|
ИСТИНА |
Войти в систему Регистрация |
ИПМех РАН |
||
Selection of Wavelet Transform and Neural Network Parameters for Classification of Breathing Patterns of Bio-radiolocation Signalsстатья
- Авторы: Alekhin M.D., Anishchenko L.N., Tataraidze A.B., Ivashov S.I., Korostovtseva L.S., Sviryaev Y.V., Bogomolov A.V.
- Сборник: Proceedings of The First International Aizu Conference on Biomedical Informatics and Technology (ACBIT 2013)
- Серия: Communications in Computer and Information Science
- Том: 404
- Год издания: 2014
- Издательство: SPRINGER-VERLAG BERLIN
- Местоположение издательства: HEIDELBERGER PLATZ 3, BERLIN, GERMANY,D-14197
- DOI: 10.1007/978-3-642-54121-6_15
- Аннотация: A novel method for classification of breathing patterns of bio-radiolocation signals breathing patterns (BSBP) in the task of non-contact screening of sleep apnea syndrome (SAS) is proposed, implemented on the base of wavelet transform (WT) and neural network (NNW) application with automated selection of their optimal parameters. The effectiveness of the proposed approach is tested on clinically verified database of BRL signals corresponding to the three classes of breathing patterns: obstructive sleep apnea (OSA); central sleep apnea (CSA); normal calm sleeping (NCS) without sleep- disordered breathing (SDB) episodes.
- Добавил в систему: Алёхин Максим Дмитриевич