IMU-Enhanced EEG Motion Artifact Removal with Fine-Tuned Large Brain Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Yuhong, Zhu, Xusheng, Xu, Yuchen, Lu, ChiaEn, Shih, Hsinyu, Cauwenberghs, Gert, Jung, Tzyy-Ping
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908512173424640
author Zhang, Yuhong
Zhu, Xusheng
Xu, Yuchen
Lu, ChiaEn
Shih, Hsinyu
Cauwenberghs, Gert
Jung, Tzyy-Ping
author_facet Zhang, Yuhong
Zhu, Xusheng
Xu, Yuchen
Lu, ChiaEn
Shih, Hsinyu
Cauwenberghs, Gert
Jung, Tzyy-Ping
contents Electroencephalography (EEG) is a non-invasive method for measuring brain activity with high temporal resolution; however, EEG signals often exhibit low signal-to-noise ratios because of contamination from physiological and environmental artifacts. One of the major challenges hindering the real-world deployment of brain-computer interfaces (BCIs) involves the frequent occurrence of motion-related EEG artifacts. Most prior studies on EEG motion artifact removal rely on single-modality approaches, such as Artifact Subspace Reconstruction (ASR) and Independent Component Analysis (ICA), without incorporating simultaneously recorded modalities like inertial measurement units (IMUs), which directly capture the extent and dynamics of motion. This work proposes a fine-tuned large brain model (LaBraM)-based correlation attention mapping method that leverages spatial channel relationships in IMU data to identify motion-related artifacts in EEG signals. The fine-tuned model contains approximately 9.2 million parameters and uses 5.9 hours of EEG and IMU recordings for training, just 0.2346\% of the 2500 hours used to train the base model. We compare our results against the established ASR-ICA benchmark across varying time scales and motion activities, showing that incorporating IMU reference signals significantly improves robustness under diverse motion scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01073
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IMU-Enhanced EEG Motion Artifact Removal with Fine-Tuned Large Brain Models
Zhang, Yuhong
Zhu, Xusheng
Xu, Yuchen
Lu, ChiaEn
Shih, Hsinyu
Cauwenberghs, Gert
Jung, Tzyy-Ping
Machine Learning
Signal Processing
Neurons and Cognition
Electroencephalography (EEG) is a non-invasive method for measuring brain activity with high temporal resolution; however, EEG signals often exhibit low signal-to-noise ratios because of contamination from physiological and environmental artifacts. One of the major challenges hindering the real-world deployment of brain-computer interfaces (BCIs) involves the frequent occurrence of motion-related EEG artifacts. Most prior studies on EEG motion artifact removal rely on single-modality approaches, such as Artifact Subspace Reconstruction (ASR) and Independent Component Analysis (ICA), without incorporating simultaneously recorded modalities like inertial measurement units (IMUs), which directly capture the extent and dynamics of motion. This work proposes a fine-tuned large brain model (LaBraM)-based correlation attention mapping method that leverages spatial channel relationships in IMU data to identify motion-related artifacts in EEG signals. The fine-tuned model contains approximately 9.2 million parameters and uses 5.9 hours of EEG and IMU recordings for training, just 0.2346\% of the 2500 hours used to train the base model. We compare our results against the established ASR-ICA benchmark across varying time scales and motion activities, showing that incorporating IMU reference signals significantly improves robustness under diverse motion scenarios.
title IMU-Enhanced EEG Motion Artifact Removal with Fine-Tuned Large Brain Models
topic Machine Learning
Signal Processing
Neurons and Cognition
url https://arxiv.org/abs/2509.01073