Ballistocardiogram signal processing: a review

Abstract

There are several algorithms for analyzing and interpreting cardiorespiratory signals obtained from in-bed based sensors. In sum, these algorithms can be broadly grouped into three categories: time-domain algorithms, frequency-domain algorithms, and wavelet-domain algorithms. A summary of these algorithms is given below to highlight which category of algorithms will be used in our analysis. First, time-domain algorithms are mainly focused on detecting local maxima or local minima using a moving window, and therefore finding the interval between the dominant J-peaks of ballistocardiogram signal. However, this approach has many limitations because of the nonlinear and nonstationary behavior of the ballistocardiogram signal. The implication is that the ballistocardiogram signal does not display consistent J-peaks, which can usually be the case for overnight, in-home monitoring, particularly with frail elderly. Additionally, its accuracy will be undoubtedly affected by motion artifacts. Second, frequency-domain algorithms do not provide information about interbeat intervals. Nevertheless, they can provide information about heart rate variability. This is usually done by taking the fast Fourier transform or the inverse Fourier transform of the logarithm of the estimated spectrum, i.e., cepstrum of the signal using a sliding window. Thereafter, the dominant frequency is obtained in a particular frequency range. The limit of these algorithms is that the peak in the spectrum may get wider and multiple peaks may appear, which might cause a problem in measuring the vital signs. At last, the objective of wavelet-domain algorithms is to decompose the signal into different components, hence the component which shows an agreement with the vital signs can be selected. In other words, the selected component contains only information about the heart cycles or respiratory cycles, respectively. Interbeat intervals can be found easily by applying a simple peak detector. An empirical mode decomposition is an alternative approach to wavelet decomposition, and it is also a very suitable approach to cope with nonlinear and nonstationary signals such as cardiorespiratory signals. Apart from the above-mentioned algorithms, machine learning approaches have been implemented for measuring heartbeats. However, manual labeling of training data is a restricting property. Furthermore, the training step should be repeated whenever the data collection protocol has been changed.

Privacy and Security of IoT Based Healthcare Systems: Concerns, Solutions, and Recommendations

“…On the one hand, there are some standard features that these sensors claim to measure, such as heart rate, respiration, sleep and wake-up time, and sleep interruptions. There are several publications in the existing literature that can support these claims, as mentioned in [20].…”

“…These sensors technologies are preferred than those popular sensors (e.g., ECG) when we are considering long-term (trend over time, early detection and intervention by sending alarms to family members or caregivers through well-designed user interfaces), mobile, convenient and practical (aging-in-place, senior activity centers). However, in critical situations, gold-standard methods should be considered [20].…”

Heart Rhythm Analyzed via Shapelets Distinguishes Sleep From Awake

“…Under real life conditions it would be preferable to do this online from automated analysis of vital signs recorded with minimally obtrusive sensor systems. In fact, several approaches have already been explored (Canisius and Penzel, 2007;Romine et al, 2019;Sadek et al, 2019) to achieve this. Various medical applications are easy to imagine, but perhaps more important are practical applications in which vigilance plays an important role.…”

Bedscales: A non-contact adherence-independent multi-person sensor for longitudinal physiologic monitoring in the home bed

“…Non-contact sensors have been developed using under-the-mattress piezoelectric-, strain gauge-, or radio frequency-based sensing, and are highly sensitive to dynamic respiratory and ballistocardiographic signals (16,17). However, they are sensitive to subject-sensor proximity and orientation and are unable to reliably differentiate signals from individuals who share a bed with a partner or pet (18)(19)(20).…”