Microsleep Prediction System

This study aims to provide a microsleep predicting system using EEG signals. The system analyzes a user’s mental state with EEG signals in a real-time environment and alerts the user when the user’s future mental state is highly like to be in a microsleep state. The system predicts the probability of the user’s future mental state with present EEG signals and alerts the user if the probability of future mental state reached the arbitrary threshold. By using this system, the user can avoid industrial or traffic accidents caused by microsleep.

Contact: Heon-Gyu Kwak (hg_kwak@korea.ac.kr)

Experimental Paradigm Demo for EEG Based Lie Detection

Experimental paradigm for EEG based off-line lie detection. Experiment consists of a 2-participant system with primary user(player) and observer, where the primary user (as per program instructions) tries to either truthfully or falsely report observed stimuli to the observer. Data collection is performed for EEG on both participants, as well as facial expression video of the primary user. With utilization of machine learning algorithms which include neural networks, our research reports above-chance binary classification of deceptive/truthful intents.

Contact: Yiyu Chen (yaya2808@korea.ac.kr)

Real-Time Movement Artifact Removal Methods

We proposed a removal method of movement artifacts from EEG signals in real-time by estimating artifact signals using reference signals of isolated electrodes and IMU sensors and removing artifacts using constrained conditional adaptive method.

Contact: Y.-E. Lee (ye_lee@korea.ac.kr)

EEG-based Intention-Recognizing Top-Down SSVEP Paradigm

Augmented reality (AR) technology using a head-mounted display (HMD) is one of the fundamental tools in the next smart internet of things (IoT) society. Nowadays, portable brain-machine interfaces (BMIs) using an HMD have been studied for the future of BMI interlocked with the present IoT technology. In order to investigate the feasibility of the top-down SSVEP (steady-state visual evoked potential) BMI embedded in an HMD, SSVEP stimuli were presented in a HoloLens (Microsoft) for augmented reality (AR) constructed by holography. Electroencephalogram (EEG) was measured during the top-down SSVEP-based BMI performance, where a grid-shaped flickering visual stimulus was presented in the display of HoloLens.

Contact: J.-W. Kim (kjw1992@gmail.com)

Single/Two-player SSVEP BCI based Mole Catching Game

In this demo, SSVEP BCI based mole catching game was implemented for single and two-player mode. The user can catch the moles that appear randomly by paying attention to one of the three visual flickers flashing at different frequencies. In two-player mode, users can compete for scores, or they can cooperate in order to hit the same target mole.

Contact: H.-G. Kim (kim0401hg@gist.ac.kr)

Intuitive Communication System Using Imagined Speech

This study aims to provide an intuitive BCI communication system using imagined speech paradigm. The system operates by user’s imagined speech, producing speech sound output using EEG as an input. While the subject performs imagined speech, model estimates the word class with the highest probability. By using this system, the user can feel as though the system is ‘reading the mind’ and speak outs the user’s inner speech.

Contact: Seo-Hyun Lee (seohyunlee@korea.ac.kr)


Decoding Meta-RL Strategies in VR Environment

This study aims to apply the EEG meta-BCI system that estimates learning strategies of the subject on a virtual environment. While the model estimates the learning strategies the subject performs the penalty kick game, which is basically same as the two-stage MDP task. Well trained BCI system is possible to decode not only the learning strategy but also the decisions made.

Contact: Dongjae Kim (kim10481@kaist.ac.kr)


Wireless Multi-Modal BCI with Real-Time Multiple Measurements

This video demonstrates a wireless BCI device for fNIRS and EEG signal measurements. Implemented using Bluetooth Low Energy communication protocol, it is possible to connect and measure multiple devices at the same time. In addition, measurement results can be transmitted in real-time.

Contact: J.-W. Park (pjinwoo123@korea.ac.kr)


Smart Home based on Brain-Computer Interface

This technique is a smart home control system using a smartphone. If you take a look at the icons you want to operate on the smartphone screen, you can control the appliances of a living room, bedroom, kitchen, and utility room.

Contact: M.-H. Lee (mh_lee@korea.ac.kr)


Neurofeedback Game – MindCar

This neurofeedback game up/down-regulates target frequency power by modulating car speed in a racing game. During playing the game, the direction is automatically changed, but the speed is changed upon target frequency band power. Subjects trained to modulate their brain activity by observing the feedback (car speed).

Contact: K.-H. Won (kyunghowon0712@gist.ac.kr)