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

Soltanian, M. R. K.; Borna, Keivan

doi:10.1016/j.bspc.2021.103333

Cited by 15 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

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%

“…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%

“…Dataset size also can be the cause of data being too “similar,” meaning that data samples are similar to one another, which also induces a lack of real-world representativeness. It is, for example, the case in Mohammad and Borna [ 28 ] who, to overcome this problem, use repeated random split and cross-validation on the Virufy dataset (of 121 samples).…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review

2022

View full text Add to dashboard Cite

In the past two years, medical researchers and data scientists worldwide have focused their efforts on containing the pandemic of coronavirus disease 2019 (COVID-19). Deep learning models have been proven to be capable of efficient medical diagnosis and prognosis in cancer, common lung diseases, and COVID-19. On the other hand, artificial neural networks have demonstrated their potential in pattern recognition and classification in various domains, including healthcare. This literature review aims to report the state of research on developing neural network models to diagnose COVID-19 from cough sounds to create a cost-efficient and accessible testing tool in the fight against the pandemic. A total of 35 papers were included in this review following a screening of the 161 outputs of the literature search. We extracted information from articles on data resources, model structures, and evaluation metrics and then explored the scope of experimental studies and methodologies and analyzed their outcomes and limitations. We found that cough is a biomarker, and its associated information can determine an individual’s health status. Convolutional neural networks were predominantly used, suggesting they are particularly suitable for feature extraction and classification. The reported accuracy values ranged from 73.1% to 98.5%. Moreover, the dataset sizes ranged from 16 to over 30,000 cough audio samples. Although deep learning is a promising prospect in identifying COVID-19, we identified a gap in the literature on research conducted over large and diversified data sets.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review

2022

View full text Add to dashboard Cite

show abstract

“…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%

Explainable COVID-19 detection using fractal dimension and vision transformer with Grad-CAM on cough sounds

Sobahi¹,

Atila²,

Deniz³

et al. 2022

Biocybernetics and Biomedical Engineering

View full text Add to dashboard Cite

The Role of Artificial Intelligence and Machine Learning for the Fight Against COVID-19

Iglesias,

Gálvez,

Suárez

2023

Springer Optimization and Its Applications

View full text Add to dashboard Cite

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

Cited by 15 publications

References 30 publications

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review

Explainable COVID-19 detection using fractal dimension and vision transformer with Grad-CAM on cough sounds

The Role of Artificial Intelligence and Machine Learning for the Fight Against COVID-19

Contact Info

Product

Resources

About