Towards an international standard for snore-based obstructive sleep apnea syndrome diagnosis

2015 Fiscal Year Final Research Report

• Project/Area Number: 24700498
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Medical systems
• Research Institution: The University of Tokushima
• Principal Investigator: Emoto Takahiro 徳島大学, ソシオテクノサイエンス研究部, 講師 (90418989)
• Project Period (FY): 2012-04-01 – 2016-03-31
• Keywords: 閉塞型睡眠時無呼吸症候群 / いびき / 呼吸音 / 非接触 / 高速化 / モデル

Outline of Final Research Achievements

Towards an international standard for snore-based system for the diagnosis of obstructive sleep apnea syndrome (OSAS), we have developed the following five methods:(1)neural newtork(NN)-based breathing sound detection method which can accurately detect breathing sounds in a sleep sound recording, (2) automatic method to classify snore and breathing sounds using the feature:‘positive/ negative amplitude ratio (PNAR)’to capture the shape of the sound signal, (3)NN-based fundamental approach which is capable of rapidly detecting breathing sounds with low signal to noise ratio (SNR) with the same accuracy as the conventional method, (4)a basic approach to classify the sleep sound into two categories using a model considering human auditory properties, (5)a fundamental approach to model the basic hearing abilities of absolute pitch possessors.

Free Research Field

生体医工学