Electrocardiogram Signals Denoising Using Improved Variational Mode Decomposition

Malhotra, Vikas; Sandhu, Mandeep Kaur

doi:10.4103/jmss.jmss_17_20

Cited by 4 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the lunar gateway as a reference for new-generation deep-space spacecraft environments, its 400-Hz power supply will be converted to 60 Hz for experiments and commercial equipment 47 . Thus, three types of ECG frequencies need to be removed 48 : under 3–4 Hz (baseline wander noise, muscle artifacts, breathing), over 50–60 Hz (spacecraft power interface, instrumentation noise), and electrode motion artifacts. This is in line with literature raising the importance of maintaining frequency modes under 15 Hz that contain most ECG components (P and T waves) and modes between 30–60 Hz that contain most QRS complex information 36 .…”

Section: Methodsmentioning

confidence: 99%

Machine learning workflow for edge computed arrhythmia detection in exploration class missions

Mani,

Paul,

Archambault

et al. 2024

npj Microgravity

View full text Add to dashboard Cite

Deep-space missions require preventative care methods based on predictive models for identifying in-space pathologies. Deploying such models requires flexible edge computing, which Open Neural Network Exchange (ONNX) formats enable by optimizing inference directly on wearable edge devices. This work demonstrates an innovative approach to point-of-care machine learning model pipelines by combining this capacity with an advanced self-optimizing training scheme to classify periods of Normal Sinus Rhythm (NSR), Atrial Fibrillation (AFIB), and Atrial Flutter (AFL). 742 h of electrocardiogram (ECG) recordings were pre-processed into 30-second normalized samples where variable mode decomposition purged muscle artifacts and instrumentation noise. Seventeen heart rate variability and morphological ECG features were extracted by convoluting peak detection with Gaussian distributions and delineating QRS complexes using discrete wavelet transforms. The decision tree classifier’s features, parameters, and hyperparameters were self-optimized through stratified triple nested cross-validation ranked on F1-scoring against cardiologist labeling. The selected model achieved a macro F1-score of 0.899 with 0.993 for NSR, 0.938 for AFIB, and 0.767 for AFL. The most important features included median P-wave amplitudes, PRR20, and mean heart rates. The ONNX-translated pipeline took 9.2 s/sample. This combination of our self-optimizing scheme and deployment use case of ONNX demonstrated overall accurate operational tachycardia detection.

show abstract

Section: Methodsmentioning

confidence: 99%