arXiv subjects

Jiahui An

Publications and source records attributed to Jiahui An.

4 recordsLinked to original sources

arXiv2026

Understanding and Correcting Low-Frequency Bias in EEG Foundation Model

Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models, which remains across dataset scales, model capacities, and pretraining objectives. Our analysis links this bias to the interaction between EEG's $1/f^\alpha$-like spectral structure and neural networks' tendency to preferentially learn low-frequency components. In masked autoencoders, the $\ell_2$ reconstruction objective further amplifies this imbalance: under comparable relative reconstruction errors, high-power low-frequency components contribute disproportionately to the loss. To address this issue, we introduce FAME, a frequency-balanced masked autoencoding framework that reconstructs time--frequency activity in predefined EEG bands from masked EEG inputs. FAME independently standardizes the reconstruction targets within each band and assigns equal weight to all band-specific losses, thereby balancing supervision across the EEG spectrum. Evaluated on 41 downstream tasks in OmniEEG-Bench, FAME learns more spectrally balanced representations and achieves state-of-the-art performance on 24 of them. These results underscore the importance of balanced spectral supervision for learning transferable EEG representations.

cs.LG↗

arXiv2025

EEG-Based Cognitive Load Classification During Landmark-Based VR Navigation

Brain computer interfaces enable real-time monitoring of cognitive load, but their effectiveness in dynamic navigation contexts is not well established. Using an existing VR navigation dataset, we examined whether EEG signals can classify cognitive load during map-based wayfinding and whether classification accuracy depends more on task complexity or on individual traits. EEG recordings from forty-six participants navigating routes with 3, 5, or 7 map landmarks were analyzed with a nested cross-validation framework across multiple machine learning models. Classification achieved mean accuracies up to 90.8% for binary contrasts (3 vs. 7 landmarks) and 78.7% for the three-class problem, both well above chance. Demographic and cognitive variables (age, gender, spatial ability, working memory) showed no significant influence. These findings demonstrate that task demands outweigh individual differences in shaping classification performance, highlighting the potential for task-adaptive navigation systems that dynamically adjust map complexity in response to real-time cognitive states.

cs.HC↗

arXiv2025

Neuromorphic Deployment of Spiking Neural Networks for Cognitive Load Classification in Air Traffic Control

This paper presents a neuromorphic system for cognitive load classification in a real-world setting, an Air Traffic Control (ATC) task, using a hardware implementation of Spiking Neural Networks (SNNs). Electroencephalogram (EEG) and eye-tracking features, extracted from an open-source dataset, were used to train and evaluate both conventional machine learning models and SNNs. Among the SNN architectures explored, a minimalistic, single-layer model trained with a biologically inspired delta-rule learning algorithm achieved competitive performance (80.6%). To enable deployment on neuromorphic hardware, the model was quantized and implemented on the mixed-signal DYNAP-SE chip. Despite hardware constraints and analog variability, the chip-deployed SNN maintained a classification accuracy of up to 73.5% using spike-based input. These results demonstrate the feasibility of event-driven neuromorphic systems for ultra-low-power, embedded cognitive state monitoring in dynamic real-world scenarios.

cs.NE↗

arXiv2025

Spiking Neural Networks for Mental Workload Classification with a Multimodal Approach

Accurately assessing mental workload is crucial in cognitive neuroscience, human-computer interaction, and real-time monitoring, as cognitive load fluctuations affect performance and decision-making. While Electroencephalography (EEG) based machine learning (ML) models can be used to this end, their high computational cost hinders embedded real-time applications. Hardware implementations of spiking neural networks (SNNs) offer a promising alternative for low-power, fast, event-driven processing. This study compares hardware compatible SNN models with various traditional ML ones, using an open-source multimodal dataset. Our results show that multimodal integration improves accuracy, with SNN performance comparable to the ML one, demonstrating their potential for real-time implementations of cognitive load detection. These findings position event-based processing as a promising solution for low-latency, energy efficient workload monitoring in adaptive closed-loop embedded devices that dynamically regulate cognitive load.

cs.NE↗