Organism State Identification and Forecast Based on Comprehensive Sensor Measurement Processing with the Adaptive Algorithms

Abstract

Many medical devices are using photoplethysmography (PPG) signals to estimate cardiac rate (CR), respiratory rate (RR), blood pressure (BP) and blood oxygen (SpO2). Photoplethysmography demonstrated its great potential in non-invasive monitoring of the human organism state [17], but application of this method with wearable devices is extremely difficult due to its vulnerability to motion artifacts. This paper presents implementation of a photoplethysmography device on the Raspberry Pi 3 B+ single-board computer.The work uses adaptive algorithms to study the cardiovascular system state in severe device operating conditions degrading the evaluation accuracy of CR rate and other parameters of the heart rate. Selection of the device component base and component parts was made based on their availability and multi-functionality. The manufactured mockup made it possible to carry out research to determine the most effective algorithms for digital processing of signals received from sensors.Methods of digital signal processing based on adaptive algorithms are proposed: Wiener algorithms, algorithms based on the method of least squares (MLS) and algorithms based on the Kalman filtering. In the course of measurements taken on simulation objects and volunteers invited to participate in the study, analysis of the results of various measurement processing algorithms operation was carried out. A method is proposed for assessing the accuracy of calculating the CR and analyzing effectiveness of the external noise filtering with adaptive filters. Processing the sensor measurements made it possible to monitor the heart rate with the given accuracy, as well as to predict the human body state.