2021
DOI: 10.1016/j.compbiomed.2021.104532
|View full text |Cite
|
Sign up to set email alerts
|

SCNN: Scalogram-based convolutional neural network to detect obstructive sleep apnea using single-lead electrocardiogram signals

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
31
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2

Relationship

2
7

Authors

Journals

citations
Cited by 60 publications
(31 citation statements)
references
References 35 publications
0
31
0
Order By: Relevance
“…The type of classification system used in a BCI system is mostly determined by the application's nature and location. With the recent application of deep learning (DL) in different domain (Mashrur et al, 2019 , 2021a ; Nazi et al, 2021 ), Teo et al ( 2017 ) showed the subjects 3D virtual jewelry objects, asked to rate them on a Likert scale, and then categorized EEG signals using deep learning. Again, Aldayel et al ( 2020 ) emphasized the need of spectral valence features to improve prediction accuracy and the merging of classifiers using deep learning to extract features.…”
Section: Introductionmentioning
confidence: 99%
“…The type of classification system used in a BCI system is mostly determined by the application's nature and location. With the recent application of deep learning (DL) in different domain (Mashrur et al, 2019 , 2021a ; Nazi et al, 2021 ), Teo et al ( 2017 ) showed the subjects 3D virtual jewelry objects, asked to rate them on a Likert scale, and then categorized EEG signals using deep learning. Again, Aldayel et al ( 2020 ) emphasized the need of spectral valence features to improve prediction accuracy and the merging of classifiers using deep learning to extract features.…”
Section: Introductionmentioning
confidence: 99%
“…It is divided into a method of diagnosing apnea using electrical biosignals obtained through PSG and a method of diagnosing apnea using ECG obtained via PSG. A scalogram-based convolutional neural network was introduced to detect sleep apnea using single-lead ECG signals [21]. In the work by Shen et al [13], the detection of sleep apnea employs a multiscale, dilated-attention, one-dimensional convolutional neural network and a weighted-loss time-dependent classification model.…”
Section: Related Researchmentioning
confidence: 99%
“…In their work, they've applied a windowing strategy, with window sizes of 500, 1000, 1500, 2000 and 2500 for validation of their model, which achieved 93.77% accuracy for window size of 500 on the PhysioNet Apnea-ECG database [12]. Mashrur et al [28] have proposed a novel Scalogram-based CNN to detect OSA using ECG signals. In their work, they've obtained hybrid scalograms from the ECG signals using continuous wavelet transform (CWT) and empirical mode decomposition (EMD).…”
Section: Related Workmentioning
confidence: 99%