arXiv subjects

Dung Truong

Publications and source records attributed to Dung Truong.

14 recordsLinked to original sources

arXiv2026

EEGDash: An open-source platform for machine learning on public neurophysiological data

Public neurophysiological datasets are increasingly accessible but remain hard to reuse: turning one into a trained model still takes thousands of lines of code for download, loading, format repair, windowing, and evaluation, and a dataset that meets metadata standards can still fail to load. EEG-Dash is a software resource that catalogues 791 publicly archived recordings (39,778 participants, over 86,051 hours) spanning electroencephalography (EEG), magnetoencephalography (MEG), intracranial EEG (iEEG), electromyography (EMG), and functional near-infrared spectroscopy (fNIRS) from the OpenNeuro and NEMAR archives. It exposes each dataset as an importable, queryable class that preserves signal attributes and loads into machine-learning workflows without custom code, delegating signal handling to MNE-Python, windowing to Braindecode, and format compliance to the official Brain Imaging Data Structure (BIDS) validator. A metadata-first registry adds semantic search, a format-repair layer, automatic dataset-level tags drawn from each source publication, and a feature-extraction framework. The catalogue, with per-record loadability and compliance metadata, supports benchmarking, model development, and cross-dataset analysis.

q-bio.NC↗

arXiv2026

Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes

Scaling EEG foundation models requires pooling data across heterogeneous electrode montages, a prerequisite both for larger pretraining corpora and for downstream deployment. We present the first systematic comparison of four channel adaptation methods (Conv1d projection, spherical spline interpolation (SSI), source-space decomposition, and Riemannian re-centering) across five pretrained EEG foundation models (5M--157M parameters), five downstream tasks, and two training regimes with 10--15 random seeds each. We find that rigid-montage models (BENDR, Neuro-GPT) require external adaptation, while flexible models (EEGPT, CBraMod) match or exceed it natively when fine-tuned but benefit from external methods under frozen-encoder deployment. A probe-SFT asymmetry exists: external adaptation can cause severe negative transfer during fine-tuning of flexible models. The optimal method is architecture-dependent (Conv1d for BENDR, SSI/Riemannian for Neuro-GPT, source-space decomposition for depression detection), and 5M-parameter CBraMod outperforms models up to 31$\times$ larger on 4/5 datasets, consistent with independent findings that compact EEG-specific architectures can match larger models.

cs.LG↗

arXiv2025

Strategic Server Deployment under Uncertainty in Mobile Edge Computing

Server deployment is a fundamental task in mobile edge computing: where to place the edge servers and what user cells to assign to them. To make this decision is context-specific, but common goals are 1) computing efficiency: maximize the amount of workload processed by the edge, and 2) communication efficiency: minimize the communication cost between the cells and their assigned servers. We focus on practical scenarios where the user workload in each cell is unknown and time-varying, and so are the effective capacities of the servers. Our research problem is to choose a subset of candidate servers and assign them to the user cells such that the above goals are sustainably achieved under the above uncertainties. We formulate this problem as a stochastic bilevel optimization, which is strongly NP-hard and unseen in the literature. By approximating the objective function with submodular functions, we can utilize state-of-the-art greedy algorithms for submodular maximization to effectively solve our problem. We evaluate the proposed algorithm using real-world data, showing its superiority to alternative methods; the improvement can be as high as 55%

cs.DC↗

arXiv2025

RobustFSM: Submodular Maximization in Federated Setting with Malicious Clients

Submodular maximization is an optimization problem benefiting many machine learning applications, where we seek a small subset best representing an extremely large dataset. We focus on the federated setting where the data are locally owned by decentralized clients who have their own definitions for the quality of representability. This setting requires repetitive aggregation of local information computed by the clients. While the main motivation is to respect the privacy and autonomy of the clients, the federated setting is vulnerable to client misbehaviors: malicious clients might share fake information. An analogy is backdoor attack in conventional federated learning, but our challenge differs freshly due to the unique characteristics of submodular maximization. We propose RobustFSM, a federated submodular maximization solution that is robust to various practical client attacks. Its performance is substantiated with an empirical evaluation study using real-world datasets. Numerical results show that the solution quality of RobustFSM substantially exceeds that of the conventional federated algorithm when attacks are severe. The degree of this improvement depends on the dataset and attack scenarios, which can be as high as 200%

cs.LG↗

arXiv2025

EEG Foundation Challenge: From Cross-Task to Cross-Subject EEG Decoding

Current electroencephalogram (EEG) decoding models are typically trained on small numbers of subjects performing a single task. Here, we introduce a large-scale, code-submission-based competition comprising two challenges. First, the Transfer Challenge asks participants to build and test a model that can zero-shot decode new tasks and new subjects from their EEG data. Second, the Psychopathology factor prediction Challenge asks participants to infer subject measures of mental health from EEG data. For this, we use an unprecedented, multi-terabyte dataset of high-density EEG signals (128 channels) recorded from over 3,000 child to young adult subjects engaged in multiple active and passive tasks. We provide several tunable neural network baselines for each of these two challenges, including a simple network and demographic-based regression models. Developing models that generalise across tasks and individuals will pave the way for ML network architectures capable of adapting to EEG data collected from diverse tasks and individuals. Similarly, predicting mental health-relevant personality trait values from EEG might identify objective biomarkers useful for clinical diagnosis and design of personalised treatment for psychological conditions. Ultimately, the advances spurred by this challenge could contribute to the development of computational psychiatry and useful neurotechnology, and contribute to breakthroughs in both fundamental neuroscience and applied clinical research.

eess.SP↗

arXiv2025

Data Normalization Strategies for EEG Deep Learning

Normalization is a critical yet often overlooked component in the preprocessing pipeline for EEG deep learning applications. The rise of large-scale pretraining paradigms such as self-supervised learning (SSL) introduces a new set of tasks whose nature is substantially different from supervised training common in EEG deep learning applications. This raises new questions about optimal normalization strategies for the applicable task. In this study, we systematically evaluate the impact of normalization granularity (recording vs. window level) and scope (cross-channel vs. within-channel) on both supervised (age and gender prediction) and self-supervised (Contrastive Predictive Coding) tasks. Using high-density resting-state EEG from 2,836 subjects in the Healthy Brain Network dataset, we show that optimal normalization strategies differ significantly between training paradigms. Window-level within-channel normalization yields the best performance in supervised tasks, while minimal or cross-channel normalization at the window level is more effective for SSL. These results underscore the necessity of task-specific normalization choices and challenge the assumption that a universal normalization strategy can generalize across learning settings. Our findings provide practical insights for developing robust EEG deep learning pipelines as the field shifts toward large-scale, foundation model training.

eess.SP↗

arXiv2025

From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data

Recent advancements in Large Language Models have inspired the development of foundation models across various domains. In this study, we evaluate the efficacy of Large EEG Models (LEMs) by fine-tuning LaBraM, a state-of-the-art foundation EEG model, on a real-world stress classification dataset collected in a graduate classroom. Unlike previous studies that primarily evaluate LEMs using data from controlled clinical settings, our work assesses their applicability to real-world environments. We train a binary classifier that distinguishes between normal and elevated stress states using resting-state EEG data recorded from 18 graduate students during a class session. The best-performing fine-tuned model achieves a balanced accuracy of 90.47% with a 5-second window, significantly outperforming traditional stress classifiers in both accuracy and inference efficiency. We further evaluate the robustness of the fine-tuned LEM under random data shuffling and reduced channel counts. These results demonstrate the capability of LEMs to effectively process real-world EEG data and highlight their potential to revolutionize brain-computer interface applications by shifting the focus from model-centric to data-centric design.

cs.LG↗

arXiv2024

Automatic EEG Independent Component Classification Using ICLabel in Python

ICLabel is an important plug-in function in EEGLAB, the most widely used software for EEG data processing. A powerful approach to automated processing of EEG data involves decomposing the data by Independent Component Analysis (ICA) and then classifying the resulting independent components (ICs) using ICLabel. While EEGLAB pipelines support high-performance computing (HPC) platforms running the open-source Octave interpreter, the ICLabel plug-in is incompatible with Octave because of its specialized neural network architecture. To enhance cross-platform compatibility, we developed a Python version of ICLabel that uses standard EEGLAB data structures. We compared ICLabel MATLAB and Python implementations to data from 14 subjects. ICLabel returns the likelihood of classification in 7 classes of components for each ICA component. The returned IC classifications were virtually identical between Python and MATLAB, with differences in classification percentage below 0.001%.

eess.SP↗

arXiv2024

Hierarchical Event Descriptor library schema for EEG data annotation

Standardizing terminology to annotate electrophysiological events can improve both computational research and clinical care. Sharing data enriched with standard terms can facilitate data exploration, from case studies to mega-analyses. The machine readability of such electrophysiological event annotations is essential for performing analyses efficiently across software tools and packages. Hierarchical Event Descriptors (HED) provide a framework for describing events in neuroscience experiments. HED library schemas extend the standard HED schema vocabulary to include specialized vocabularies, such as standardized clinical terms for electrophysiological events. The Standardized Computer-based Organized Reporting of EEG (SCORE) defines terms for annotating EEG events, including artifacts. This study developed a HED library schema for SCORE, making the terms machine-readable. We demonstrate that the HED-SCORE library schema can be used to annotate events in EEG data stored in the Brain Imaging Data Structure (BIDS). Clinicians and researchers worldwide can now use the HED-SCORE library schema to annotate and compute on electrophysiological data obtained from the human brain.

q-bio.NC↗

arXiv2023

Deep learning applied to EEG data with different montages using spatial attention

The ability of Deep Learning to process and extract relevant information in complex brain dynamics from raw EEG data has been demonstrated in various recent works. Deep learning models, however, have also been shown to perform best on large corpora of data. When processing EEG, a natural approach is to combine EEG datasets from different experiments to train large deep-learning models. However, most EEG experiments use custom channel montages, requiring the data to be transformed into a common space. Previous methods have used the raw EEG signal to extract features of interest and focused on using a common feature space across EEG datasets. While this is a sensible approach, it underexploits the potential richness of EEG raw data. Here, we explore using spatial attention applied to EEG electrode coordinates to perform channel harmonization of raw EEG data, allowing us to train deep learning on EEG data using different montages. We test this model on a gender classification task. We first show that spatial attention increases model performance. Then, we show that a deep learning model trained on data using different channel montages performs significantly better than deep learning models trained on fixed 23- and 128-channel data montages.

cs.LG↗

arXiv2022

A streamable large-scale clinical EEG dataset for Deep Learning

Deep Learning has revolutionized various fields, including Computer Vision, Natural Language Processing, as well as Biomedical research. Within the field of neuroscience, specifically in electrophysiological neuroimaging, researchers are starting to explore leveraging deep learning to make predictions on their data without extensive feature engineering. The availability of large-scale datasets is a crucial aspect of allowing the experimentation of Deep Learning models. We are publishing the first large-scale clinical EEG dataset that simplifies data access and management for Deep Learning. This dataset contains eyes-closed EEG data prepared from a collection of 1,574 juvenile participants from the Healthy Brain Network. We demonstrate a use case integrating this framework, and discuss why providing such neuroinformatics infrastructure to the community is critical for future scientific discoveries.

cs.LG↗

arXiv2022

NEMAR: An open access data, tools, and compute resource operating on NeuroElectroMagnetic data

To take advantage of recent and ongoing advances in large-scale computational methods, and to preserve the scientific data created by publicly funded research projects, data archives must be created as well as standards for specifying, identifying, and annotating deposited data. The OpenNeuro.org archive, begun as a repository for magnetic resonance imaging (MRI) data, is such an archive. We present a gateway to OpenNeuro for human electrophysiology data (BIDS-formatted EEG and MEG, as well as intracranial data). The NEMAR gateway allows users to visualize electrophysiological data, including time-domain and frequency-domain dynamics time locked to sets of experimental events recorded using BIDS- and HED-formatted data annotation. In addition, NEMAR allows users to process archived EEG data on the XSEDE high-performance resources at SDSC in conjunction with the Neuroscience Gateway (nsgportal.org), a freely available and easy to use portal to leverage high-performance computing resources for neuroscience research.

q-bio.QM↗

arXiv2021

Assessing learned features of Deep Learning applied to EEG

Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc. These achievements benefit from the CNNs' outstanding capability to learn discriminative features with deep layers of neuron structures and iterative training process. This has inspired the EEG research community to adopt CNN in performing EEG classification tasks. However, CNNs learned features are not immediately interpretable, causing a lack of understanding of the CNNs' internal working mechanism. To improve CNN interpretability, CNN visualization methods are applied to translate the internal features into visually perceptible patterns for qualitative analysis of CNN layers. Many CNN visualization methods have been proposed in the Computer Vision literature to interpret the CNN network structure, operation, and semantic concept, yet applications to EEG data analysis have been limited. In this work we use 3 different methods to extract EEG-relevant features from a CNN trained on raw EEG data: optimal samples for each classification category, activation maximization, and reverse convolution. We applied these methods to a high-performing Deep Learning model with state-of-the-art performance for an EEG sex classification task, and show that the model features a difference in the theta frequency band. We show that visualization of a CNN model can reveal interesting EEG results. Using these tools, EEG researchers using Deep Learning can better identify the learned EEG features, possibly identifying new class relevant biomarkers.

cs.LG↗

arXiv2021

Deep Convolutional Neural Network Applied to Electroencephalography: Raw Data vs Spectral Features

The success of deep learning in computer vision has inspired the scientific community to explore new analysis methods. Within the field of neuroscience, specifically in electrophysiological neuroimaging, researchers are starting to explore leveraging deep learning to make predictions on their data without extensive feature engineering. This paper compares deep learning using minimally processed EEG raw data versus deep learning using EEG spectral features using two different deep convolutional neural architectures. One of them from Putten et al. (2018) is tailored to process raw data; the other was derived from the VGG16 vision network (Simonyan and Zisserman, 2015) which is designed to process EEG spectral features. We apply them to classify sex on 24-channel EEG from a large corpus of 1,574 participants. Not only do we improve on state-of-the-art classification performance for this type of classification problem, but we also show that in all cases, raw data classification leads to superior performance as compared to spectral EEG features. Interestingly we show that the neural network tailored to process EEG spectral features has increased performance when applied to raw data classification. Our approach suggests that the same convolutional networks used to process EEG spectral features yield superior performance when applied to EEG raw data.

cs.LG↗