• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1171-1180
• /
• 2019

Emotion is a psycho-physiological process that plays an important role in human interactions. Affective computing is centered on the development of human-aware artificial intelligence that can understand and regulate emotions. This field of study is also critical as mental diseases such as depression, autism, attention deficit hyperactivity disorder, and game addiction are associated with emotion. Despite the efforts in emotions recognition and emotion detection from nonstationary, detecting emotions from abnormal EEG signals requires sophisticated learning algorithms because they require a high level of abstraction. In this paper, we investigated LSTM hyperparameters for an optimal emotion EEG classification. Results of several experiments are hereby presented. From the results, optimal LSTM hyperparameter configuration was achieved.

• Journal of Biomedical Engineering Research
• /
• v.41 no.1
• /
• pp.22-27
• /
• 2020

Auditory stimuli are commonly used in various electroencephalogram experiments, also in EEG-based brain-computer interface systems. However, using conventional earphones that blocks the ear canal attenuates or even blocks external environmental sound which might cause loss of crucial information from surroundings. Instead, bone-conductive earphones are able to deliver sound through vibration without blocking the ear canal. To investigate the feasibility of the bone-conductive earphones for auditory-stimuli based experiments, we compared N100 event-related potential features as well the event-related spectral perturbation and inter-trial coherence of auditory steady-state response between conventional and bone-conductive earphones. The results showed no significant differences between bone conduction and conventional earphones regardless of distinct sound pressures. This result shows that bone conductive earphones can be used for auditory experiments when the environmental sound is crucial to the user.

• Journal of Korea Game Society
• /
• v.13 no.6
• /
• pp.15-26
• /
• 2013

In recent years, studies in BCI game with popular BCI devices are progressing actively by the development of BCI(Brain Computer Interface) techniques. Most of BCI games have developed as experimental contents for researching. On the game control paradigm, it is insufficient to conduct a study about induced methods of proper barinwave to control the BCI game. In this study, we suggest a rhythm game using BCI which has a new play element that visualizes the rhythm of music and represents the notes of music in sound and a generation method of visual-auditory feedback through the synchronization of the tempo of music with brainwave. Experimental Results make certain that our suggestion is possible for the improvement of game score through the induction of brainwave that is necessary to control the game.

• Journal of the Ergonomics Society of Korea
• /
• v.26 no.2
• /
• pp.167-171
• /
• 2007

Brain computer interface is the technology of interface for next generation. Recently, user intention has been tried to be recognized for interfacing a computer. EEG plays important role in developing practical application in this area. Much research has focused on extracting EEG commander generated by human movement. ERD/ERS has generally accepted as important EEG parameters for prediction of human movement. However, There has been difference between initial movement indicated by ERD/ERS and real movement. Therefore, this study was to determine the time differences for brain interface by ERD/ERS. Five university students performed ten repetitive movements. ERD/ERS was determined according to movement execution and the significant pattern showed the difference between movement execution and movement indication of ERD/ERS.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.228-233
• /
• 2021

In this paper, we propose a method to extract and classify features of multi-channel ElectroEncephalo Graphy (EEG) that change according to various musical tempo stimuli. In the proposed method, a 3D convolutional bidirectional gated recurrent neural network extracts spatio-temporal and long time-dependent features from the 3D EEG input representation transformed through the preprocessing. The experimental results show that the proposed tempo stimuli classification method is superior to the existing method and the possibility of constructing a music-based brain-computer interface.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2349-2356
• /
• 2008

In this paper, we present the method to effectively extract and classify the EEG caused by only brain activity when a normal subject is in a state of mental activity. We measure the synchronous EEG on the auditory event when a subject who is in a normal state thinks of a specific task, and then shift the baseline and reduce the effect of biological artifacts on the measured EEG. Finally we extract only the mental task signal by averaging method, and then perform the recognition of the extracted mental task signal by computing the AR coefficients. In the experiment, the auditory stimulus is used as an event and the EEG was recorded from the three channel $C_3-A_1$, $C_4-A_2$ and $P_Z-A_1$. After averaging 16 times for each channel output, we extracted the features of specific mental tasks by modeling the output as 12th order AR coefficients. We used total 36th order coefficient as an input parameter of the neural network and measured the training data 50 times per each task. With data not used for training, the rate of task recognition is 34-92 percent on the two tasks, and 38-54 percent on the four tasks.

• Progress in Medical Physics
• /
• v.8 no.1
• /
• pp.17-24
• /
• 1997

We developed PC-based planning system for linear accelerator based stereotactic radiosurgery. The system was developed under Windows 95 on Pentium Pro$\^$(R) 200 ㎒ IBM PC with 128 MB RAM. It was programed using IDL$\^$(R)/ of Research Systems, Inc. as a programing tool. CT image data obtained with BRW stereotactic frame is transferred to PC through magnetoptical disk. As loading the image, the system automatically recognizes the location of rods and establishes stereotactic coordinates. It accurately calculates and corrects the coordinates, degree of tilting, and magnification rate of axial images. After the coordinates is defined we can delineate and edit the contours of target and organs of interest on axial images. Upon delineating contours of target, isocenter is determined automatically and we can set up the beam configuration for radiosurgery. The system provides beam's eye view and room's eye view for efficient confuguring of beams. The system calculates dose distribution 3-dimensionally. It takes 1 to 2 minutes to calculate dose distribution for 5 arcs. We can verify the dose distribution on serial axial images. We can analyze the dose distribution quantitatively by evaluation of dose-volume histogram of target and organ of interest. This system, PC-based radiosurgery planning system, includes the basic features for radiosurgery planning and calculates dose distribution within reasonable time for clinical application.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.1
• /
• pp.40-48
• /
• 2009

Leading of the computer, IT technology has make great strides. As a information-industry-community was highly developed, user's needs to convenience about intelligence and humanization of interface is being increase today. Nowadays, researches with are related to BCI are progress put the application-technology development first in importance eliminating research about fountainhead technology with DB construction. These problems are due to a BCI-related research studies have not overcome the initial level, and not toward a systematic study. Brain wave are collected from subjects is a signal that the signal is appropriate and necessary in the experiment is difficult to distinguish. In addition, brain wave that it's not necessary to collect the experiment, serious eyes flicker, facial and body movements of an EMG and electrodes attached to the state, noise, vibration, etc. It is hard to collect accurate brain wave was caused by mixing disturbance wave in experiment on the environment. This movement, and the experiment of subject impact on the environment due to the mixing disturbance wave can cause that lowering cognitive and decline of efficiency when embodied BCI system. Therefore, in this paper, we propose an accurate and efficient brain-wave DB building system that more exactness and cognitive basis studies when embodied BCI system with brain-wave. For the minimize about brain wave DB with mixing disturbance, we propose a DB building method using an automatic control and prevent unnecessary action, put to use the subjects face tracking.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.289-294
• /
• 2015

This paper proposes an autonomous machine learning method applicable to the BCI(Brain-Computer Interface) is based on the self-organizing Kohonen method, one of the exemplary method of unsupervised learning. In addition we propose control method of learning region and self machine learning rule using an interactive function. The learning region control and machine learning was used to control the side effects caused by interaction function that is based on the self-organizing Kohonen method. After determining the winner neuron, we decided to adjust the connection weights based on the learning rules, and learning region is gradually decreased as the number of learning is increased by the learning. So we proposed the autonomous machine learning to reach to the network equilibrium state by reducing the flow toward the input to weights of output layer neurons.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.29-34
• /
• 2015

Brain-computer interface (BCI) is being studied for convenient life in various application fields. The purpose of this study is to investigate a changing electroencephalography (EEG) for precise motion of a robot or an artificial arm. Three subjects who participated in this experiment performed three-task: Grip, Move, Relax. Acquired EEG data was extracted feature data using two feature extraction algorithm (power spectrum analysis and multi-common spatial pattern). Support vector machine (SVM) were applied the extracted feature data for classification. The classification accuracy was the highest at Grip class of two subjects. The results of this research are expected to be useful for patients required prosthetic limb using EEG.