TY - GEN
T1 - DeepApnea
T2 - 22nd IEEE International Conference on Pervasive Computing and Communications, PerCom 2024
AU - Liu, Zida
AU - Chen, Xianda
AU - Ma, Fenglong
AU - Fernandez-Mendoza, Julio
AU - Cao, Guohong
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Sleep apnea is a serious sleep disorder where patients have multiple extended pauses in breath during sleep. Although some portable or contactless sleep apnea detection systems have been proposed, none of them can achieve fine-grained sleep apnea detection without strict requirements on the device or environmental settings. To address this problem, we present DeepApnea, a deep learning based sleep apnea detection system that leverages patients' wrist movement data collected by smartwatches to identify different types of sleep apnea events (i.e., central apneas, obstructive apneas, and hypopneas). Through a clinical study, we identify some special characteristics associated with different types of sleep apnea captured by smartwatch. However, there are many technical challenges such as how to extract informative apnea features from the noisy data and how to leverage features extracted from the multi-axis sensing data. To address these challenges, we first propose signal pre-processing methods to filter the raw accelerometer (ACC) data, smoothing away noise while preserving the respiratory signal and potential features for identifying sleep apnea. Then, we design a deep learning architecture to extract features from three ACC axes collaboratively, where self attention and cross-axis correlation techniques are leveraged to improve the classification accuracy. We have implemented DeepApnea on smartwatches and performed a clinical study. Evaluation results demonstrate that DeepApnea can significantly outperform existing work on identifying different types of sleep apnea.
AB - Sleep apnea is a serious sleep disorder where patients have multiple extended pauses in breath during sleep. Although some portable or contactless sleep apnea detection systems have been proposed, none of them can achieve fine-grained sleep apnea detection without strict requirements on the device or environmental settings. To address this problem, we present DeepApnea, a deep learning based sleep apnea detection system that leverages patients' wrist movement data collected by smartwatches to identify different types of sleep apnea events (i.e., central apneas, obstructive apneas, and hypopneas). Through a clinical study, we identify some special characteristics associated with different types of sleep apnea captured by smartwatch. However, there are many technical challenges such as how to extract informative apnea features from the noisy data and how to leverage features extracted from the multi-axis sensing data. To address these challenges, we first propose signal pre-processing methods to filter the raw accelerometer (ACC) data, smoothing away noise while preserving the respiratory signal and potential features for identifying sleep apnea. Then, we design a deep learning architecture to extract features from three ACC axes collaboratively, where self attention and cross-axis correlation techniques are leveraged to improve the classification accuracy. We have implemented DeepApnea on smartwatches and performed a clinical study. Evaluation results demonstrate that DeepApnea can significantly outperform existing work on identifying different types of sleep apnea.
UR - http://www.scopus.com/inward/record.url?scp=85191253772&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85191253772&partnerID=8YFLogxK
U2 - 10.1109/PerCom59722.2024.10494473
DO - 10.1109/PerCom59722.2024.10494473
M3 - Conference contribution
AN - SCOPUS:85191253772
T3 - 2024 IEEE International Conference on Pervasive Computing and Communications, PerCom 2024
SP - 206
EP - 216
BT - 2024 IEEE International Conference on Pervasive Computing and Communications, PerCom 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 March 2024 through 15 March 2024
ER -