Sanghyun Choo
Ph.D. Student
- Email: schoo2@ncsu.edu
- Office: 4101 Fitts-Woolard Hall
I am a Ph.D. student in Industrial and Systems Engineering at NC State University since 2018. My research interests include brain-computer interface (BCI), machine learning, deep learning, interactive reinforcement learning (IRL), and neuroergonomics. I am currently developing (1) regularization methods for enhancing EEG classifiers using data augmentation and adaptive batch-
size sampling (2) uncertainty-aware action advising framework for IRL to reduce sample complexity of deep reinforcement learning.
Artificial Intelligence
EEG-based Cognitive States Recognition: Deep Learning Approaches
This research aims to detect/predict cognitive states such as human emotion and human trust calibration in automation using deep learning (DL) with EEG signals. This study will allow us to detect the mental states in both offline/online with high classification accuracy by using the EEG signals of humans since the DL techniques are excellent for encoding/decoding complex data.
EEG Data Augmentation in Cognitive States Recognition: Generative Models-based Approaches
This research aims to improve DL classifiers for EEG-based cognitive states recognition by generating synthetic EEG signals using generative models (GMs), representing data distributions, such as generative adversarial networks (GANs) and variational autoencoders (VAEs). This study will solve not only the data scarcity problem in EEG experiment domains but also the overfitting problem of DL-based classifiers using EEG.
Interactive Reinforcement Learning: Uncertainty-Aware Action Advising Framework
This research aims to develop an interactive reinforcement learning (IRL) framework that can reduce the sample complexity of conventional reinforcement learning (RL) by advising the action of a learner-agent based on uncertainty given a state. This study will allow a trainer-agent to use the limited amount of advice effectively and efficiently and improve the learner-agent’s performance significantly.
Hyperscanning: Quantification Method for Inter-Brain Neural Synchrony
The objective of this research is to develop a computational framework that can quantify the degree of the inter-brain synchrony change over time. This study provides numerical convergence information between inter-brains. It helps to identify the consensus of information between agents in a specific paradigm like social interaction.
Publications
- Designing an XAI interface for BCI experts: A contextual design for pragmatic explanation interface based on domain knowledge in a specific context
- Kim, S., Choo, S., Park, D., Park, H., Nam, C. S., Jung, J.-Y., & Lee, S. (2023), INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES, 174. https://doi.org/10.1016/j.ijhcs.2023.103009
- Effectiveness of multi-task deep learning framework for EEG-based emotion and context recognition
- Choo, S., Park, H., Kim, S., Park, D., Jung, J.-Y., Lee, S., & Nam, C. S. (2023), EXPERT SYSTEMS WITH APPLICATIONS, 227. https://doi.org/10.1016/j.eswa.2023.120348
- Detecting Human Trust Calibration in Automation: A Convolutional Neural Network Approach
- Choo, S., & Nam, C. (2022, January 19), IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, Vol. 1. https://doi.org/10.1109/THMS.2021.3137015
- Emotion depends on context, culture and their interaction: evidence from effective connectivity
- Pugh, Z. H., Choo, S., Leshin, J. C., Lindquist, K. A., & Nam, C. S. (2022), SOCIAL COGNITIVE AND AFFECTIVE NEUROSCIENCE, 17(2), 206–217. https://doi.org/10.1093/scan/nsab092
- Evaluating Effective Connectivity of Trust in Human-Automation Interaction: A Dynamic Causal Modeling (DCM) Study
- Huang, J., Choo, S., Pugh, Z. H., & Nam, C. S. (2022), HUMAN FACTORS, 64(6), 1051–1069. https://doi.org/10.1177/0018720820987443
- Brain-to-Brain Neural Synchrony During Social Interactions: A Systematic Review on Hyperscanning Studies
- Nam, C. S., Choo, S., Huang, J., & Park, J. (2020). [Review of , ]. APPLIED SCIENCES-BASEL, 10(19). https://doi.org/10.3390/app10196669
- Designing of smart chair for monitoring of sitting posture using convolutional neural networks
- Kim, W., Jin, B., Choo, S., Nam, C. S., & Yun, M. H. (2019), DATA TECHNOLOGIES AND APPLICATIONS, 53(2), 142–155. https://doi.org/10.1108/DTA-03-2018-0021
- Learning Framework of Multimodal Gaussian-Bernoulli RBM Handling Real-value Input Data
- Choo, S., & Lee, H. (2018), Neurocomputing, 275(1), 1813–1822. https://doi.org/10.1016/j.neucom.2017.10.018