Hybrid Bayesian Network in Neural Network based Deep Learning Framework for Detection of Obstructive Sleep Apnea Syndrome
Farah Nadiah Binti Mohamed Farouk1, Toni Anwar2, Nordin bin Zakaria3
1Farah Nadiah binti Mohamed Farouk, Department of Computer & Sciences, University Techonology PETRONAS, Tronoh, Perak, Malaysia.
2Dr. Toni Anwar, Department of Computer & Sciences, University Techonology PETRONAS, Tronoh, Perak, Malaysia.
3Dr. M Nordin bin Zakaria, Department of Computer & Sciences, University Techonology PETRONAS, Tronoh, Perak, Malaysia.
Manuscript received on September 23, 2019. | Revised Manuscript received on October 15, 2019. | Manuscript published on October 30, 2019. | PP: 4922-4926 | Volume-9 Issue-1, October 2019 | Retrieval Number: A2077109119/2019©BEIESP | DOI: 10.35940/ijeat.A2077.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This study aimed to develop Bayesian Network model integrated with Deep Learning to help doctors diagnose Obstructive Sleep Apnoea Syndrome (OSAS) more holistically and clearly. The results of this research will produce a useful and beneficial clinical workflow for future support in health care. The model will be developed based on the methods of analysis and the quantitative data used to compromise the developing of Hybrid Bayesian Network in Neural Network using Deep Learning Algorithm. The aim of this study was to apply a hybrid model of convolutional neural network (CNN) that could be used during sleep consultation to determine the need for electrocardiography (ECG) signals stimuli for Polysomnography (PSG).
Keywords: Convolution neural network (CNN), Obstructive sleep apnoea syndrome (OSAS), Polysomnography (PSG), Electrocardiography (ECG)