Novel eye-blink artefact detection algorithm from raw EEG signals using FCN-based semantic segmentation method

Abstract

Electroencephalography (EEG) signal artefacts cause some problems in processing and analysis of EEG signals. There are several options in the literature to identify artefacts in signal areas. However, high accuracy level in artefact detection was not achieved with these methods. New methods are needed to increase the level of accuracy. Semantic segmentation algorithms, which are widely used in image processing, were used for the first time in this study to detect eye-blink artefacts in EEG signals. In the proposed method, EEG recordings obtained from four channels were divided into 10-s segments. These segments were converted into images in 256 × 256 resolution and were labelled as eye-blink, not-blink and background. The algorithm was trained with these labelled images. The trained algorithm was tested with images containing 1630 eye-blink and not-blink signal segments obtained from single-channel and multi-channel EEG signals. Classification accuracy of the algorithm was 94.4%. The proposed method successfully detected eye-blink artefacts in simultaneous multi-channel signal images.