• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.155-160
• /
• 2021

This paper proposes an automatic method for detecting snore sound, one of the important symptoms of sleep apnea patients. In the proposed method, sound signals generated during sleep are input to detect a sound generation section, and a spectrogram transformed from the detected sound section is applied to a classifier based on a Convolutional Bidirectional Gated Recurrent Unit (CBGRU) with attention mechanism. The applied attention mechanism improved the snoring sound detection performance by extending the CBGRU model to learn discriminative feature representation for the snoring detection. The experimental results show that the proposed snoring detection method improves the accuracy by approximately 3.1 % ~ 5.5 % than existing method.

• Science of Emotion and Sensibility
• /
• v.14 no.3
• /
• pp.459-466
• /
• 2011

Sleep diseases such as snoring and sleep apnea are physically, mentally harmful and results serious health problems. Snoring, known as breathing noise, is caused by coupled oscillation of the airway when the air passes through the trachea, and sleep apnea is caused by upper airway blockage. In order to solve these problems, many attempts have been made to detect the snoring during sleep and alleviate it. In this study, a new sensing system and analysis algorithm were developed in order to detect snoring sounds correctly under various sleep environments. Two polyvinylidene fluoride (PVDF) vibration sensors were used inside the pillow. The first PVDF sensor detects vibration transmitted through skull caused by snoring. And the second PVDF sensor detects both snoring sounds and ambient noises. The signals of two sensors were acquired through the designed analog circuits, and analyzed for snoring detection. Ten volunteers were participated for the experiment under five different conditions. Data from two PVDF sensors were processed by the established analysis algorithm, and snoring sounds were compared to noises. The results indicated that the energy of snoring is 70% bigger than that of ambient noise, which proves effectiveness of sensing system and analysis algorithm. Further study would be continued for more wide clinical studies with various environment noises. Based on this study, development of anti-snore pillow and sleep monitoring system for comfort sleep could be developed.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.2
• /
• pp.105-110
• /
• 2019

People sleep about one-third of their lives and their sleep time varies according to age. Adult usually sleep 8 hours a day. However, that dose not guarantee good sleep. The cause of this is due to sleep disorders like snoring and sleep apnea. In this paper, the smart pillow for detecting snoring among sleep disorders is investigated. This pillow consists of two microphones located on the left and right side of the pillow. For simple detecting, the snoring signal was converted into the pulse using a peak detection circuit. The decision of the snoring occurrence was by pulse duration. The accuracy of the snoring detection was about 97%. The research results show that the smart pillow can be use to detect the snoring during sleeping.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.05a
• /
• pp.35-36
• /
• 2011

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.212-217
• /
• 2019

In this paper, a sleep management pillow system for snoring detection and respiration measurement is investigated. The sleep management pillow system consists of four force sensing resistor(FSR) sensors, two microphones(MIC), a pillow, a measurement system. Four FSR sensors attached at the bottom part of the pillow are used for respiration measurement and snoring detection. Two microphones located at the middle left and right of the pillow are utilized for only snoring detection. The respiration and the snoring of ten young people were measured using the sleep management pillow system composed of a data acquisition board, interface circuit, and personal computer. The measurement accuracy of the respiration was about 98% and the measurement accuracy of the snoring was about 97%. The experiment results show that the sleep management pillow system can be used for snoring detection and respiration rate measurement during sleeping.

• Science of Emotion and Sensibility
• /
• v.14 no.4
• /
• pp.545-554
• /
• 2011

In this study, the parameters of Polysomnography (PSG) test, such as total sleep time, snoring time, had been analyzed to evaluate the effectiveness of a developed anti-snore pillow. The developed anti-snore pillow is made up of two polyvinylidene fluoride (PVDF) vibration sensors, pumps, valves, and air bladders. The two PVDF sensors inside the pillow can acquire the sound signals and the algorithm was perfectly designed to extract snoring by removing unwanted noise accurately and automatically. Once the pillow recognizes snore, a pump inside the hardware activates, and a bladder under the neck area inside the pillow will be inflated. The PSG test was used and two volunteers were participated for the study. The parameters of the PSG results were analyzed to evaluate the effectiveness of the anti-snore pillow. The total sleep time of each volunteer was similar on each phase of test, but the snoring time and the longest snoring episode were significantly decreased with the use of anti-snore pillow. The overall results showed excellent possibilities for reducing snoring for the person who snores during sleep by using the anti-snore pillow. The effectiveness of the anti-snore pillow can be evaluated by the PSG test. Moreover, the relationship between each parameter of PSG test and the quality of sleep will be used for further researches.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1423-1424
• /
• 2015

본 연구는 IoT 환경에서 수면 중 비정상호흡 모니터링을 위한 모듈개발 사전연구로, 베개 안에 삽입할 수 있는 가속도, 진동 측정 모듈을 제작하고, 측정된 신호를 기반으로 수면 중 발생하는 호흡활동을 관찰하는 것을 목적으로 한다. 이를 위하여 압전센서 및 3축 가속도 센서를 내장한 진동, 가속도 측정 모듈 프로토타입을 설계 및 제작하였으며, 파일럿 실험을 통하여 개발된 모듈의 동작을 확인하였다. 실험 결과 가속도 및 압전센서에서 획득된 신호에서 호흡성분이 검출되는 것을 확인하였으나, 샘플링율, 센서 민감도 설정에 따라 코골이 성분은 검출되지 않았다.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.7
• /
• pp.327-333
• /
• 2002

In this study, we developed a snoring detection algorithm that detects snores automatically. It consists of preprocessing and snoring detection part. The preprocessing part is composed of a noise removal part using spectrum subtraction, and segmentation part, and computation part of temporal and spectral features. And the snoring detection part decides whether detected blocks are snores with BPNN(Back-Propagation Neural Network). BPNN with one hidden layer and one output layer, is trained with data of 7 subjects and tested with data of 11 subjects of total 18 subjects. The proposed algorithm showed a Sensitivity of 90.41% and a Predictive Positive Value of 84.95%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.243-245
• /
• 2012

대표적인 수면장애로 수면 무호흡증과 코골이가 있는데 수면다원검사를 통해 진단할 수 있다. 그러나 수면다원검사는 비용적, 공간적, 시간적 제약이 수반되기 때문에 이를 해결하려는 연구가 대두되고 있다. 수면장애와 그 요인을 검출하기 위해 가속도센서, 소음센서, 온도센서, 습도센서로 구성된 측정 장치에서 획득한 데이터와 건강, 운동, 생활습관 데이터를 활용하여 어떤 요인에 의해 수면장애의 정도가 악화되고 개선되는지를 사용자에게 제공하는 의사결정 지원시스템을 설계한다. 또한 홈 게이트웨이와 뷰어 역할에 스마트 폰을 사용하여 일반인이 보다 쉽게 측정하고 측정결과와 추론결과를 지속적으로 확인할 수 있는 시스템을 제안한다.

• Journal of Biomedical Engineering Research
• /
• v.36 no.5
• /
• pp.143-149
• /
• 2015

In this paper, we proposed a novel method for automatic detection for snoring and heart beat using a single piezoelectric sensor. For this study multi-rate signal processing technique was applied to detect snoring and heart beat from the single source signal. The sound event duration and intensity features were used to snore detection and heart beat was found by autocorrelation. The performance of the proposed method was evaluated on clinical database, which is the nocturnal piezoelectric snoring data of 30 patients that suffered obstructive sleep apnea. The method achieved sensitivity of 88.6%, specificity of 96.1% with accuracy of 95.6% for snoring and sensitivity of 94.1% and positive predictive value of 87.6% for heart beat, respectively. These results suggest that the proposed method can be a useful tool in sleep monitoring and sleep disordered breathing diagnosis.