Chih-Sheng Huang

Chun-Hsiang Chuang, Kong-Yi Chang, Chih-Sheng Huang et al.

Artifact removal in electroencephalography (EEG) is a longstanding challenge that significantly impacts neuroscientific analysis and brain-computer interface (BCI) performance. Tackling this problem demands advanced algorithms, extensive noisy-clean training data, and thorough evaluation strategies. This study presents the Artifact Removal Transformer (ART), an innovative EEG denoising model employing transformer architecture to adeptly capture the transient millisecond-scale dynamics characteristic of EEG signals. Our approach offers a holistic, end-to-end denoising solution for diverse artifact types in multichannel EEG data. We enhanced the generation of noisy-clean EEG data pairs using an independent component analysis, thus fortifying the training scenarios critical for effective supervised learning. We performed comprehensive validations using a wide range of open datasets from various BCI applications, employing metrics like mean squared error and signal-to-noise ratio, as well as sophisticated techniques such as source localization and EEG component classification. Our evaluations confirm that ART surpasses other deep-learning-based artifact removal methods, setting a new benchmark in EEG signal processing. This advancement not only boosts the accuracy and reliability of artifact removal but also promises to catalyze further innovations in the field, facilitating the study of brain dynamics in naturalistic environments.

Chun-Hsiang Chuang, Kong-Yi Chang, Chih-Sheng Huang et al.

Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent misinterpretations of neural signals and underperformance of brain-computer interfaces. This study developed a new artifact removal method, IC-U-Net, which is based on the U-Net architecture for removing pervasive EEG artifacts and reconstructing brain sources. The IC-U-Net was trained using mixtures of brain and non-brain sources decomposed by independent component analysis and employed an ensemble of loss functions to model complex signal fluctuations in EEG recordings. The effectiveness of the proposed method in recovering brain sources and removing various artifacts (e.g., eye blinks/movements, muscle activities, and line/channel noises) was demonstrated in a simulation study and three real-world EEG datasets collected at rest and while driving and walking. IC-U-Net is user-friendly and publicly available, does not require parameter tuning or artifact type designations, and has no limitations on channel numbers. Given the increasing need to image natural brain dynamics in a mobile setting, IC-U-Net offers a promising end-to-end solution for automatically removing artifacts from EEG recordings.

Jun-Wei Hsieh, Ming-Ching Chang, Ping-Yang Chen et al.

Differentiable Architecture Search (DARTS) is an effective continuous relaxation-based network architecture search (NAS) method with low search cost. It has attracted significant attentions in Auto-ML research and becomes one of the most useful paradigms in NAS. Although DARTS can produce superior efficiency over traditional NAS approaches with better control of complex parameters, oftentimes it suffers from stabilization issues in producing deteriorating architectures when discretizing the continuous architecture. We observed considerable loss of validity causing dramatic decline in performance at this final discretization step of DARTS. To address this issue, we propose a Mean-Shift based DARTS (MS-DARTS) to improve stability based on sampling and perturbation. Our approach can improve bot the stability and accuracy of DARTS, by smoothing the loss landscape and sampling architecture parameters within a suitable bandwidth. We investigate the convergence of our mean-shift approach, together with the effects of bandwidth selection that affects stability and accuracy. Evaluations performed on CIFAR-10, CIFAR-100, and ImageNet show that MS-DARTS archives higher performance over other state-of-the-art NAS methods with reduced search cost.

Chun-Hsiang Chuang, Zehong Cao, Po-Tsang Chen et al.

Predicting a driver's cognitive state, or more specifically, modeling a driver's reaction time (RT) in response to the appearance of a potential hazard warrants urgent research. In the last two decades, the electric field that is generated by the activities in the brain, monitored by an electroencephalogram (EEG), has been proven to be a robust physiological indicator of human behavior. However, mapping the human brain can be extremely challenging, especially owing to the variability in human beings over time, both within and among individuals. Factors such as fatigue, inattention and stress can induce homeostatic changes in the brain, which affect the observed relationship between brain dynamics and behavioral performance, and thus make the existing systems for predicting RT difficult to generalize. To solve this problem, an ensemble-based weighted prediction system is presented herein. This system comprises a set of prediction submodels that are individually trained using groups of data with similar EEG-RT relationships. To obtain a final prediction, the prediction outcomes of the sub-models are then multiplied by weights that are derived from the EEG alpha coherences of 10 channels plus theta band powers of 30 channels, whose changes were found to be indicators of variations in the EEG-RT relationship. The results thus obtained reveal that the proposed system with a time-varying adaptive weighting mechanism significantly outperforms the conventional system in modeling a driver's RT. The adaptive design of the proposed system demonstrates its feasibility in coping with the variability in the brain-behavior relationship. In this contribution surprisingly simple EEG-based adaptive methods are used in combination with an ensemble scheme to significantly increase system performance.