Physics

Pattern recognition (psychology)

Biology

Noise (video)

Image (mathematics)

Signal processing

Data mining

Epistemology

Machine learning

Wearable computer

Detection theory

Philosophy

Embedded system

Paleontology

Artificial intelligence

Power (physics)

Programming language

Quality (philosophy)

SIGNAL (programming language)

Context (archaeology)

Computer science

Quantum mechanics

Reliability (semiconductor)

Radar

Telecommunications

Detector

IEEE Reviews in Biomedical Engineering

Electrocardiogram (ECG) signal quality assessment (SQA) plays a vital role in significantly improving the diagnostic accuracy and reliability of unsupervised ECG analysis systems. In practice, the ECG signal is often corrupted with different kinds of noises and artifacts. Therefore, numerous SQA methods were presented based on the ECG signal and/or noise features and the machine learning classifiers and/or heuristic decision rules. This paper presents an overview of current state-of-the-art SQA methods and highlights the practical limitations of the existing SQA methods. Based upon past and our studies, it is noticed that a lightweight ECG noise analysis framework is highly demanded for real-time detection, localization, and classification of single and combined ECG noises within the context of wearable ECG monitoring devices which are often resource constrained.

A Review of Signal Processing Techniques for Electrocardiogram Signal Quality Assessment