Hybrid RF and PCA method: The number and Posture of piezoresistive sensors in a multifunctional technology for respiratory monitoring

Abstract

The motivation of the research work is Respiratory Rate (RR) monitoring which is susceptible to environmental and physiological stimuli, knowing it may help in assessing the health of patients. In this work, at rest, six trials on a treadmill were to be completed by 10 healthy males, while low-speed jogging in order to evaluate a new approach based on Principal Component Analysis (PCA). Random Forest (RF) with PCA for sensory selection using a special wearable system with six piezoresistive sensors. For instance, a single sensor is needed for a breathing evaluation while at rest, three sensors are needed for a low-speed walk, and four sensors are needed for a high-speed walk and run assessment. The findings may be helpful in the deployment of specialized algorithms to continuously and accurately monitor RR, as well as the creation of the best instrumented wearable devices for RR monitoring both while the subject is at rest and when they are engaging in physical activity. A smart garment was utilized to obtain the breathing information delivering six respiration signals in the three compartmental parts, and a data gathering board (DAQ NI USB6002 from National Instruments) was used to gather the reference respiratory data. The performance measurements are often calculated using it (e.g., accuracy, sensitivity, specificity, precision and F1 score).

Keywords

• Respiratory rate
• Principal component analysis
• Random forest
• Sensory selection and piezoresistive sensors