LAUSR

Motivation: This paper proposes a motion artifact removal (MAR) algorithm and its evaluation method for wearable functional near infrared spectroscopy (fNIRS) system. Methods: Two types of motion artifacts (MAs) and their characteristics have been investigated, and a coarse/fine dual-stage MAR method is proposed, which can remove the MAs with different features and magnitudes to protect the original data from damage. In addition, an evaluation method is also proposed based on the classification of 4 mental tasks, which objectively quantize the performance of the MAR algorithms. Results: With the proposed MAR algorithm, the mental-task classification accuracy increased from 74.73% to 83.70% in average.