Diagnostic Interpretation of Non-Uniformly Sampled Electrocardiogram

Augustyniak, Piotr

doi:10.3390/s21092969

Cited by 2 publications

(2 citation statements)

References 108 publications

(125 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dengao Li et al used a novel neural network structure based on the 12 most common electrocardiographic leads proposed to classify 9 arrhythmias [5]. Piotr Augustyniak used a time-independent QRS detection method [10]. We applied a graph data representation and applied a heterogeneous time-scale transform finding the exact P, QRS and T wave demarcation points.…”

Section: Ecg Characteristic Analysis and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The Comparison Features of ECG Signal with Different Sampling Frequencies and Filter Methods for Real-Time Measurement

Bui

Byun

2021

Symmetry

View full text Add to dashboard Cite

Electrocardiogram (ECG) signals have been used to monitor and diagnose signs of cardiovascular disease and abnormal signals about the human body. ECG signals are typically characterized by the PR, QRS, QT interval, ST-segment, and heart rate (HR) parameters. ECG devices are widely used for many applications, especially for the elderly. However, ECG signals are often affected by noises from the environment. There are mainly two types of noises that affect the ECG signals: low frequencies from muscle activity and 50/60 Hz from the electrical grid. Removing these noises is important for improving the quality of the ECG signal. A clear ECG signal makes it easy to diagnose cardiovascular problems. ECG signals with high sampling frequency are more accurate. However, the noises in the signal will be more obvious and it will be difficult to remove these noises with filters. We analyzed the symmetrical correlation between the sampling frequency of the signal and the parameters of the signal such as signal to noise ratio (SNR) and signal amplitude. This study will compare characterization of ECG signals performed at different sampling frequencies before and after applying infinite impulse response (IIR) and symmetric finite impulse response (FIR) filters. Therefore, it is critical that the sampling frequency is consistent at the same frequency of the ECG signal for accurate diagnosis. Furthermore, the approach can be also important for the device to help reduce the device’s computing power and hardware resources. Our results were tested with the MIT/ BIH database at 360 Hz sampling frequency with 11-bit resolution. We also experimented with the device operating in real-time with a sampling frequency from 100 Hz to 2133 Hz and a 24-bit resolution. The test results show the advantages of the symmetric FIR filter over IIR when applied to the filtering of ECG signals. The study’s conclusions can be applied to real-world devices to improve the quality of ECG signals.

show abstract

Section: Ecg Characteristic Analysis and Related Workmentioning

confidence: 99%

“…The electrocardiogram is a common non-invasive measurement method in the screening and diagnosing of various diseases [5][6][7][8]. One of the critical applications is in health monitoring and diagnosis [9,10]. It provides one of the essential pieces of information supporting the diagnosis of stroke.…”

Section: Introductionmentioning

confidence: 99%

The Comparison Features of ECG Signal with Different Sampling Frequencies and Filter Methods for Real-Time Measurement

Bui

Byun

2021

Symmetry

View full text Add to dashboard Cite

show abstract

Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain

Bhattacharjee,

Augustyniak

2024

Applied Sciences

View full text Add to dashboard Cite

Electrocardiographic signals (ECG) are ubiquitous, which justifies the research of their optimal storage and transmission. However, proposals for non-uniform signal sampling must take into account the priority of diagnostic data accuracy and record integrity, as well as robustness to noise and interference. In this study, two novel methods are introduced, each utilizing a distinct neural network architecture for optimizing non-uniform sampling of ECG signal. A transformer model refines each time point selection through an iterative process using gradient descent optimization, with the goal of minimizing the mean squared error between the original and resampled signals. It adaptively modifies time points, which improves the alignment between both signals. In contrast, the Temporal Convolutional Network model trains on the original signal, and gradient descent optimization is utilized to improve the selection of time points. Evaluation of both strategies’ efficacy is performed by calculating signal distances at lower and higher sampling rates. First, a collection of synthetic data points that resembled the P-QRS-T wave was used to train the model. Then, the ECG-ID database for real data analysis was used. Filtering to remove baseline wander followed by evaluation and testing were carried out in the real patient data. The results, in particular MSE = 0.0005, RMSE = 0.0216, and Pearson’s CC = 0.9904 for 120 sps in the case of the transformer patient data model, provide viable paths for maintaining the precision and dependability of ECG-based diagnostic systems at much lower sampling rate. Outcomes indicate that both techniques are effective at improving the fidelity between the original and modified ECG signals.

show abstract

Diagnostic Interpretation of Non-Uniformly Sampled Electrocardiogram

Cited by 2 publications

References 108 publications

The Comparison Features of ECG Signal with Different Sampling Frequencies and Filter Methods for Real-Time Measurement

The Comparison Features of ECG Signal with Different Sampling Frequencies and Filter Methods for Real-Time Measurement

Comparative Evaluation of Neural Network Models for Optimizing ECG Signal in Non-Uniform Sampling Domain

Contact Info

Product

Resources

About