This project implements a non-invasive sleep monitoring system using a bed pressure sensor array. The system detects changes in the contact pressure between a subject and the bed and is able to automatically select the sensor with the best respiratory signal, determine the respiratory rate (RR), count number of sleep apneas and count body position changes through the night. The respiratory signal is validated with an airflow sensor using Pearson's correlation coefficient. To determine the performance of body position and apnea detection algorithms, the sensibility and positive predictivity is computed on preliminary data and known records from a Physionet database. Real data is obtained from 5 subjects totaling 39 hours measured at home during a full night sleep, in a non-invasive way. The data is used to calculate relevant parameters to estimate a sleep quality. Cumulative frequency of sleep interval duration is proposed as a novel metric for sleep assessment.
This work implements a noninvasive system that measures the movements caused by cardiac activity. It uses unobtrusive Electro-Mechanical Films (EMFi) on the seat and on the backrest of a regular chair. The system detects ballistocardiogram (BCG) and respiration movements. Real data was obtained from 54 volunteers. 19 of them were measured in the laboratory and 35 in a hospital waiting room. Using a BIOPAC acquisition system, the ECG was measured simultaneously to the BCG for comparison. Wavelet Transform (WT) is a better option than Empirical Mode Decomposition (EMD) for signal extraction and produces higher effective measurement time. In the laboratory, the best results are obtained on the seat. The correlation index was 0.9800 and the Bland-Altman limits of agreement were 0.7136 ± 4.3673 [BPM]. In the hospital waiting room, the best results are also from the seat sensor. The correlation index was 0.9840, and the limits of agreement were 0.4386 ± 3.5884 [BPM]. The system is able to measure BCG in an unobtrusive way and determine the cardiac frequency with high precision. It is simple to use, which means the system can easily be used in non-standard settings: resting in a chair or couch, at the gym, schools or in a hospital waiting room, as shown.
This paper presents the results from actual measurements of cardiac activity acquired through the use of noninvasive sensors to detect Ballistocardiogram (BCG). The results show that it is feasible to unobtrusively monitor heart rate in non-standard settings such as waiting rooms or at school using simple chairs fitted with capacitive sensors. The selected sensors, based on electromechanical principles, are able to measure BCG from a variety of subjects. We present the results for 114 participants from homes, school and a hospital waiting room, adding up over 815 minutes of data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.