Automatic ECG artifact removal in the real-time SEMG recording system

The contaminated electrocardiography (ECG) is a big problem in the surface electromyography (SEMG) signal detection and analysis. The objective of the current study is to propose and validate an algorithm for the automated feature cognition and identification for eliminating ECG artifact from the raw SEMG signals. The utilization of Independent Component Analysis (ICA) method is to decompose the raw SEMG signals into individual independent source components. After that, some of the independent source components with the characteristics of ECG artifact were detected by the automated identification algorithm and thereafter eliminated. The sensitivity and specificity of the algorithm for distinguishing ECG source components from independent source components are 100% and 99% respectively. The automated identification algorithm exhibits the prominent performance of recognition for ECG artifact and can be considered reliable and effective.