Tzyy-Ping Jung

Yuhong Zhang, Qin Li, Sujal Nahata et al.

With the recent proliferation of large language models (LLMs), such as Generative Pre-trained Transformers (GPT), there has been a significant shift in exploring human and machine comprehension of semantic language meaning. This shift calls for interdisciplinary research that bridges cognitive science and natural language processing (NLP). This pilot study aims to provide insights into individuals' neural states during a semantic relation reading-comprehension task. We propose jointly analyzing LLMs, eye-gaze, and electroencephalographic (EEG) data to study how the brain processes words with varying degrees of relevance to a keyword during reading. We also use a feature engineering approach to improve the fixation-related EEG data classification while participants read words with high versus low relevance to the keyword. The best validation accuracy in this word-level classification is over 60\% across 12 subjects. Words of high relevance to the inference keyword had significantly more eye fixations per word: 1.0584 compared to 0.6576 when excluding no-fixation words, and 1.5126 compared to 1.4026 when including them. This study represents the first attempt to classify brain states at a word level using LLM knowledge. It provides valuable insights into human cognitive abilities and the realm of Artificial General Intelligence (AGI), and offers guidance for developing potential reading-assisted technologies.

Jane Hanqi Li, Yuhong Zhang, Jiaqi Liu et al.

The use of generative AI (genAI) tools as informal tutors is becoming increasingly prevalent among secondary school students in mathematics learning. In many schools, individualized instructional support is limited, and one-on-one human tutoring remains costly in most learning contexts. GenAI has the potential to provide timely, on-demand help to students when teachers or tutors are not available. However, there are still few studies that examine students' preferences for AI tutor support that enhances autonomous learning. We investigated learner expectations for AI tutoring through a survey with secondary school students in China (Grades 7-11; N=330). Students generally preferred support that preserves learner autonomy (e.g., time to think, hints over direct answers), expressed mixed or cautious preferences between human and AI tutors, and held nuanced views of proactive intervention, valuing adaptivity but also worrying about annoyance and autonomy. Privacy boundaries were uneven: many accepted sharing problem steps and error patterns, while willingness dropped for more sensitive signals such as attention or behavior. Our findings offer learner-centered insights for designing AI tutors that balance timely intervention with student agency, and personalization with perceived boundaries in a K-12 context.

Yuhong Zhang, Xusheng Zhu, Yuchen Xu et al.

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.

Yuhong Zhang, Jialu Li, Shilai Yang et al.

Reading comprehension is a fundamental skill in human cognitive development. With the advancement of Large Language Models (LLMs), there is a growing need to compare how humans and LLMs understand language across different contexts and apply this understanding to functional tasks such as inference, emotion interpretation, and information retrieval. Our previous work used LLMs and human biomarkers to study the reading comprehension process. The results showed that the biomarkers corresponding to words with high and low relevance to the inference target, as labeled by the LLMs, exhibited distinct patterns, particularly when validated using eye-tracking data. However, focusing solely on individual words limited the depth of understanding, which made the conclusions somewhat simplistic despite their potential significance. This study used an LLM-based AI agent to group words from a reading passage into nodes and edges, forming a graph-based text representation based on semantic meaning and question-oriented prompts. We then compare the distribution of eye fixations on important nodes and edges. Our findings indicate that LLMs exhibit high consistency in language understanding at the level of graph topological structure. These results build on our previous findings and offer insights into effective human-AI co-learning strategies.

Siwen Wang, Shitou Zhang, Wan-Lin Chen et al.

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.

Kuan-Jung Chiang, Steven Dong, Chung-Kuan Cheng et al.

Objective: The Electroencephalogram (EEG) is gaining popularity as a physiological measure for neuroergonomics in human factor studies because it is objective, less prone to bias, and capable of assessing the dynamics of cognitive states. This study investigated the associations between memory workload and EEG during participants' typical office tasks on a single-monitor and dual-monitor arrangement. We expect a higher memory workload for the single-monitor arrangement. Approach: We designed an experiment that mimics the scenario of a subject performing some office work and examined whether the subjects experienced various levels of memory workload in two different office setups: 1) a single-monitor setup and 2) a dual-monitor setup. We used EEG band power, mutual information, and coherence as features to train machine learning models to classify high versus low memory workload states. Main results: The study results showed that these characteristics exhibited significant differences that were consistent across all participants. We also verified the robustness and consistency of these EEG signatures in a different data set collected during a Sternberg task in a prior study. Significance: The study found the EEG correlates of memory workload across individuals, demonstrating the effectiveness of using EEG analysis in conducting real-world neuroergonomic studies.

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.

Kuan-Jung Chiang, Chun-Shu Wei, Masaki Nakanishi et al.

Objective: This study aims to establish a generalized transfer-learning framework for boosting the performance of steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) by leveraging cross-domain data transferring. Approach: We enhanced the state-of-the-art template-based SSVEP decoding through incorporating a least-squares transformation (LST)-based transfer learning to leverage calibration data across multiple domains (sessions, subjects, and EEG montages). Main results: Study results verified the efficacy of LST in obviating the variability of SSVEPs when transferring existing data across domains. Furthermore, the LST-based method achieved significantly higher SSVEP-decoding accuracy than the standard task-related component analysis (TRCA)-based method and the non-LST naive transfer-learning method. Significance: This study demonstrated the capability of the LST-based transfer learning to leverage existing data across subjects and/or devices with an in-depth investigation of its rationale and behavior in various circumstances. The proposed framework significantly improved the SSVEP decoding accuracy over the standard TRCA approach when calibration data are limited. Its performance in calibration reduction could facilitate plug-and-play SSVEP-based BCIs and further practical applications.

Lubin Meng, Jian Huang, Zhigang Zeng et al.

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is implementable in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it.

Daniel H. Lee, Tzyy-Ping Jung

The objective of this study is to develop and use a virtual reality game as a tool to assess the effects of realistic stress on the behavioral and physiological responses of participants. The game is based on a popular Steam game called Keep Talking Nobody Explodes, where the player collaborates with another person to defuse a bomb. Varying levels of difficulties in solving a puzzle and time pressures will result in different stress levels that can be measured in terms of errors, response time lengths, and other physiological measurements. The game was developed using 3D programming tools including Blender and virtual reality development kit (VRTK). To measure response times accurately, we added LSL (Lab Stream Layer) Markers to collect and synchronize physiological signals, behavioral data, and the timing of game events. We recorded Electrocardiogram (ECG) data during gameplay to assess heart rate and heart-rate variability (HRV) that have been shown as reliable indicators of stress. Our empirical results showed that heart rate increased significantly while HRV reduced significantly when the participants under high stress, which are consistent with the prior mainstream stress research. We further experimented with other tools to enhance communication between two players under adverse conditions and found that an automatic speech recognition software effectively enhanced the communication between the players by displaying keywords into the player's headset that lead to the facilitation of finding the solution of the puzzles or modules. This VR game framework is publicly available in Github and allows researchers to measure and synchronize other physiological signals such as electroencephalogram, electromyogram, and pupillometry.

Xiao Zhang, Dongrui Wu, Lieyun Ding et al.

An electroencephalogram (EEG) based brain-computer interface (BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g., amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a computer. Most studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e., they can be severely attacked by adversarial perturbations, which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.

Xiaotong Gu, Zehong Cao, Alireza Jolfaei et al.

Brain-Computer Interface (BCI) is a powerful communication tool between users and systems, which enhances the capability of the human brain in communicating and interacting with the environment directly. Advances in neuroscience and computer science in the past decades have led to exciting developments in BCI, thereby making BCI a top interdisciplinary research area in computational neuroscience and intelligence. Recent technological advances such as wearable sensing devices, real-time data streaming, machine learning, and deep learning approaches have increased interest in electroencephalographic (EEG) based BCI for translational and healthcare applications. Many people benefit from EEG-based BCIs, which facilitate continuous monitoring of fluctuations in cognitive states under monotonous tasks in the workplace or at home. In this study, we survey the recent literature of EEG signal sensing technologies and computational intelligence approaches in BCI applications, compensated for the gaps in the systematic summary of the past five years (2015-2019). In specific, we first review the current status of BCI and its significant obstacles. Then, we present advanced signal sensing and enhancement technologies to collect and clean EEG signals, respectively. Furthermore, we demonstrate state-of-art computational intelligence techniques, including interpretable fuzzy models, transfer learning, deep learning, and combinations, to monitor, maintain, or track human cognitive states and operating performance in prevalent applications. Finally, we deliver a couple of innovative BCI-inspired healthcare applications and discuss some future research directions in EEG-based BCIs.

Sharaj Panwar, Paul Rad, Tzyy-Ping Jung et al.

Electroencephalography (EEG) data are difficult to obtain due to complex experimental setups and reduced comfort with prolonged wearing. This poses challenges to train powerful deep learning model with the limited EEG data. Being able to generate EEG data computationally could address this limitation. We propose a novel Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) to synthesize EEG data. This network addresses several modeling challenges of simulating time-series EEG data including frequency artifacts and training instability. We further extended this network to a class-conditioned variant that also includes a classification branch to perform event-related classification. We trained the proposed networks to generate one and 64-channel data resembling EEG signals routinely seen in a rapid serial visual presentation (RSVP) experiment and demonstrated the validity of the generated samples. We also tested intra-subject cross-session classification performance for classifying the RSVP target events and showed that class-conditioned WGAN-GP can achieve improved event-classification performance over EEGNet.

Siddharth Siddharth, Tzyy-Ping Jung, Terrence J. Sejnowski

In recent years, the use of bio-sensing signals such as electroencephalogram (EEG), electrocardiogram (ECG), etc. have garnered interest towards applications in affective computing. The parallel trend of deep-learning has led to a huge leap in performance towards solving various vision-based research problems such as object detection. Yet, these advances in deep-learning have not adequately translated into bio-sensing research. This work applies novel deep-learning-based methods to various bio-sensing and video data of four publicly available multi-modal emotion datasets. For each dataset, we first individually evaluate the emotion-classification performance obtained by each modality. We then evaluate the performance obtained by fusing the features from these modalities. We show that our algorithms outperform the results reported by other studies for emotion/valence/arousal/liking classification on DEAP and MAHNOB-HCI datasets and set up benchmarks for the newer AMIGOS and DREAMER datasets. We also evaluate the performance of our algorithms by combining the datasets and by using transfer learning to show that the proposed method overcomes the inconsistencies between the datasets. Hence, we do a thorough analysis of multi-modal affective data from more than 120 subjects and 2,800 trials. Finally, utilizing a convolution-deconvolution network, we propose a new technique towards identifying salient brain regions corresponding to various affective states.

Kuan-Jung Chiang, Chun-Shu Wei, Masaki Nakanishi et al.

Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs) have shown its robustness in facilitating high-efficiency communication. State-of-the-art training-based SSVEP decoding methods such as extended Canonical Correlation Analysis (CCA) and Task-Related Component Analysis (TRCA) are the major players that elevate the efficiency of the SSVEP-based BCIs through a calibration process. However, due to notable human variability across individuals and within individuals over time, calibration (training) data collection is non-negligible and often laborious and time-consuming, deteriorating the practicality of SSVEP BCIs in a real-world context. This study aims to develop a cross-subject transferring approach to reduce the need for collecting training data from a test user with a newly proposed least-squares transformation (LST) method. Study results show the capability of the LST in reducing the number of training templates required for a 40-class SSVEP BCI. The LST method may lead to numerous real-world applications using near-zero-training/plug-and-play high-speed SSVEP BCIs.

Siddharth Siddharth, Tzyy-Ping Jung, Terrence J. Sejnowski

Throughout the past decade, many studies have classified human emotions using only a single sensing modality such as face video, electroencephalogram (EEG), electrocardiogram (ECG), galvanic skin response (GSR), etc. The results of these studies are constrained by the limitations of these modalities such as the absence of physiological biomarkers in the face-video analysis, poor spatial resolution in EEG, poor temporal resolution of the GSR etc. Scant research has been conducted to compare the merits of these modalities and understand how to best use them individually and jointly. Using multi-modal AMIGOS dataset, this study compares the performance of human emotion classification using multiple computational approaches applied to face videos and various bio-sensing modalities. Using a novel method for compensating physiological baseline we show an increase in the classification accuracy of various approaches that we use. Finally, we present a multi-modal emotion-classification approach in the domain of affective computing research.

Siddharth, Aashish Patel, Tzyy-Ping Jung et al.

We present a novel multi-modal bio-sensing platform capable of integrating multiple data streams for use in real-time applications. The system is composed of a central compute module and a companion headset. The compute node collects, time-stamps and transmits the data while also providing an interface for a wide range of sensors including electroencephalogram, photoplethysmogram, electrocardiogram, and eye gaze among others. The companion headset contains the gaze tracking cameras. By integrating many of the measurements systems into an accessible package, we are able to explore previously unanswerable questions ranging from open-environment interactions to emotional response studies. Though some of the integrated sensors are designed from the ground-up to fit into a compact form factor, we validate the accuracy of the sensors and find that they perform similarly to, and in some cases better than, alternatives.

Dongrui Wu, Brent J. Lance, Vernon J. Lawhern et al.

Riemannian geometry has been successfully used in many brain-computer interface (BCI) classification problems and demonstrated superior performance. In this paper, for the first time, it is applied to BCI regression problems, an important category of BCI applications. More specifically, we propose a new feature extraction approach for Electroencephalogram (EEG) based BCI regression problems: a spatial filter is first used to increase the signal quality of the EEG trials and also to reduce the dimensionality of the covariance matrices, and then Riemannian tangent space features are extracted. We validate the performance of the proposed approach in reaction time estimation from EEG signals measured in a large-scale sustained-attention psychomotor vigilance task, and show that compared with the traditional powerband features, the tangent space features can reduce the root mean square estimation error by 4.30-8.30%, and increase the estimation correlation coefficient by 6.59-11.13%.

Dongrui Wu, Jung-Tai King, Chun-Hsiang Chuang et al.

Electroencephalogram (EEG) signals are frequently used in brain-computer interfaces (BCIs), but they are easily contaminated by artifacts and noises, so preprocessing must be done before they are fed into a machine learning algorithm for classification or regression. Spatial filters have been widely used to increase the signal-to-noise ratio of EEG for BCI classification problems, but their applications in BCI regression problems have been very limited. This paper proposes two common spatial pattern (CSP) filters for EEG-based regression problems in BCI, which are extended from the CSP filter for classification, by making use of fuzzy sets. Experimental results on EEG-based response speed estimation from a large-scale study, which collected 143 sessions of sustained-attention psychomotor vigilance task data from 17 subjects during a 5-month period, demonstrate that the two proposed spatial filters can significantly increase the EEG signal quality. When used in LASSO and k-nearest neighbors regression for user response speed estimation, the spatial filters can reduce the root mean square estimation error by 10.02-19.77%, and at the same time increase the correlation to the true response speed by 19.39-86.47%.

Zhilin Zhang, Tzyy-Ping Jung, Scott Makeig et al.

Energy consumption is an important issue in continuous wireless telemonitoring of physiological signals. Compressed sensing (CS) is a promising framework to address it, due to its energy-efficient data compression procedure. However, most CS algorithms have difficulty in data recovery due to non-sparsity characteristic of many physiological signals. Block sparse Bayesian learning (BSBL) is an effective approach to recover such signals with satisfactory recovery quality. However, it is time-consuming in recovering multichannel signals, since its computational load almost linearly increases with the number of channels. This work proposes a spatiotemporal sparse Bayesian learning algorithm to recover multichannel signals simultaneously. It not only exploits temporal correlation within each channel signal, but also exploits inter-channel correlation among different channel signals. Furthermore, its computational load is not significantly affected by the number of channels. The proposed algorithm was applied to brain computer interface (BCI) and EEG-based driver's drowsiness estimation. Results showed that the algorithm had both better recovery performance and much higher speed than BSBL. Particularly, the proposed algorithm ensured that the BCI classification and the drowsiness estimation had little degradation even when data were compressed by 80%, making it very suitable for continuous wireless telemonitoring of multichannel signals.

Zhilin Zhang, Bhaskar D. Rao, Tzyy-Ping Jung

As a lossy compression framework, compressed sensing has drawn much attention in wireless telemonitoring of biosignals due to its ability to reduce energy consumption and make possible the design of low-power devices. However, the non-sparseness of biosignals presents a major challenge to compressed sensing. This study proposes and evaluates a spatio-temporal sparse Bayesian learning algorithm, which has the desired ability to recover such non-sparse biosignals. It exploits both temporal correlation in each individual biosignal and inter-channel correlation among biosignals from different channels. The proposed algorithm was used for compressed sensing of multichannel electroencephalographic (EEG) signals for estimating vehicle drivers' drowsiness. Results showed that the drowsiness estimation was almost unaffected even if raw EEG signals (containing various artifacts) were compressed by 90%.

Zhilin Zhang, Tzyy-Ping Jung, Scott Makeig et al.

Telemonitoring of electroencephalogram (EEG) through wireless body-area networks is an evolving direction in personalized medicine. Among various constraints in designing such a system, three important constraints are energy consumption, data compression, and device cost. Conventional data compression methodologies, although effective in data compression, consumes significant energy and cannot reduce device cost. Compressed sensing (CS), as an emerging data compression methodology, is promising in catering to these constraints. However, EEG is non-sparse in the time domain and also non-sparse in transformed domains (such as the wavelet domain). Therefore, it is extremely difficult for current CS algorithms to recover EEG with the quality that satisfies the requirements of clinical diagnosis and engineering applications. Recently, Block Sparse Bayesian Learning (BSBL) was proposed as a new method to the CS problem. This study introduces the technique to the telemonitoring of EEG. Experimental results show that its recovery quality is better than state-of-the-art CS algorithms, and sufficient for practical use. These results suggest that BSBL is very promising for telemonitoring of EEG and other non-sparse physiological signals.

Zhilin Zhang, Tzyy-Ping Jung, Scott Makeig et al.

Fetal ECG (FECG) telemonitoring is an important branch in telemedicine. The design of a telemonitoring system via a wireless body-area network with low energy consumption for ambulatory use is highly desirable. As an emerging technique, compressed sensing (CS) shows great promise in compressing/reconstructing data with low energy consumption. However, due to some specific characteristics of raw FECG recordings such as non-sparsity and strong noise contamination, current CS algorithms generally fail in this application. This work proposes to use the block sparse Bayesian learning (BSBL) framework to compress/reconstruct non-sparse raw FECG recordings. Experimental results show that the framework can reconstruct the raw recordings with high quality. Especially, the reconstruction does not destroy the interdependence relation among the multichannel recordings. This ensures that the independent component analysis decomposition of the reconstructed recordings has high fidelity. Furthermore, the framework allows the use of a sparse binary sensing matrix with much fewer nonzero entries to compress recordings. Particularly, each column of the matrix can contain only two nonzero entries. This shows the framework, compared to other algorithms such as current CS algorithms and wavelet algorithms, can greatly reduce code execution in CPU in the data compression stage.