I see artifacts: ICA-based EEG artifact removal does not improve deep network decoding across three BCI tasks
Taeho Kang, Yiyu Chen, Christian Wallraven
TLDR
ICA-based EEG artifact removal does not consistently improve deep network decoding across three BCI tasks, despite significant computational cost.
Key contributions
- Evaluated ICA-based EEG artifact removal for deep learning decoding across diverse BCI tasks.
- Compared two ICA methods (Infomax, AMICA) and three rejection strategies (ICLabel, MARA).
- Tested on three EEG datasets (motor imagery, memory) and three deep network architectures.
- Found ICA-based artifact removal provides only minor, inconsistent decoding benefits.
Why it matters
This paper challenges the common assumption that ICA-based artifact removal is essential for EEG decoding. It suggests researchers might save significant computational resources by omitting these methods, especially with deep learning, streamlining data processing and accelerating BCI research.
Original Abstract
In this paper, we conduct a detailed investigation on the effect of independent component (IC)-based noise rejection methods in neural network classifier-based decoding of electroencephalography (EEG) data in different task datasets. We apply a pipeline matrix of two popular different independent component (IC) decomposition methods (Infomax and Adaptive Mixture Independent Component Analysis (AMICA)) with three different component rejection strategies (none, ICLabel, and multiple artifact rejection algorithm [MARA]) on three different EEG datasets (motor imagery, long-term memory formation, and visual memory). We cross-validate processed data from each pipeline with three architectures commonly used for EEG classification (two convolutional neural networks and one long short-term memory-based model. We compare decoding performances on within-participant and within-dataset levels.Our results show that the benefit from using IC-based noise rejection for decoding analyses is at best minor, as component-rejected data did not show consistently better performance than data without rejections; especially given the significant computational resources required for independent component analysis (ICA) computations.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.