward network, and DNN against the ResNet-50 model performance.…”
Section: Resultsmentioning
confidence: 99%
“…Meanwhile, Chaudhari et al [ 31 ] presented a multi-branch ensemble architecture of ResNet-50, a simple feedforward network, and DNN against the ResNet-50 model performance. Soltanian and Borna [ 28 ] showed that quadratic-based CNNs could provide higher accuracy when compared to “ordinary” CNN. Often, studies used their models to compete against the existing ones in the literature [ 26 , 32 ].…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…A contrastive pre-training phase was used to train a transformer-based feature encoder with unlabeled data. In deep neural networks, Soltanian et al [46] employed a mix of quadratic kernels and the notion of separable kernels to improve recognition accuracy concurrently.…”
Section: Discussionmentioning
confidence: 99%
“…Authors obtained 83.15% and 83.74% accuracy scores for VGGish and Transformer-CP classifiers, respectively. Soltanian et al [46] used MFCC images with ordinary CNN and a novel CNN model to detect COVID-19 on the VIRUFY dataset.…”
Section: Discussionmentioning
confidence: 99%