Breathing Rate Estimation from Head-Worn Photoplethysmography Sensor Data Using Machine Learning

Abstract

Breathing rate is considered one of the fundamental vital signs and a highly informative indicator of physiological state. Given that the monitoring of heart activity is less complex than the monitoring of breathing, a variety of algorithms have been developed to estimate breathing activity from heart activity. However, estimating breathing rate from heart activity outside of laboratory conditions is still a challenge. The challenge is even greater when new wearable devices with novel sensor placements are being used. In this paper, we present a novel algorithm for breathing rate estimation from photoplethysmography (PPG) data acquired from a head-worn virtual reality mask equipped with a PPG sensor placed on the forehead of a subject. The algorithm is based on advanced signal processing and machine learning techniques and includes a novel quality assessment and motion artifacts removal procedure. The proposed algorithm is evaluated and compared to existing approaches from the related work using two separate datasets that contains data from a total of 37 subjects overall. Numerous experiments show that the proposed algorithm outperforms the compared algorithms, achieving a mean absolute error of 1.38 breaths per minute and a Pearson’s correlation coefficient of 0.86. These results indicate that reliable estimation of breathing rate is possible based on PPG data acquired from a head-worn device.

Facial EMG sensing for monitoring affect using a wearable device

“…For data collection, we used the emteqPro device 20 – 22 . The device comprises a facial electromyographic (EMG), a photoplethysmographic (PPG), and an inertial measurement unit (IMU) sensor integrated within a soft frame that fits on the face of the wearer.…”

“…This study investigates the association between facial sEMG and subjective and objective affect, using a novel wearable sEMG sensing device in VR environments. We used a set of dry, arrayed sEMG sensors (emteqPro) 20 – 22 , attached to a Pico Virtual Reality (VR) headset. During the experiments, physiological recordings and subjective self-reported data were collected from participants following exposure to videos varying in arousal and valence.…”

A Multifunctional Network with Uncertainty Estimation and Attention-Based Knowledge Distillation to Address Practical Challenges in Respiration Rate Estimation

“…Birrenkott et al [ 8 ] used ML algorithms such as random forest regression, support vector regression, etc., to create a smart fusion that fuses the RR obtained from different modulations of ECG and PPG. An ML-based approach to extract RR from headworn PPG was presented by [ 30 ]. Chan et al [ 11 ] used linear regression to fuse the respiration signal obtained from ECG and accelerometer.…”

Mass‐Producible 3D Hair Structure‐Editable Silk‐Based Electronic Skin for Multiscenario Signal Monitoring and Emergency Alarming System

“…According to relevant reports, the breathing rate of healthy and normal adults is ≈12-20 times per minute, and the breathing rate is 12-18 times in a resting state, when the breathing exceeds this range, it means that your physical state may be in an unhealthy and uneasy state. [41,42] Figure 4d imitates the beard of the human body, put the P-silk/RG e-skin under the nose of the human body, and monitors the respiratory state and air exchange frequency changes of the same human body in a healthy state and a sick state. The results showed that the breathing intensity of the human body in the sick state was lower than that in the healthy state, but the breathing rate increased (from 18 times min −1 to 23 times min −1 ).…”