Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
This work addresses the need for privacy-compliant and energy-efficient ECG analysis in portable systems, but it appears incremental as it focuses on evaluating existing methods for a specific project.
The paper tackled the problem of selecting real-time preprocessing methods for ECG signal analysis in edge computing, evaluating them based on energy efficiency, processing capability, and real-time applicability for the FACE project, but did not report specific numerical results.
The increasing popularity of portable ECG systems and the growing demand for privacy-compliant, energy-efficient real-time analysis require new approaches to signal processing at the point of data acquisition. In this context, the edge domain is acquiring increasing importance, as it not only reduces latency times, but also enables an increased level of data security. The FACE project aims to develop an innovative machine learning solution for analysing long-term electrocardiograms that synergistically combines the strengths of edge and cloud computing. In this thesis, various pre-processing steps of ECG signals are analysed with regard to their applicability in the project. The selection of suitable methods in the edge area is based in particular on criteria such as energy efficiency, processing capability and real-time capability.