• 재활복지공학회논문지
• /
• 제11권1호
• /
• pp.45-52
• /
• 2017

EEG 신호는 신체적으로 불편함을 가지고 있는 사용자에게서도 동일하게 발생되는 신호로써 차세대 인터페이스로 각광받고 있다. 본 논문에서는 사용자의 EEG 신호를 이용하여 감성적인 정보처리와 논리적인 정보처리를 보조하는 실내 환경을 제어하는 사물인터넷 시스템을 제안한다. 제안된 시스템은 EEG 측정 장치, EEG 시뮬레이션 소프트웨어, 실내 환경 제어 장치로 구성된다. 실험 데이터로는 편안한 상태에서 발생되는 감성적인 정보처리에 대한 EEG 신호 데이터와 집중 시에 발생되는 논리적인 정보처리에 대한 EEG 신호 데이터를 사용한다. 측정된 신호에서는 ICA 알고리즘이 적용하여 잡음이 제거되고 베타파만을 추출한다. 이후 SVM을 통한 학습 및 테스트 과정을 거치게 된다. 피험자는 EEG 시뮬레이션 소프트웨어를 통해 EEG 신호 정확도 향상 훈련을 거친 결과 평균 82.69%의 정확도를 보였다. EEG 측정 장치로부터 입력되는 EEG 신호는 Serial 통신을 통해 EEG 시뮬레이션 소프트웨어로 전송되며 감성적인 정보처리와 논리적인 정보처리를 분류하여 제어 명령이 생성된다. 이후 생성된 제어 명령은 Zigbee 통신을 통해 실내 환경 제어 장치로 전달되어 감성적인 정보처리일 경우 은은한 조명과 클래식 음악이 출력되고 논리적인 정보처리일 경우 밝은 조명과 함께 학습용 백색소음이 출력된다. 제안한 시스템은 BCI 기반 소프트웨어 및 디바이스 제어에 응용될 수 있어 몸이 불편한 사용자가 자신의 신체적인 한계를 극복하는 것을 가능하게 한다.

• 센서학회지
• /
• 제25권4호
• /
• pp.257-263
• /
• 2016

Among several technologies related to human brain, Brain Computer Interface (BCI) system is one of the most notable technologies recently. Conventional BCI for direct communication between human brain and machine are discomfort because normally electroencephalograghy(EEG) signal is measured by using multichannel EEG sensor. In this study, we propose 2-channel EEG sensor-based application control system which is more convenience and low complexity to wear to get EEG signal. EEG sensor module and system algorithm used in this study are developed and designed and one of the BCI methods, Motor Imagery (MI) is implemented in the system. Experiments are consisted of accuracy measurement of MI classification and driving control test. The results show that our simple wearable system has comparable performance with studies using multi-channel EEG sensor-based system, even better performance than other studies.

• 한국지능시스템학회논문지
• /
• 제23권2호
• /
• pp.172-177
• /
• 2013

BCI (Brain Computer Interface)는 인간의 뇌에서 측정된 EEG (Electroencephalogram)를 활용하여 의수와 같은 기기를 조종할 수 있는 좋은 방법 중 하나이다. 본 논문에서는 EEG와 힘과의 관계를 알아보고자 최대수축악력 (MVC)의 25%, 50%, 75%로 3개의 등급으로 나누어 EEG 변화를 측정하였다. 얻어진 EEG data를 FFT와 power spectrum analysis로 ${\alpha}$, ${\beta}$, ${\gamma}$파로 나누어 각 파형의 파워 값을 구한 뒤, 구해진 EEG 파워 값을 PCA와 LDA를 사용하여 특징 추출 및 분류를 하였다. 실험 결과 25%의 악력을 가할 때 보다 75%의 악력 때 더 높은 EEG 파워의 증가를 확인하였고, 왼손과 오른손은 각각 52.03%와 77.7%의 분류율을 나타내었다.

• 안보군사학연구
• /
• 통권1호
• /
• pp.249-267
• /
• 2003

EEG is an electrical signal, which occurs during information processing in the brain. These EEG signals have been used clinically, but nowadays we are mainly studying Brain-Computer Interface (BCI) such as interfacing with a computer through the EEG, controlling the machine through the EEG. The ultimate purpose of BCI study is specifying the EEG at various mental states so as to control the computer and machine. This research makes the controlling system of directions with the artifact that are generated from the subject's will, for the purpose of controlling the machine correctly and reliably. We made the system like this. First, we select the particular artifact among the EEG mixed with artifact, then, recognize and classify the signals' pattern, then, change the signals to general signals that can be used by the controlling system of directions.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.19-23
• /
• 1996

A full automatic interpretation of awake electroencephalogram (EEG) had been developed by the authors and presented at the past KACCs in series. The automatic EEG interpretation consists of four main parts: quantitative EEG interpretation, EEG report making, preprocessing of EEG data and adaptable EEG interpretation. The automatic EEG interpretation reveals essentially the same findings as the electroencephalographer's (EEG's), and then would be applicable in clinical use as an assistant tool for EEGer. The method had been developed through collaboration works between the engineering field (Saga University) and the medical field (Kyoto University). This work can be understood as an artificial realization of human expert skill. The procedure for the artificial realization was summarized in a methodology for artificial realization of human skill which will be applicable in other fields of systems control.

• 대한임베디드공학회논문지
• /
• 제18권2호
• /
• pp.81-87
• /
• 2023

With the development of BCI devices, it is now possible to use EEG control technology to move the robot's arms or legs to help with daily life. In this paper, we propose a customized vehicle control model based on BCI. This is a model that collects BCI-based driver EEG signals, determines information according to EEG signal analysis, and then controls the direction of the vehicle based on the determinated information through EEG signal analysis. In this case, in the process of analyzing noisy EEG signals, controlling direction is supplemented by using a camera-based eye tracking method to increase the accuracy of recognized direction . By synthesizing the EEG signal that recognized the direction to be controlled and the result of eye tracking, the vehicle was controlled in five directions: left turn, right turn, forward, backward, and stop. In experimental result, the accuracy of direction recognition of our proposed model is about 75% or higher.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.509-513
• /
• 1992

This paper investigates the EEG waveform distortions caused by the transient responses of various types of signal conditioning filters, which are generally introduced for automated analysis of EEG. This study explicitly simulates the filter responses to the typical EEG waveform models, and compares the distortions. The filter distortion effects are also illustrated with the experiments on real EEG signals.

• 한국의류산업학회지
• /
• 제14권6호
• /
• pp.1010-1017
• /
• 2012

This study examined the clothing wearing comfort of elderly women by electroencephalogram (EEG) and electrocardiogram (ECG) analyses. This study utilized 7 elderly individuals aged 65 or more. Two kinds of clothing ensemble (control and prototype) were used as experimental clothing. The control consisted of a general clothing ensemble and the prototype consisted of clothing that added an extra gap. Subjects wore the control or prototype from 9:00 to 21:30 and EEG and ECG signals were measured in the last 30 minutes. The EEG analysis showed that relative band power of a and ${\alpha}$/high ${\beta}$ were higher when they wore the prototype rather than the control. The ECG analysis showed that absolute band power of HF was higher; however, absolute band power of LF and LF/HF was lower when they wore the prototype rather than the control. Subjects felt less stressful and more comfortable when they wore the prototype. The results demonstrate the necessity to develop clothing in consideration of the body changes in elderly women. It is significant that the assessment of wearing comfort was aided by the use of EEG and ECG analysis in the field of clothing and textiles.

• 제어로봇시스템학회논문지
• /
• 제13권9호
• /
• pp.832-837
• /
• 2007

Electroencephalographic(EEG) is used to record activities of human brain in the area of psychology for many years. As technology develope, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study Emotion Recognition method which uses one of EEG signals and Gestures in the existing research. In this paper, we use together EEG signals and Gestures for Emotion Recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both EEG signals and gestures gets high recognition rates better than using EEG signals or gestures. Both EEG signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on a reinforcement learning.

• 대한간호학회지
• /
• 제45권6호
• /
• pp.928-938
• /
• 2015

Purpose: This study explored the effects of neurofeedback training on Electroencephalogram (EEG), Continuous Performance Task (CPT) and ADHD symptoms in ADHD prone college students. Methods: Two hundred forty seven college students completed Korean Version of Conners' Adult ADHD Rating Scales (CAARS-K) and Korean Version of Beck Depression Inventory (K-BDI). The 16 participants who ranked in the top 25% of CAARS-K score and had 16 less of K-BDI score participated in this study. Among them, 8 participants who are fit for the research schedule were assigned to neurofeedback training group and 8 not fit for the research schedule to the control group. All participants completed Adult Attention Deficiency Questionnaire, CPT and EEG measurement at pretest. The neurofeedback group received 15 neurofeedback training sessions (5 weeks, 3 sessions per week). The control group did not receive any treatment. Four weeks after completion of the program, all participants completed CAARS-K, Adult Attention Deficiency Questionnaire, CPT and EEG measurement for post-test. Results: The neurofeedback group showed more significant improvement in EEG, CPT performance and ADHD symptoms than the control group. The improvements were maintained at follow up. Conclusion: Neurofeedback training adjusted abnormal EEG and was effective in improving objective and subjective ADHD symptoms in ADHD prone college students.