About

Dr. Hyuk Oh is an Assistant Research Professor at the University of Maryland's School of Public Health, within the Department of Kinesiology. His research focuses on studying the relationship between brain activity and specific cognitive, affective, and motor functions through the use of various functional neuroimaging and computational approaches. He investigates neural modeling, computations, and simulations that contribute to cognitive-motor performance. Additionally, Dr. Oh conducts research on the impact of brain injuries such as traumatic brain injury (TBI) and post-traumatic stress disorder (PTSD) on the brain and mental health. His academic background includes a Ph.D. in Neuroscience and Cognitive Science from the University of Maryland, an M.S. in Computer Science from the University of Southern California, and a B.S. in Computer Science from Seoul National University.

Research topics

• Computer Science
• Psychology
• Human–computer interaction
• Engineering
• Developmental psychology
• Geography
• Neuroscience
• Simulation
• Cognitive psychology
• Social psychology

Selected publications

• Performance and mental workload dynamics during in-person and virtually-based remote learning of action sequences

  Figshare · 2026-04-16

  articleOpen access

  Despite numerous motor learning studies, none investigated performance and mental workload during in-person and remote practice of sequential tasks. This study examined these dynamics during in-person and virtual-based remote learning of goal-oriented action sequences (i.e. the Tower of Hanoi task). Performance and mental workload were assessed <i>via</i> the Levenshtein distance and NASA Task Load Index, respectively. Besides traditional group-based analyses, cluster-based examinations were conducted to identify individual performance patterns. Results revealed that both in-person and remote learning improved performance, reduced mental workload, and enhanced cognitive-motor efficiency. However, performance improved faster in the remote group, potentially by facilitating executive functioning <i>via</i> reduced anxiety and fine sensorimotor control demands. Slower improvement in the in-person group was likely driven by greater variability in performance, with some individuals unable to achieve optimal performance by late practice. These findings can inform human cognitive-motor behaviour during remote learning with implications for tele-robotics and tele-health. Although remote learning is important for applications such as tele-health and tele-robotics, it is unclear how it differs from in-person learning. This work examines performance and mental workload evolution throughout in-person and remote learning. Both learning modalities attenuated mental workload while performance was enhanced albeit more slowly for in-person learning.

  PublisherDOI

• Neurocognitive and Autonomic Signatures of Performance Under Motivational Stress: An Integrated Psychophysiological Analysis of Reward and Punishment in Shooting Performance

  Scandinavian Journal of Medicine and Science in Sports · 2026-02-01 · 2 citations

  articleOpen access

  Motivational framing-such as reward and punishment-critically shapes performance under pressure, yet the underlying neurocognitive and autonomic mechanisms remain unclear. Guided by the cognitive-affective-motor (CAM) model and psychomotor efficiency theory (PET), this study examined how motivational context modulates brain-body dynamics during high-pressure precision performance. Using a within-subject design, elite marksmen performed a simulated shooting task under reward, punishment, and neutral conditions. Neurophysiological markers were assessed across four domains: affective regulation (frontal alpha asymmetry [FAA], eyeblink startle [EBS]), cognitive control (feedback-related negativity [fERN], frontal midline theta), motor readiness (sensorimotor rhythm [SMR], fronto-temporal coherence), and autonomic flexibility (heart rate variability [HRV]). Reward framing elicited a coordinated brain-body state marked by elevated SMR and HRV, greater left-frontal activation, and reduced fERN and coherence-supporting focus, emotional control, and movement stability. Punishment elicited defensive arousal, heightened error sensitivity, and disrupted cortical communication, particularly in lower performers. These results demonstrate that motivational incentives recalibrate neurocognitive and autonomic systems, shaping performance resilience or vulnerability. The identified markers represent viable targets for neurofeedback and biofeedback interventions aimed at enhancing resilience, attentional control, and execution in elite sport performance.

  PublisherOA PDFDOI

• Performance and mental workload dynamics during in-person and virtually-based remote learning of action sequences

  Figshare · 2026-04-16

  articleOpen access

  Despite numerous motor learning studies, none investigated performance and mental workload during in-person and remote practice of sequential tasks. This study examined these dynamics during in-person and virtual-based remote learning of goal-oriented action sequences (i.e. the Tower of Hanoi task). Performance and mental workload were assessed <i>via</i> the Levenshtein distance and NASA Task Load Index, respectively. Besides traditional group-based analyses, cluster-based examinations were conducted to identify individual performance patterns. Results revealed that both in-person and remote learning improved performance, reduced mental workload, and enhanced cognitive-motor efficiency. However, performance improved faster in the remote group, potentially by facilitating executive functioning <i>via</i> reduced anxiety and fine sensorimotor control demands. Slower improvement in the in-person group was likely driven by greater variability in performance, with some individuals unable to achieve optimal performance by late practice. These findings can inform human cognitive-motor behaviour during remote learning with implications for tele-robotics and tele-health. Although remote learning is important for applications such as tele-health and tele-robotics, it is unclear how it differs from in-person learning. This work examines performance and mental workload evolution throughout in-person and remote learning. Both learning modalities attenuated mental workload while performance was enhanced albeit more slowly for in-person learning.

  PublisherDOI

• A physics-based rigid-body model of motion-induced electromagnetic harmonic artifacts in surface biosignals

  Journal of Neural Engineering · 2026-01-26

  articleOpen access1st authorCorresponding

  Motion-induced electromagnetic interference remains a major obstacle to the accurate interpretation of surface-recorded biosignals collected during movement. This study presented a physics-based rigid-body model that integrated electromagnetic theory with a kinematic framework to describe the generation of motion-induced artifacts in surface biosignals through electromagnetic induction. The model was derived from Faraday's law and a 6D rigid-body kinematic formulation, which coupled rotational and translational motion to spatial magnetic-field gradients and curvature. This formulation predicted that any conductive loop moving within a nonuniform magnetic field produced a time-varying electromotive force (EMF) determined by the interaction between motion, field geometry, and sensor orientation. To illustrate and validate the theoretical model, computational simulations reproduced treadmill locomotion under two conditions: (1) an idealized fixed-cadence case with time-invariant field gradients, and (2) a realistic varying-cadence case incorporating stride-to-stride jitter and event-related spectral perturbation baseline correction. The simulated EMF spectra exhibited motion-locked harmonic patterns extending up to 15 Hz with electrode-dependent variations in magnitude and broadened harmonic envelopes, closely matching empirical treadmill electroencephalography spectra. Accelerometer spectra displayed broader harmonic content up to 50 Hz, consistent with their direct measurement of kinematic oscillations. Quantitative decomposition further revealed that rotational motion dominated the induced EMF, with smaller, electrode-dependent contributions from translation. Robustness analyses indicated that dominant harmonic structure is preserved under multi-axis kinematics and increased magnetic-field complexity, with greater sensitivity confined to weaker higher-order components. These results demonstrated that harmonic contamination could emerge naturally from rigid-body motion in a spatially varying magnetic field, providing a physics-based foundation for interpreting motion artifacts in surface electrical potentials and motivating practical mitigation strategies that incorporate motion and magnetic-field measurements. Through principled understanding and physics-based modeling of motion-induced electromagnetic artifacts, this framework supports interpretation of surface biosignals during movement and motivates the development of mitigation algorithms.

  PublisherDOI

• Performance and mental workload dynamics during in-person and virtually-based remote learning of action sequences

  Ergonomics · 2026-04-16

  article

  PRACTITIONER SUMMARY: Although remote learning is important for applications such as tele-health and tele-robotics, it is unclear how it differs from in-person learning. This work examines performance and mental workload evolution throughout in-person and remote learning. Both learning modalities attenuated mental workload while performance was enhanced albeit more slowly for in-person learning.

  PublisherDOI

• RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation

  2025-06-21 · 4 citations

  articleOpen accessSenior author

  This paper introduces a learning-based visual planner for agile drone flight in cluttered environments.The proposed planner generates collision-free waypoints in milliseconds, enabling drones to perform agile maneuvers in complex environments without building separate perception, mapping, and planning modules.Learning-based methods, such as behavior cloning (BC) and reinforcement learning (RL), demonstrate promising performance in visual navigation but still face inherent limitations.BC is susceptible to compounding errors due to limited expert imitation, while RL struggles with reward function design and sample inefficiency.To address these limitations, this paper proposes an inverse reinforcement learning (IRL)based framework for high-speed visual navigation.By leveraging IRL, it is possible to reduce the number of interactions with simulation environments and improve capability to deal with high-dimensional spaces (i.e., visual information) while preserving the robustness of RL policies.A motion primitivebased path planning algorithm collects an expert dataset with privileged map data from diverse environments (e.g., narrow gaps, cubes, spheres, trees), ensuring comprehensive scenario coverage.By leveraging both the acquired expert and learner dataset gathered from the agent's interactions with the simulation environments, a robust reward function and policy are learned across diverse states.While the proposed method is trained in a simulation environment only, it can be directly applied to real-world scenarios without additional training or tuning.The performance of the proposed method is validated in both simulation and real-world environments, including forests and various structures.The trained policy achieves an average speed of 7 m/s and a maximum speed of 8.8 m/s in real flight experiments.To the best of our knowledge, this is the first work to successfully apply an IRL framework for high-speed visual navigation of drones.The experimental videos can be found at https://youtu.be/ZfV6ij0qZMI.

  PublisherDOI

• Between Languages, Beyond Words: Emotional Expression and Code-Switching in Bilinguals

  Scholarly review . · 2025-09-02

  articleOpen access1st authorCorresponding

  Code-switching, the alternation between two or more languages within a single interaction, is a ubiquitous feature of bilingual communication traditionally examined through linguistic or cognitive lenses. However, growing evidence reveals that code-switching also serves critical emotional functions, allowing bilingual speakers to express, regulate, and modulate emotions in context-sensitive ways. This literature review synthesizes interdisciplinary research from sociolinguistics, psycholinguistics, and neurocognitive studies to explore the emotional dimensions of code-switching. It highlights how language choice is influenced by emotional resonance, cultural identity, and interpersonal goals, and demonstrates how code-switching facilitates emotional authenticity, psychological distancing, and social intimacy. Practical implications are discussed across educational, therapeutic, and professional settings, with attention to how emotional code-switching enhances communication and belonging. The review concludes by identifying key gaps in current research—such as understudied language pairs, age-related patterns, and the need for longitudinal studies—and proposes future directions that leverage technological advancements to deepen our understanding of bilingual emotional life.

  PublisherOA PDFDOI

• Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling

  2025-08-17 · 1 citations

  article
  PublisherDOI

• Campus-Scale Waste Collection Challenge: A Unified Framework for Robotic Perception, Navigation, and Manipulation

  2025-08-27

  article1st authorCorresponding

  This paper introduces the Campus-Scale Waste Collection Challenge, a simulation-based benchmark for autonomous mobile manipulation in outdoor environments with perceptual uncertainty. Built in NVIDIA Isaac Sim as a digital twin of a real university campus, the environment includes diverse terrain, dynamic obstacles, and variable lighting. Participants must detect, localize, and classify waste using partial CCTV observations, and perform full pick-and-place tasks with wheeled manipulators. A ROS 2-based API enables integration of perception, planning, and control modules. The challenge evaluates performance across perception, navigation, and manipulation stages using metrics such as accuracy, success rate, and execution time. A baseline implementation, dataset, and imitation learning pipeline are provided to support reproducibility and development. This testbed promotes robust, scalable solutions for real-world service robotics.

  PublisherDOI

• Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling

  ArXiv.org · 2025-08-08

  preprintOpen access

  Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing enrollment-free methods capable of identifying targets without explicit speaker labeling. This work introduces a new approach to train simultaneous speech separation and diarization using automatic identification of target speaker embeddings, within mixtures. Our proposed model employs a dual-stage training pipeline designed to learn robust speaker representation features that are resilient to background noise interference. Furthermore, we present an overlapping spectral loss function specifically tailored for enhancing diarization accuracy during overlapped speech frames. Experimental results show significant performance gains compared to the current SOTA baseline, achieving 71% relative improvement in DER and 69% in cpWER.

  PublisherOA PDFDOI

Frequent coauthors

• Rodolphe J. Gentili

  University of Maryland, College Park

  31 shared

• Bradley D. Hatfield

  University of Maryland, College Park

  16 shared

• Jeremy C. Rietschel

  12 shared

• José L. Contreras-Vidal

  University of Houston

  12 shared

• James A. Reggia

  11 shared

• Li‐Chuan Lo

  University of Maryland, College Park

  8 shared

• Kyle J. Jaquess

  Veterans Health Administration

  8 shared

• Ying Tan

  University of Melbourne

  7 shared