• Journal of Computing Science and Engineering
• /
• 제7권2호
• /
• pp.132-138
• /
• 2013

Multi-modal techniques have received increasing interest in the neuroscientific and brain computer interface (BCI) communities in recent times. Two aspects of multi-modal imaging for BCI will be reviewed. First, the use of recordings of multiple subjects to help find subject-independent BCI classifiers is considered. Then, multi-modal neuroimaging methods involving combined electroencephalogram and near-infrared spectroscopy measurements are discussed, which can help achieve enhanced and robust BCI performance.

• 대한의용생체공학회:의공학회지
• /
• 제31권1호
• /
• pp.1-13
• /
• 2010

There are a great numbers of disabled individuals who cannot freely move or control specific parts of their body because of serious neurological diseases such as spinal cord injury, amyotrophic lateral sclerosis, brainstem stroke, and so on. Brain-computer interfaces (BCIs) can help them to drive and control external devices using only their brain activity, without the need for physical body movements. Over the past 30 years, several Bel research programs have arisen and tried to develop new communication and control technology for those who are completely paralyzed. Thanks to the rapid development of computer science and neuroimaging technology, new understandings of brain functions, and most importantly many researchers' efforts, Bel is now becoming 'practical' to some extent. The present review article summarizes the current state of electroencephalogram (EEG)-based Bel, which have been being studied most widely, with specific emphasis on its basic concepts, system developments, and prospects for the future.

• Journal of Computing Science and Engineering
• /
• 제7권2호
• /
• pp.139-146
• /
• 2013

Recent advances in computer science enabled people with severe motor disabilities to use brain-computer interfaces (BCI) for communication, control, and even to restore their motor disabilities. This paper reviews the most recent works of BCI in stroke rehabilitation with a focus on methodology that reported on data collected from stroke patients and clinical studies that reported on the motor improvements of stroke patients. Both types of studies are important as the former advances the technology of BCI for stroke, and the latter demonstrates the clinical efficacy of BCI in stroke. Finally some challenges are discussed.

• 사물인터넷융복합논문지
• /
• 제9권6호
• /
• pp.17-22
• /
• 2023

뇌-기계 인터페이스(BMI)는 신경활동을 통해 발생하는 전기 신호인 뇌파를 해석하여 기계를 제어하는 인터페이스이다. BMI는 다양한 분야에 적용될 수 있으나 뇌파 측정 및 해석을 위한 하드웨어의 휴대성이 낮아 대중적으로 사용되기에 어렵다는 단점이 있다. 이런 문제점을 해결하기 위해 이전 연구에서는 클라우드 컴퓨팅을 이용한 사물인터넷 기반 뇌-기계 인터페이스 시스템을 제안하였다. 본 연구에서는 위 시스템의 실시간 사용성을 증명하기 위하여 뇌파로 퐁(Pong) 게임을 조종하는 애플리케이션을 개발하여 테스트하였다. 그 결과 제안된 BMI 사용자가 최적 제어 인공지능과의 실시간 퐁 게임 대결에서 대등한 스코어를 보였다. 따라서 본 연구 결과는 사물인터넷 기반 뇌-기계 인터페이스가 일상생활 속 다양항 실시간 애플리케이션으로 활용될 수 있음을 시사한다.

• Journal of Multimedia Information System
• /
• 제2권3호
• /
• pp.275-280
• /
• 2015

Recently brainwaves are utilized diversely in the field of medicine, entertainment, education and so on. In the case of medicine, brainwaves are analyzed to estimate patients' diseases. However, the applications for entertainments usually utilize brainwaves as control signal without figuring out the characters of the brainwaves. Given that users' brainwaves are different each other, a normalization method is essential. The traditional brainwave normalization approaches utilize normal distribution. However, those approaches assume that brainwaves are collected enough to conduct normal distribution. When the few amounts of brainwaves are measured, the accuracy of the control signal based on the measured brainwaves becomes low. In this paper, we propose a normalization framework of BCI-based facial interfaces for novel volume controllers, which can normalizes the few amounts of brainwaves and then generates the control signals of BCI-based facial interfaces. In the experiments, two subjects were involved to validate the proposed framework and then the normalization processes were introduced.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.1673-1675
• /
• 2013

인간 활동의 전 영역을 총괄하는 대뇌정보기능을 대표하는 뇌파는 대뇌피질에서 발현된다고 알려져 있다. 의학적인 연구 결과에 의하면 인지 사고 등의 역동적인 지식 활동, 다양한 감성 행동, 및 고차원적인 정신활동까지도 뇌파 분석을 통해서 어느 정도는 기계적인 인식이 가능한 것으로 알려져 있다. 뇌-컴퓨터 인터페이스는 인간 중심의 시스템을 위한 핵심 연구로서 뇌파 신호 분석에 의한 사용자 의도 인식 시스의 개발을 목표로 한다. 이에 따라서, 범용적으로 적용 가능한 뇌파신호 분석 기법 및 자동 처리 시스템에 관한 연구가 활발히 진행 중이다. 특히, 뇌는 부위별로 그 기능이 세분화 되어 있으며 의식 상태와 정신활동에 따라 뇌파가 수시로 변하면서 특정한 패턴을 갖는다. 이러한 뇌의 정보처리 메커니즘을 밝혀내면 전자장치와의 통신 인터페이스를 통해 기기를 제어할 수 있다. 본 논문은 사용자의 의도를 분석하는 방법과 이를 통해 다른 장치의 인터페이스를 제어할 수 있는 시스템을 설계했다.

• International Journal of Contents
• /
• 제14권4호
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• 한국지능시스템학회논문지
• /
• 제25권3호
• /
• pp.254-259
• /
• 2015

본 논문은 BCI(Brain Computer Interface)기반의 정상상태시각유발전위(SSVEP : Steady-State Visual Evoked Potential)를 사용하여 무선 로봇 제어를 위한 시스템을 제안하였다. CPSD(Cross Power Spectral Density)를 사용하여 전극의 신호를 분석하였다. 또한 분류를 위해서 LDA(Linear Discriminant Analysis)와 SVM(Support Vector Machine)을 사용하였다. 그 결과 피험자들의 평균 분류율은 약 70%로 나타났다. 로봇제어의 경우 뇌파의 값을 분류하여 나타난 결과 값으로 로봇이 움직일 수 있도록 구현하였고, 블루투스 통신을 이용하여 로봇제어를 수행하였다.

• 산업공학
• /
• 제17권3호
• /
• pp.249-260
• /
• 2004

The objective of this study is to measure and to predict the efficiency of participating groups of BK 21 by using DEA. DEA is a methodology to measure and to evaluate the relative efficiency of a homogeneous set of decision-making units (DMUs) in a process which uses multiple inputs to produce multiple outputs. In order to reflect the effect of the environmental factors of BK 21, we consider not only a general DEA model but also a logistic model for DEA. As a result, location of participating groups of BK 21 turns out to be significant. Our proposed approach can predict the efficiency of a new BK 21 group with given environmental factors. It is expected that these models can give a feedback for effective management of BK 21.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2015년도 제46회 하계학술대회
• /
• pp.1243-1244
• /
• 2015

Finding solutions for the disabled is a major challenge for our society. In the case of a disability due to a malfunction of the nervous system, the origin may be accidental, genetic, or induced by environmental factors. This type of loss can cause loss or movement disorders (paraplegia, hemiplegia, quadriplegia, epilepsy, Parkinson's disease, multiple sclerosis, etc.) or malfunction of certain sensory functions (blindness, deafness, chronic pain, etc.). Many alternatives, more technology, have been imported to create interfaces between the human body and an artificial prosthesis in order to restore some functions of the human body. A wireless system, battery neurons probe was developed for one hand reading neural signals in the brain, and on the other hand also able to excite the neuron in the brain using a surface acoustic wave one ports (SAW) delay line reflection.