• Proceedings of the KOSOMBE Conference
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.193-194
• /
• 1998

This paper describes a multi-functional EEG (electroencephalogram) software. The software manages the patient's EEG data systematically and analyzes the signal and display the parameters on a PC monitor in real-time. Since the software provides various parameters simultaneously, user can observe patients multilaterally. Reference patterns of CSA and DSA can be captured and displayed on top of the monitor. And user can mark events of surgical operation or patient's conditions, so it is possible to jump to the points of events directly, when reviewing the recorded file afterwards. Many convenient functions are equipped and these are operated by mouse clicks.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.1715-1717
• /
• 2015

최근 의학 및 게임 분야에서 뉴로 피드백에 관한 연구들이 활발하다. 뉴로 피드백이란 뇌의 전기적 활동을 뜻하는EEG(Electroencephalogram)을 대상으로 하는 바이오피드백(biofeedback) 시스템의 일종이다. 좌 우뇌의 불균형은 불안과 우울 등의 정서적 장애를 초래한다. 본 논문에서는 좌, 우뇌 활성도를 대칭적으로 향상시켜 뇌기능의 최적화를 위한 시스템을 제안하며 뇌파를 분석하여 정서 상태 파악 후 규칙적 훈련을 통한 우울, 불안 등의 정서적 문제를 개선하는 뉴로 피드백 시스템 개발에 대한 결과를 보고한다. 실험을 통한 시스템의 검증으로 3주간 진행한 훈련 결과를 비교하였으며 그 증가율을 살펴보았다. 1주차와 3주차의 데이터를 비교해본 결과 평균적으로 26.18%의 증가율을 보였고 좌, 우뇌의 활성도의 대칭이 향상된 것을 알 수 있었다.

• The Korean Journal of Applied Statistics
• /
• 제37권2호
• /
• pp.139-155
• /
• 2024

This study performed a multi-classification task to classify mesial temporal lobe epilepsy with left hippocampal sclerosis patients (left mTLE), mesial temporal lobe epilepsy with right hippocampal sclerosis (right mTLE), and healthy controls (HC) using magnetoencephalography (MEG) data. We applied various artificial neural networks and compared the results. As a result of modeling with convolutional neural networks (CNN), recurrent neural networks (RNN), and graph neural networks (GNN), the average k-fold accuracy was excellent in the order of CNN-based model, GNN-based model, and RNN-based model. The wall time was excellent in the order of RNN-based model, GNN-based model, and CNN-based model. The graph neural network, which shows good figures in accuracy, performance, and time, and has excellent scalability of network data, is the most suitable model for brain research in the future.

• Journal of the Korea Society of Computer and Information
• /
• 제28권10호
• /
• pp.133-153
• /
• 2023

In this paper, we propose a novel approach to investigating brain-signal measurement technology using Electroencephalography (EEG). Traditionally, researchers have combined EEG signals with bio-signals (BSs) to enhance the classification performance of emotional states. Our objective was to explore the synergistic effects of coupling EEG and BSs, and determine whether the combination of EEG+BS improves the classification accuracy of emotional states compared to using EEG alone or combining EEG with pseudo-random signals (PS) generated arbitrarily by random generators. Employing four feature extraction methods, we examined four combinations: EEG alone, EG+BS, EEG+BS+PS, and EEG+PS, utilizing data from two widely-used open datasets. Emotional states (task versus rest states) were classified using Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) classifiers. Our results revealed that when using the highest accuracy SVM-FFT, the average error rates of EEG+BS were 4.7% and 6.5% higher than those of EEG+PS and EEG alone, respectively. We also conducted a thorough analysis of EEG+BS by combining numerous PSs. The error rate of EEG+BS+PS displayed a V-shaped curve, initially decreasing due to the deep double descent phenomenon, followed by an increase attributed to the curse of dimensionality. Consequently, our findings suggest that the combination of EEG+BS may not always yield promising classification performance.

• Journal of Advanced Navigation Technology
• /
• 제22권5호
• /
• pp.472-477
• /
• 2018

In this paper, we develop interactive content services for preventing depression of users through an intelligent Internet of Things(IoT) mirror system. For interactive content services, an IoT mirror device measures attention and meditation data from an EEG headset device and also measures facial expression data such as "sad", "angery", "disgust", "neutral", " happy", and "surprise" classified by a multi-layer perceptron algorithm through an webcam. Then, it sends the measured data to an oneM2M-compliant IoT server. Based on the collected data in the IoT server, a machine learning model is built to classify three levels of depression (RED, YELLOW, and GREEN) given by a proposed merge labeling method. It was verified that the k-nearest neighbor (k-NN) model could achieve about 93% of accuracy by experimental results. In addition, according to the classified level, a social network service agent sent a corresponding alert message to the family, friends and social workers. Thus, we were able to provide an interactive content service between users and caregivers.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• 제35권8호
• /
• pp.73-79
• /
• 2019

The purpose of this study is to analyze the stress variation according to Hitler's residence using EEG data. Hitler's residence, one of the most monumental buildings, is designed as a grand and overbearing space, giving the visitor a sense of psychological pressure when moving from a high space to low space. Based on the above background, this paper constructs Hitler's residence using virtual reality and measure the changes of the beta waves which are known to be related with stress when the floor level moves from high to low space in Hitler's residence built in virtual space. The results of the experiment are as follows; when moving from high to low space, the subjects' stress was high and at the same time brain waves variation was increased greatly due to changes in space.

• 전자공학회논문지 IE
• /
• 제43권1호
• /
• pp.16-24
• /
• 2006

This paper is aimed to develope of an integrated BCI(Brain Computer Interface System) that make possible for simultaneous multichannel data process and used extra cellular neural activity from the vestibular system instead of electroencephalogram signals for more precision control. The electrical properties pre-amplifier are 47.6 dB of gain, 0.005 % of distortion at 100 Hz, 12M$\Omega$ of input impedance. Window discriminator used two CPU with difference role to increase processing speed so that sampling frequency was 87 kHz. The designed window discriminator has more not only two times in signal resolution power but also ten times in error discrimination power than commericially available discriminator. The proposed method decreases 100 times in amount of integrated data then BCI system during 100 ms.

• Journal of IKEEE
• /
• 제23권4호
• /
• pp.1273-1279
• /
• 2019

Though sleep polysomnography (PSG) is considered as a golden rule for medical diagnosis of sleep disorder, it is essential to find alternative diagnosis methods due to its cost and time constraints. Recently, as the popularity of wearable health devices, there are many research trials to replace conventional actigraphy to consumer grade devices. However, these devices are very limited in their use due to the accessibility of the data and algorithms. In this paper, we showed the predictive model for sleep stages classified by American Academy of Sleep Medicine (AASM) standard and we proposed the estimation of sleep cycle by comparing sensor data and power spectrums of δ wave and θ wave. The sleep stage prediction for 31 subjects showed an accuracy of 85.26%. Also, we showed the possibility that proposed algorithm can find the sleep cycle of REM sleep and NREM sleep.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제20권1호
• /
• pp.153-158
• /
• 2010

This paper showed the possibilities of performance improvement of Brain-Computer Interface (BCI) decreasing classification error rates of EEG signals by applying Variance-Considered Machine (VCM) which proposed in our previous study. BCI means controlling system such as computer by brain signals. There are many factors which affect performances of BCI. In this paper, we used suggested algorithm as a classification algorithm, the most important factor of the system, and showed the increased correct rates. For the experiments, we used data which are measured during imaginary movements of left hand and foot. The results indicated that superiority of VCM by comparing error rates of the VCM and SVM. We had shown excellence of VCM with theoretical results and simulation results. In this study, superiority of VCM is demonstrated by error rates of real data.

• The Journal of the Convergence on Culture Technology
• /
• 제5권4호
• /
• pp.451-456
• /
• 2019

Recently, various bioinformation technologies have been proposed, and research and development on the collection and analysis of the human body related bioinformation have been continuously conducted to support the human life environment and healthcare. These biomedical research and development processes add to the redundancy and complexity of the R&D elements and put a heavy burden on the follow-up research developers. Therefore, this study utilizes an open bioinformation platform that effectively supports the collection and analysis of bioinformation to improve the redundancy and complexity of bioinformatics R&D based on the bioinformatics platform. In addition, I propose an open interface that supports acquisition, processing, analysis, and application of bio-signals. In particular, we propose a biometric information normalization pattern model through data analysis modeling of brain wave information based on an open interface.