Compressed sensing methods for ECG and PPG signals substantially reduce data volume while retaining critical clinical features, utilizing various dictionaries, sensing matrices, and reconstruction algorithms.
This review highlights recent advancements in compressed sensing techniques for efficient compression and management of ECG and PPG signals in healthcare monitoring systems.
Abstract The increasing integration of information and communication technologies in healthcare has enabled advanced patient monitoring and personalized treatment. Efficient data management is crucial in such systems, as the high volume of biomedical signals requires optimized compression techniques. Compressed sensing has emerged as an approach within lossy compression methods, leveraging signal sparsity to achieve high compression ratios (CR) without significant loss of critical information. This paper provides a concise review of the most recent developments in CS for electrocardiogram (ECG) and photoplethysmogram (PPG) signals, summarizing key advances in standard CS methods, dictionary-based approaches, and emerging frameworks incorporating artificial intelligence. The review aims to highlight current trends and outline directions for future research in biomedical signal compression.
Kovacova et al. (Mon,) conducted a review in ECG and PPG signal compression. Compressed sensing was evaluated. Compressed sensing methods for ECG and PPG signals substantially reduce data volume while retaining critical clinical features, utilizing various dictionaries, sensing matrices, and reconstruction algorithms.