Wyniki wyszukiwania - BazTech

1

Constant Q-transform-based deep learning architecture for detection of obstructive sleep apnea

Kandukuri Usha Rani, Prakash Allam Jaya, Patro Kiran Kumar, Neelapu Bala Chakravarthy, Tadeusiewicz Ryszard, Pławiak Paweł

International Journal of Applied Mathematics and Computer Science

|

2023

|

Vol. 33, no. 3

493--506

EN

Obstructive sleep apnea (OSA) is a long-term sleep disorder that causes temporary disruption in breathing while sleeping. Polysomnography (PSG) is the technique for monitoring different signals during the patient’s sleep cycle, including electroencephalogram (EEG), electromyography (EMG), electrocardiogram (ECG), and oxygen saturation (SpO2). Due to the high cost and inconvenience of polysomnography, the usefulness of ECG signals in detecting OSA is explored in this work, which proposes a two-dimensional convolutional neural network (2D-CNN) model for detecting OSA using ECG signals. A publicly available apnea ECG database from PhysioNet is used for experimentation. Further, a constant Q-transform (CQT) is applied for segmentation, filtering, and conversion of ECG beats into images. The proposed CNN model demonstrates an average accuracy, sensitivity and specificity of 91.34%, 90.68% and 90.70%, respectively. The findings obtained using the proposed approach are comparable to those of many other existing methods for automatic detection of OSA.

2

Projekt systemu monitorowania obturacyjnego bezdechu sennnego

Szyszkowski Przemysław, Śmigielski Grzegorz

Studia i Materiały Informatyki Stosowanej

|

2019

|

nr 2

11--14

PL

W artykule przedstawiono prototyp urządzenia, opartego o mikrokontroler AVR, służącego do monitorowania obturacyjnego bezdechu sennego.

EN

Article presents prototype of device based on microcontroller AVR , which serves as an obstructive sleep apnea monitor.

3

Teaching Machines on Snoring : A Benchmark on Computer Audition for Snore Sound Excitation Localisation

Qian K., Janott C., Zhang Z., Deng J., Baird A., Heiser C., Hohenhorst W., Herzog M., Hemmert W., Schuller B.

Archives of Acoustics

|

2018

|

Vol. 43, No. 3

465--475

EN

This paper proposes a comprehensive study on machine listening for localisation of snore sound excitation. Here we investigate the effects of varied frame sizes, and overlap of the analysed audio chunk for extracting low-level descriptors. In addition, we explore the performance of each kind of feature when it is fed into varied classifier models, including support vector machines, k-nearest neighbours, linear discriminant analysis, random forests, extreme learning machines, kernel-based extreme learning machines, multilayer perceptrons, and deep neural networks. Experimental results demonstrate that, wavelet packet transform energy can outperform most other features. A deep neural network trained with subband Energy ratios reaches the highest performance achieving an unweighted average recall of 72.8% from four types for snoring.

4

Lung volumes, airflow limitations, and the level of arterial oxygen saturation during sleep in obstructive sleep apnea patients

Brzecka A., Piesiak P., Kosacka M., Jankowska R.

Biocybernetics and Biomedical Engineering

|

2006

|

Vol. 26, no. 2

39-51

EN

The aim of the study was to find out whether the level of arterial oxygen saturation (Sa02) during sleep in obstructive sleep apnea (OSA) patients can be predicted on the basis of the static or dynamic lung volumes measurements or respiratory resistance measurements performed during wakefulness in the sitting and supine positions. Nineteen OSA patients were divided into 2 groups depending on the high and low Sa02 during sleep apneas (85:3% vs 78:9%). In the patients with the high Sa02 there was a bigger vital capacity (both in the sitting and supine positions), a lower residual volume/ total lung capacity ratio in the supine position and a smaller decrease of the expiratory reserve volume on adopting the supine posture, a higher mid-expiratory-flow, both in the sitting and supine positions, and a higher peak-expiratory-flow in the supine position as compared with patients with the low Sa02 during sleep apneas. The respiratory resistance and forced-expiratory-volume 1sec/vital capacity ratio were similar in both groups. Conclusion: the measurements of the lung volumes and capacities in the both the sitting and supine position allow predicting the level of the arterial oxygen desaturation during the episodes of sleep apnea in the OSA patients. Small-airways disease (that can be detected in the sitting and especially, in the supine position) leads to a more severe arterial oxygen desaturation during sleep in the OSA patients. The respiratory resistance does not influence the arterial oxygen desaturation in the OSA patients.

5

Aparaty do terapii obturacyjnego bezdechu sennego

Bańkowski A., Rudnicka A., Zaar C.

Acta Bio-Optica et Informatica Medica. Inżynieria Biomedyczna

|

2006

|

Vol. 12, nr 1

10-10

PL

Leczenie chorych z obturacyjnym bezdechem sennym (OBS) polega na udrożnieniu górnych dróg oddechowych w czasie snu. Można to uzyskać metodami chirurgicznymi lub postępowaniem zachowawczym. Efekty kliniczne leczenia chirurgicznego są często niedostateczne (wynoszą ok. 20%) i dlatego leczeniem z wybru jest postępowanie zachowawcze: odchudzanie, pozycja ciała na boku w czasie snu, unikanie spożywania alkoholu, a przede wszystkim leczenie za pomocą aparatów wytwarzających stałe dodatnie ciśnienie w drogach oddechowych CPAP (Continuous Positive Air Pressure).