2022
DOI: 10.18280/ts.390509
|View full text |Cite
|
Sign up to set email alerts
|

Dealing with Imbalanced Sleep Apnea Data Using DCGAN

Abstract: Data in the health sector are often lacking and unbalanced. It is because collecting data takes time and many resources. One example is sleep apnea data which takes about 8–10 hours to get data and uses specialized hardware like polysomnography (PSG). This study proposes a data augmentation technique to handle unbalanced data using DCGAN and several deep learning models such as 1D-CNN, ANN, LSTM, and 1D-CNN+LSTM as a classifier for apnea detection. The DCGAN architecture used is CNN on the generator and discri… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 27 publications
0
2
0
Order By: Relevance
“…Moreover, recent advancements in biometricbased human identification show great promise for accurate recognition based on ECG data [20,21]. In addition, ECG analysis can also be utilized for detecting emotions and stress [22], pain [23], sleep-apnea [24,25], identification of COVID-19 infections [26][27][28][29], assessment of signal quality [30,31], and many other potential applications. In this study, we considered all applications as long as they investigated on DA of ECG via AI techniques.…”
Section: Typical Ecg Applicationsmentioning
confidence: 99%
See 1 more Smart Citation
“…Moreover, recent advancements in biometricbased human identification show great promise for accurate recognition based on ECG data [20,21]. In addition, ECG analysis can also be utilized for detecting emotions and stress [22], pain [23], sleep-apnea [24,25], identification of COVID-19 infections [26][27][28][29], assessment of signal quality [30,31], and many other potential applications. In this study, we considered all applications as long as they investigated on DA of ECG via AI techniques.…”
Section: Typical Ecg Applicationsmentioning
confidence: 99%
“…In the context of ECG DA, the authors of [15,17,18,24,94,100,105,[107][108][109][110][111][112][114][115][116][117][118][119]122,123,126] used GAN to augment the samples of the minor classes of the MIT-BIH AD. The augmented samples were then fed to a DL model for ECG beat classification, which demonstrated a notable improvement ranging from 0.24-32% compared to the unaugmented samples.…”
Section: Deep Generative Modelsmentioning
confidence: 99%