arXiv subjects

Ying Choon Wu

Publications and source records attributed to Ying Choon Wu.

3 recordsLinked to original sources

arXiv2026

The Identity Trap in EEG Foundation Models: A Diagnostic Audit

Objective. EEG foundation models (FMs) report strong accuracy on clinical resting-state EEG. However, high accuracy under subject-disjoint cross-validation remains ambiguous: it can reflect a genuine clinical biomarker, or subject-identity features that correlate with the label. We name this the Identity Trap and ask whether it can be diagnosed at the representation level before fine-tuning. Approach. We propose FMScope, a frozen-representation protocol packaging five diagnostics: variance decomposition, subject-axis erasure, aperiodic 1/f ablation, layer-wise label probing, and within-subject direction consistency. We apply it to three pretrained FMs (LaBraM, CBraMod, REVE) across four datasets in a 2x2 layout: subject relation of label x presence of a consensus cross-subject EEG marker. Main results. (i) The Identity Trap is universal: frozen subject-variance is 13-89x a random null in 12/12 pairs, rising in all 12 under fine-tuning (+10 to +63 pp). This dominance is a removable linear axis: erasing it improves label decoding where the label varies within subject (+6 to +12 pp in primary cells; +4 to +27 pp across external cohorts). (ii) Aperiodic 1/f is one subject carrier: removing it drops the subject probe by 9-19 pp on LaBraM and CBraMod. REVE saturates subject identity without measurable aperiodic dependence. (iii) Fine-tuning amplifies label-variance only in cells with a literature-established cross-subject marker. Significance. The Identity Trap is a physically-grounded instance of shortcut learning: the preferred cue has a measurable physiological component, and subject-disjoint splitting alone cannot rule it out. FMScope separates gains reflecting a biological marker from those reflecting subject identity.

cs.LG↗

arXiv2024

Launching Your VR Neuroscience Laboratory

The proliferation and refinement of affordable virtual reality (VR) technologies and wearable sensors have opened new frontiers in cognitive and behavioral neuroscience. This chapter offers a broad overview of VR for anyone interested in leveraging it as a research tool. In the first section, it examines the fundamental functionalities of VR and outlines important considerations that inform the development of immersive content that stimulates the senses. In the second section, the focus of the discussion shifts to the implementation of VR in the context of the neuroscience lab. Practical advice is offered on adapting commercial, off-theshelf devices to specific research purposes. Further, methods are explored for recording, synchronizing, and fusing heterogeneous forms of data obtained through the VR system or add-on sensors, as well as for labeling events and capturing game play.

cs.HC↗

arXiv2024

Online Mental Stress Detection Using Frontal-channel EEG Recordings in a Classroom Scenario

Objective: To investigate the effects of different approaches to EEG preprocessing, channel montage selection, and model architecture on the performance of an online-capable stress detection algorithm in a classroom scenario. Methods: This analysis used EEG data from a longitudinal stress and fatigue study conducted among university students. Their self-reported stress ratings during each class session were the basis for classifying EEG recordings into either normal or elevated stress states. We used a data-processing pipeline that combined Artifact Subspace Reconstruction (ASR)and an Independent Component Analysis (ICA)-based method to achieve online artifact removal. We compared the performance of a Linear Discriminant Analysis (LDA) and a 4-layer neural network as classifiers. We opted for accuracy, balanced accuracy, and F1 score as the metrics for assessing performance. We examined the impact of varying numbers of input channels using different channel montages. Additionally, we explored different window lengths and step sizes during online evaluation. Results: Our online artifact removal method achieved performance comparable to the offline ICA method in both offline and online evaluations. A balanced accuracy of 77% and 78% in an imbalanced binary classification were observed when using the 11-frontal-channel LDA model with the proposed artifact removal method. Moreover, the model performance remained intact when changing the channel montage from 30 full-scalp channels to just 11 frontal channels. During the online evaluation, we achieved the highest balanced accuracy (78%) with a window length of 20 seconds and a step size of 1 second. Significance: This study comprehensively investigates the deployment of stress detection in real-world scenarios. The findings of this study provide insight into the development of daily mental stress monitoring.

q-bio.NC↗