A High Accuracy & Ultra-Low Power ECG-Derived Respiration Estimation Processor for Wearable Respiration Monitoring Sensor

Abstract

The respiratory rate is widely used for evaluating a person’s health condition. Compared to other invasive and expensive methods, the ECG-derived respiration estimation is a more comfortable and affordable method to obtain the respiration rate. However, the existing ECG-derived respiration estimation methods suffer from low accuracy or high computational complexity. In this work, a high accuracy and ultra-low power ECG-derived respiration estimation processor has been proposed. Several techniques have been proposed to improve the accuracy and reduce the computational complexity (and thus power consumption), including QRS detection using refractory period refreshing and adaptive threshold EDR estimation. Implemented and fabricated using a 55 nm processing technology, the proposed processor achieves a low EDR estimation error of 0.73 on CEBS database and 1.2 on MIT-BIH Polysomnographic Database while demonstrating a record-low power consumption (354 nW) for the respiration monitoring, outperforming the existing designs. The proposed processor can be integrated in a wearable sensor for ultra-low power and high accuracy respiration monitoring.

Advances in Respiratory Monitoring: A Comprehensive Review of Wearable and Remote Technologies

“…The cameras are versatile, they can monitor continuously, and interestingly, they allow the detection of breathing in several people at the same time, which other sensors normally do not provide. 1 Bluetooth low energy, 2 Inertial measurement unit, 3 Respiration rate, 4 Heart rate, 5 Heart rate variability, 6 Respiration volume, 7 Polyvinylidene fluoride, 8 Respiratory inductance plethysmography, 9 Body temperature, 10 ECG-derived respiratory, 11 Microelectromechanical systems, 12 Electromyography, 13 Machine learning, 14 Kernel Support Vector Machine, 15 Convolutional neural network, 16 Electro-impedance plethysmography, 17 Optical fiber, 18 Numeric aperture, 19 Plastic optical fiber, 20 Fiber Bragg Grating, 21 Magnetic resonance imaging, 22 Blood pressure, 23 Grooved, photosensitive, luminescent.…”

“…In the future, we can count on the development of processors specially designed for ECG-derived respiration. The study by Fan et al [9] introduces an innovative processor specifically designed for achieving high accuracy and ultra-low power in EDR estimation. Various techniques, including QRS detection with refractory period refreshing and adaptive threshold EDR estimation, have been proposed to enhance accuracy and reduce computational complexity, subsequently lowering power consumption.…”

“…This superior performance positions the proposed processor as an ideal candidate for integration into wearable sensors, facilitating ultra-low power and highly accurate respiration monitoring. 1 ECG-derived respiration, 2 Electrocardiography, 3 Inertial measurement unit, 4 Respiration rate, 5 Heart rate variability, 6 Photoplethysmography, 7 Root mean square, 8 Fast Fourier transformation, 9 Mean absolute error, 10 Light emitting diode, 11 Bluetooth low energy, 12 Convolutional neural networks, 13 Body temperature, 14 Near field communication.…”

“…Embedded system, Renesas S5D9 120 MHz, Kernel-like minimum distance classifier, Accuracy up to 91.23% [227] 1 Digital signal processing, 2 Artificial intelligences, 3 Support vector machine, 4 Convolutional neural network, 5 Signal to noise ratio, 6 Bluetooth low energy, 7 Obstructive sleep apnea, 8 Machine learning, 9 Inertial measurement unit, 10 Peak to through differences, 11 Median of absolute error, 12 Fast Fourier transformation, 13 Power signal density.…”

“…The diagnosis, detection, and treatment of respiratory diseases typically demand hospital resources, often involving costly and invasive methods. Commonly used methods like spirometry, pneumography, plethysmography, or capnography are typically invasive, often inconvenient for patients, and require expensive equipment primarily found in ICUs [7][8][9]. Monitoring the respiratory rate (RR) serves as a vital sign to track the progression of illness, and an abnormal RR is a significant indicator of serious health issues.…”