Title :
K9. Detection of Sleep Apnea Events using analysis of thoraco-abdominal excursion signals and adaptive neuro-fuzzy inference system (ANFIS)
Author :
Abdel-Mageed, Fatma Z. ; Chadi, Fatma E Z Abou ; Salah, Hosam M. ; Loza, Shahira F.
Author_Institution :
Facualty of Eng., Mansoura Univ., Mansoura, Egypt
Abstract :
This paper describes an adaptive neuro-fuzzy inference system (ANFIS) for detection of Sleep Apnea Events using Thoracic and Abdominal Excursion signals. Mean amplitude sum analysis, and phase angle difference analysis using both Piecewise Linear Approximation (PLA) and phase difference measurements have been used to classify Normal, Obstructive Sleep Apnea (OSA), Hypopnea and Central Apnea events. A hybrid learning algorithm using a combination of Steepest Descent and Least Squares Estimation (LSE) was used to identify the parameters of ANFIS. The performance of ANFIS was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in classifying the Sleep Apnea events with an accuracy level of more than 95%.
Keywords :
fuzzy reasoning; gradient methods; least squares approximations; medical signal detection; neural nets; parameter estimation; signal classification; sleep; ANFIS; LSE; OSA; PLA; adaptive neuro-fuzzy inference system; central apnea events; hybrid learning algorithm; hypopnea; least squares estimation; mean amplitude sum analysis; normal obstructive sleep apnea classification; parameter identification; phase angle difference analysis; phase difference measurements; piecewise linear approximation; sleep apnea event detection; steepest descent estimation; thoraco-abdominal excursion signal analysis; Adaptive systems; Educational institutions; Least squares approximation; Piecewise linear approximation; Programmable logic arrays; Sleep apnea;
Conference_Titel :
Radio Science Conference (NRSC), 2012 29th National
Conference_Location :
Cairo
Print_ISBN :
978-1-4673-1884-6
DOI :
10.1109/NRSC.2012.6208584