TY - JOUR
T1 - Energy Efficient Deep Learning Inference Embedded on FPGA for Sleep Apnea Detection
AU - Hassan, Omiya
N1 - Sleep apnea is a type of disorder caused by the absence of breathing for a specific period of time coupled with a significant decrease in the blood oxygen saturation level. The monitoring process of sleep apnea is challenging due to the requirement of overnight expensive sleep study, hand-crafted feature extraction from breathing signals, and manual annotations by the sleep experts.
Hassan, Omiya; Paul, Tanmoy; Shuvo, Md Maruf Hossain; Parvin, Dilruba; Thakker, Rushil; Chen, Mengrui; . . . and Islam, Syed Kamrul. (2022). "Energy Efficient Deep Learning Inference Embedded on FPGA for Sleep Apnea Detection". Journal of Signal Processing Systems, 94, 609-619. https://doi.org/10.1007/s11265-021-01722-7
PY - 2022/6
Y1 - 2022/6
N2 - Sleep apnea is a type of disorder caused by the absence of breathing for a specific period of time coupled with a significant decrease in the blood oxygen saturation level. The monitoring process of sleep apnea is challenging due to the requirement of overnight expensive sleep study, hand-crafted feature extraction from breathing signals, and manual annotations by the sleep experts. Therefore, a low-cost, energy-efficient, portable, and automated biomedical system is necessary to improve early detection, frequent monitoring, and clinical decision-making. In this paper, a digital hardware design of a trained deep feedforward neural network (FNN) is implemented on a Field Programmable Gate-Array (FPGA) for the detection of sleep apnea. The model was trained and evaluated with hyperparameters obtained from a three-step optimization process which ensures compact design solution in low-power miniaturized CMOS circuits. A three-layer FNN trained with ADAM optimizer and mean square error (MSE) loss minimization shows an accuracy of around 88%. An application-specific deep learning inference module realized in FPGA hardware platform confirms a power consumption below 34 W which is 5 × lower than that of commercially available machine learning accelerators. The outcome of this research can be integrated into a system-on-a-chip (SoC) platform for developing a smart automated sleep apnea detection device.
AB - Sleep apnea is a type of disorder caused by the absence of breathing for a specific period of time coupled with a significant decrease in the blood oxygen saturation level. The monitoring process of sleep apnea is challenging due to the requirement of overnight expensive sleep study, hand-crafted feature extraction from breathing signals, and manual annotations by the sleep experts. Therefore, a low-cost, energy-efficient, portable, and automated biomedical system is necessary to improve early detection, frequent monitoring, and clinical decision-making. In this paper, a digital hardware design of a trained deep feedforward neural network (FNN) is implemented on a Field Programmable Gate-Array (FPGA) for the detection of sleep apnea. The model was trained and evaluated with hyperparameters obtained from a three-step optimization process which ensures compact design solution in low-power miniaturized CMOS circuits. A three-layer FNN trained with ADAM optimizer and mean square error (MSE) loss minimization shows an accuracy of around 88%. An application-specific deep learning inference module realized in FPGA hardware platform confirms a power consumption below 34 W which is 5 × lower than that of commercially available machine learning accelerators. The outcome of this research can be integrated into a system-on-a-chip (SoC) platform for developing a smart automated sleep apnea detection device.
KW - ECG
KW - FPGA
KW - deep learning
KW - feedforward neural network
KW - oxygen saturation
KW - sleep apnea
UR - https://doi.org/10.1007/s11265-021-01722-7
U2 - 10.1007/s11265-021-01722-7
DO - 10.1007/s11265-021-01722-7
M3 - Article
VL - 94
JO - Journal of Signal Processing Systems
JF - Journal of Signal Processing Systems
IS - 6
ER -