Snoring and apnea detection based on hybrid neural networks

Kang, Bingbing; Dang, Xin; Wei, Ran

doi:10.1109/icot.2017.8336088

Cited by 15 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The samples also were annotated into snore & non-snore events, and were divided into training (11), validation (3), and test (6) sets. Authors in [12] used Olympus Noise canceling Microphone (ME52) hung at a height within 20-30cm above 24 volunteer's head to record throughout the night. The samples consist of three events: snore, apnea, and silence.…”

Section: Snore Data Created Through Subjectsmentioning

confidence: 99%

“…The approach was very effective and yielded an excellent result. Approach in [12] applied a linear prediction coding (LPC), MFCC and sub-band for feature extraction along with hybrids of deep neural networks (DNN + LSTM; CNN + LSTM) to classify snoring, apnea and, silence event. However, the classification accuracy for both hybrids were less than 90%.…”

Section: A Brief Survey Of Existing Related Workmentioning

confidence: 99%

“…Aside polysomnography which has high financial cost implication [12], other several approaches [3,7], [13][14][15][16][17][18][19][20][21][22] has been proposed in literatures to detect, diagnose and remedy early snoring stage before getting to an unhealthy phase. Lately, methods in the field of signal processing and AI seems to be the promising area to detect snoring and apnea event.…”

Section: Introductionmentioning

confidence: 99%

“…Lately, methods in the field of signal processing and AI seems to be the promising area to detect snoring and apnea event. These approaches majorly include: support vector machine (SVM) [10,16], recurrent neural network (RNN) [3,22], convolutional neural network (CNN) [17], electromechanical film transducer (Emfit) signal [18], pulse transition time (PTT) [19], acoustic signal processing with KNN [20], deep neural network [13], and hybrid methods [12,20,22]. Several of these methods made use of publicly available snoring data or personally aggregated snoring dataset.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Brief on Snoring Data and Classification Methods

Adesuyi¹

2020

IJATCSE

View full text Add to dashboard Cite

Recently, research on snoring sound had gained interest especially in the area of classification in Obstructive Sleep Apnea (OSA) and distinction from non-snoring sounds. Classifiers such as Support Vector Machine (SVM), Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) had been used to meet this interest. These approaches relies on several underlying techniques such as Mel Frequency Cepstral Coefficients (MFCC), Short-Time Fourier transform (STFT) and several others to extract features from snore/apnea Spectrogram images before classification process. However, achieving desirable classification accuracy depends on choice of classifier, feature extraction techniques and, available dataset. In the paper, we presented a brief survey on existing methods and snore data acquisition processes to quickly expose and ease new researches in this domain to make appropriate choice from available methods.

show abstract

Section: Snore Data Created Through Subjectsmentioning

confidence: 99%

Section: A Brief Survey Of Existing Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Brief on Snoring Data and Classification Methods

Adesuyi¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…An investigation of the developed systems that attempt to diagnose apnea syndrome reveals the dominance of neural networks in this field of sound classification [7]. Mainly depending on convolutional deep networks, the proposed systems classify the tracheal sound excerpts by revealing deep features in the spectrotemporal changes of the sound signal [8].…”

Section: Introductionmentioning

confidence: 99%

Breathing sound detector as a means to identify possible apneic periods from tracheal sound recordings

Potirakis

Korompili

Kokkalas

et al. 2020

Proceedings of 1st International Electronic Conference on Applied Sciences

View full text Add to dashboard Cite

Tracheal sound represents an easily acquired signal, particularly popular in the evolution of smartphone-based systems for Sleep Apnea Syndrome diagnosis. The syndrome is characterized by partial or complete breath cessation for at least 10 s. The developed algorithms mainly rely on neural networks focusing on the extraction of the apneic episodes' count per sleeping hour, defined as the Apnea/Hypopnea Index. Though reported highly accurate, neural networks may be severely affected by the inter-and intra-patient breathing sound variability. Alternatively, breathing detection algorithms can contribute in identifying the dominant sound patterns within the apnea events. In this work, we employ zero-crossing rate, signal power, Tsallis entropy and Shannon information to discriminate breathing from silent frames. These features are extracted independently by tracheal sound recordings from 178 patients undergoing a hospital sleep study. Apneas correspond to silent periods detected by at least one of the four features, while hypopneas correspond to periods of reduced signal power. The algorithm presents increased sensitivity (80.45%) in identifying apnea/hypopnea events (32,824 out of 40,800). Despite the non-negligible number of false positive detections, the proposed algorithm proves the dominance of the described sound pattern during apnea/hypopnea episodes.

show abstract

Design of embedded real-time system for snoring and OSA detection based on machine learning

Luo

et al. 2023

Measurement

View full text Add to dashboard Cite

Snoring and apnea detection based on hybrid neural networks

Cited by 15 publications

References 5 publications

A Brief on Snoring Data and Classification Methods

A Brief on Snoring Data and Classification Methods

Breathing sound detector as a means to identify possible apneic periods from tracheal sound recordings

Design of embedded real-time system for snoring and OSA detection based on machine learning

Contact Info

Product

Resources

About