Convolutive Blind Source Separation on Surface EMG Signals for Respiratory Diagnostics and Medical Ventilation Control
It addresses a major obstacle in clinical use of sEMG for adaptive ventilation control by enabling discrimination of muscle activities, but the approach is incremental.
This paper applies convolutive blind source separation to surface EMG signals to separate inspiratory, expiratory, and cardiac muscle activity, achieving clear separation for respiratory diagnostics and ventilation control.
The electromyogram (EMG) is an important tool for assessing the activity of a muscle and thus also a valuable measure for the diagnosis and control of respiratory support. In this article we propose convolutive blind source separation (BSS) as an effective tool to pre-process surface electromyogram (sEMG) data of the human respiratory muscles. Specifically, the problem of discriminating between inspiratory, expiratory and cardiac muscle activity is addressed, which currently poses a major obstacle for the clinical use of sEMG for adaptive ventilation control. It is shown that using the investigated broadband algorithm, a clear separation of these components can be achieved. The algorithm is based on a generic framework for BSS that utilizes multiple statistical signal characteristics. Apart from a four-channel FIR structure, there are no further restrictive assumptions on the demixing system.