Related Experiment Video
Updated: Jun 27, 2026
06:49
Automated Analysis of Dynamic Ca2+ Signals in Image Sequences
Published on: June 16, 2014
17.2K
BCG Signal Quality Assessment Based on Time-Series Imaging Methods
Sungtae Shin1, Soonyoung Choi1, Chaeyoung Kim2
1Department of Mechanical Engineering, Dong-A University, Busan 49315, Republic of Korea.
Sensors (Basel, Switzerland)
|December 9, 2023
Summary
This study developed a method to classify arm ballistocardiogram (BCG) signal quality for accurate, non-invasive blood pressure monitoring. Using image-based deep learning, the system achieved 87.5% accuracy in distinguishing high-quality from low-quality BCG signals.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Wearable Technology
Background:
- Ballistocardiogram (BCG) signals offer potential for non-invasive, continuous blood pressure monitoring using accelerometers in wearable devices.
- BCG signals are prone to noise from motion artifacts, degrading blood pressure estimation accuracy.
- Effective signal quality classification is crucial to maintain the performance of BCG-based blood pressure measurement systems.
Purpose of the Study:
- To develop and evaluate a binary classification model for distinguishing high-quality from low-quality arm ballistocardiogram (BCG) signals.
- To prevent performance degradation in non-invasive blood pressure estimation caused by noisy BCG data.
- To explore time-series imaging techniques and convolutional neural network (CNN) architectures for BCG signal classification.
Main Methods:
- Four time-series imaging methods (recurrence plot, Gramain angular summation field, Gramain angular difference field, Markov transition field) were employed to convert BCG signals into images.
- Convolutional Neural Network (CNN) models including ResNet, SqueezeNet, DenseNet, and LeNet were utilized for image classification.
- A dataset of 9626 BCG beats was used for training, validation, and testing the classification models.
Main Results:
- The Gramain angular difference field method, when combined with ResNet and SqueezeNet CNN models, achieved a high binary classification accuracy of up to 87.5%.
- This indicates the effectiveness of converting temporal BCG signals into image representations for quality assessment.
- The study successfully demonstrated a method to identify usable BCG signals for reliable blood pressure monitoring.
Conclusions:
- The developed binary classification model effectively distinguishes between high-quality and low-quality BCG signals, crucial for accurate non-invasive blood pressure monitoring.
- Time-series imaging combined with deep learning CNNs provides a robust approach for BCG signal quality assessment.
- This method holds promise for improving the reliability and performance of wearable devices for continuous blood pressure measurement.
Keywords:
ballistocardiogramclassificationconvolutional neural networksignal quality assessmenttime-series imagingMore Related Videos
09:09Cortical Actin Flow in T Cells Quantified by Spatio-temporal Image Correlation Spectroscopy of Structured Illumination Microscopy Data
Published on: December 17, 2015
9.8K
12:54Simultaneous Brightfield, Fluorescence, and Optical Coherence Tomographic Imaging of Contracting Cardiac Trabeculae Ex Vivo
Published on: October 2, 2021
3.3K
Related Concept Videos
01:17Pulse amplitude and quality
Pulse amplitude is a crucial indicator of cardiac health because it provides valuable insights into the strength of left ventricular contractions and the overall uniformity of blood circulation within the vasculature. The strength of the pulse is directly related to the force with which the heart contracts and the volume of blood being pumped.
A weak or absent pulse may indicate reduced cardiac output or poor left ventricular contraction, which can be signs of cardiovascular dysfunction or...
A weak or absent pulse may indicate reduced cardiac output or poor left ventricular contraction, which can be signs of cardiovascular dysfunction or...
01:30Classification of Signals
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
01:22Basic Continuous Time Signals
Basic continuous-time signals include the unit step function, unit impulse function, and unit ramp function, collectively referred to as singularity functions. Singularity functions are characterized by discontinuities or discontinuous derivatives.
The unit step function, denoted u(t), is zero for negative time values and one for positive time values, exhibiting a discontinuity at t=0. This function often represents abrupt changes, such as the step voltage introduced when turning a car's...
The unit step function, denoted u(t), is zero for negative time values and one for positive time values, exhibiting a discontinuity at t=0. This function often represents abrupt changes, such as the step voltage introduced when turning a car's...
01:22Basic Operations on Signals
Basic signal operations include time reversal, time scaling, time shifting, and amplitude transformations. These operations are fundamental in signal processing and analysis.
Time Reversal mirrors a continuous-time signal about the vertical axis at t=0. This is achieved by substituting t with −t. For example, if a signal x(t) is considered, the time-reversed signal is x(−t). This operation can be graphically represented, showing the mirrored signal.
Time Reversal mirrors a continuous-time signal about the vertical axis at t=0. This is achieved by substituting t with −t. For example, if a signal x(t) is considered, the time-reversed signal is x(−t). This operation can be graphically represented, showing the mirrored signal.
01:11Sampling Continuous Time Signal
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
01:10Reconstruction of Signal using Interpolation
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...