• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.12-18
• /
• 2013

Motor imagery classification in electroencephalography (EEG)-based brain-computer interface (BCI) systems is an important research area. To simplify the complexity of the classification, selected power bands and electrode channels have been widely used to extract and select features from raw EEG signals, but there is still a loss in classification accuracy in the state-of- the-art approaches. To solve this problem, we propose a discriminative feature extraction algorithm based on power bands with principle component analysis (PCA). First, the raw EEG signals from the motor cortex area were filtered using a bandpass filter with ${\mu}$ and ${\beta}$ bands. This research considered the power bands within a 0.4 second epoch to select the optimal feature space region. Next, the total feature dimensions were reduced by PCA and transformed into a final feature vector set. The selected features were classified by applying a support vector machine (SVM). The proposed method was compared with a state-of-art power band feature and shown to improve classification accuracy.

• PNF and Movement
• /
• 제7권4호
• /
• pp.45-53
• /
• 2009

Purpose : The purpose of this article was to review the literature on mirror neuron system with reference to its functional diversity in stroke rehabilitation.. Method : This review outlines scientific findings regarding different neurophysiological properties in mirror neurons, and discusses their involvement in process of stroke rehabilitation. Result & Conclusions : Mirror neurons were first discovered in macaque monkey. These neurons, like most neurons in F5 areas in premotor cortex, fired when an individual performs an action, as well as when he/she observes a similar action done by another individual, although originally fired only during action execution. Mirror neurons form a network for motor planning and initiating of motor action. Thus, in stroke rehabilitation based on the mirror neuron-action observation, motor imagery, observation with intent to imitate and imitation-may help activate mirror neuron system for improved outcome of physical therapy. These studies provide a scientific theoretical basis and discuss for the use of mirror neuron system as a complement to clinical physical therapy in stroke rehabilitation.

• 정보과학회 논문지
• /
• 제44권6호
• /
• pp.587-594
• /
• 2017

최근, 동작 상상(Motor Imagery) Electroencephalogram(EEG)를 기반으로 한 Brain-Computer Interface(BCI) 시스템은 의학, 공학 등 다양한 분야에서 많은 관심을 받고 있다. Common Spatial Pattern(CSP) 알고리즘은 동작 상상 EEG의 특징을 추출하기 위한 가장 유용한 방법이다. 그러나 CSP 알고리즘은 공분산 행렬에 의존하기 때문에 Small-Sample Setting(SSS) 상황에서 성능에 한계가 있다. 또한 사용하는 주파수 대역에 따라 큰 성능 차이를 보인다. 이러한 문제를 동시에 해결하기 위해, 4-40Hz 대역 EEG 신호를 9개의 필터 뱅크를 이용하여 분할하고 각 밴드에 Regularized CSP(R-CSP)를 적용한다. 이후 Mutual Information-Based Individual Feature(MIBIF) 알고리즘은 R-CSP의 차별적인 특징을 선택하기 위해 사용된다. 본 연구에서는 대뇌 피질의 운동영역 부근 18개 채널을 사용하여 BCI CompetitionIII DatasetIVa의 피험자 다섯 명(aa, al, av, aw 및 ay)에 대해 각각 87.5%, 100%, 63.78%, 82.14% 및 86.11%의 정확도를 도출하였다. 제안된 방법은 CSP, R-CSP 및 FBCSP 방법보다 16.21%, 10.77% 및 3.32%의 평균 분류 정확도 향상이 있었다. 특히, 본 논문에서 제안한 방법은 SSS 상황에서 우수한 성능을 보였다.

• 대한물리의학회지
• /
• 제5권3호
• /
• pp.395-404
• /
• 2010

Purpose : The object of this study was to examine the effect of motor learning on brain activation depending on the method of motor learning. Methods : The brain activation was measured in 9 men by fMRI. The subjects were divided into the following groups depending on the method of motor learning: actually practice (AP, n=3) group, action observation (AO, n=3) group and motor imagery (MI, n=3) group. In order to examine the effect of motor learning depending on the method of motor learning, the brain activation data were measured during learning. For the investigation of brain activation, fMRI was conducted. Results : The results of brain activation measured before and during learning were as follows; (1) During learning, the AP group showed the activation in the following areas: primary motor area located in precentral gyrus, somatosensory area located in postcentral gyrus, supplemental motor area and prefrontal association area located in precentral gyrus, middle frontal gyrus and superior frontal gyrus, speech area located in superior temporal gyrus and middle temporal gyrus, Broca's area located in inferior parietal lobe and somatosensory association area of precuneus; (2) During learning, the AD groups showed the activation in the following areas: primary motor area located in precentral gyrus, prefrontal association area located in middle frontal gyrus and superior frontal gyrus, speech area and supplemental motor area located in superior temporal gyrus and middle temporal gyrus, Broca's area located in inferior parietal lobe, somatosensory area and primary motor area located in precentral gyrus of right cerebrum and left cerebrum, and somatosensory association area located in precuneus; and (3) During learning, the MI group showed activation in the following areas: speech area located in superior temporal gyrus, supplemental area, and somatosensory association area located in precuneus. Conclusion : Given the results above, in this study, the action observation was suggested as an alternative to motor learning through actual practice in serial reaction time task of motor learning. It showed the similar results to the actual practice in brain activation which were obtained using activation of mirror neuron. This result suggests that the brain activation occurred by the activation of mirror neuron, which was observed during action observation. The mirror neurons are located in primary motor area, somatosensory area, premotor area, supplemental motor area and somatosensory association area. In sum, when we plan a training program through physiotherapy to increase the effect during reeducation of movement, the action observation as well as best resting is necessary in increasing the effect of motor learning with the patients who cannot be engaged in actual practice.

• 대한의용생체공학회:의공학회지
• /
• 제32권4호
• /
• pp.295-304
• /
• 2011

In this study, we evaluated the EEG based BCI algorithm using common spatial pattern to find realistic applicability using neurofeedback EEG based BCI algorithm - EEG mode, feature vector calculation, the number of selected channels, 3 types of classifier, window size is evaluated for 10 subjects. The experimental results have been evaluated depending on conditioned experiment whether neurofeedback is used or not In case of using neurofeedback, a few subjects presented exceptional but general tendency presented the performance improvement Through this study, we found a motivation of development for the specific classifier based BCI system and the assessment evaluation system. We proposed a need for an optimized algorithm applicable to the robust motor imagery evaluation system with more useful functionalities.

• Journal of Magnetics
• /
• 제19권2호
• /
• pp.181-184
• /
• 2014

The aim of the present study was to examine whether motor imagery (MI) practice in conjunction with repetitive transcranial magnetic stimulation (rTMS) applied to stroke patients could improve theirgait ability. This study was conducted with 29 subjects diagnosed with hemiparesis due to stroke.The experimental group consisted of 15 members who were performed MI practice in conjunction with repetitive transcranial magnetic stimulation, while the control group consisted of 14 members who were performed MI practice and sham therapy. Both groups received traditional physical therapy for 30 minutes a day, 5 days a week, for 6 weeks; additionally, they received mental practice for 15 minutes. The experimental group was instructed to perform rTMS and the control group was instructed to apply sham stimulation for 15 minutes. Gait analysis was performed using a three-dimensional motion capture system, which is a real-time tracking device that delivers data via infrared reflective markers using six cameras. Results showed that the velocity, step length, and cadence of both groups were significantly improved after the practice (p<0.05). Significant differences were found between the groups in velocity and cadence (p<0.05) as well as with respect to the change rate (p<0.05) after practice. The results showed that MI practice in conjunction with rTMS is more effective in improving gait ability than MI practice alone.

• The Korean Journal of Pain
• /
• 제35권2호
• /
• pp.152-159
• /
• 2022

Background: Subjects with frozen shoulder (FS) might not be comfortable with vigorous physical therapy. Clinical trials assessing the effect of graded motor imagery (GMI) in FS are lacking. The aim of this study was to determine the effect of GMI as an adjunct to conventional physiotherapy in individuals with painful FS. Methods: Twenty subjects aged 40-65 years having stage I and II of FS were randomly divided into two study groups. The conventional physiotherapy group (n = 10) received electrotherapy and exercises while the GMI group (n = 10) received GMI along with the conventional physiotherapy thrice a week for 3 weeks. Pre- (Session 1) and post- (Session 9) intervention analysis for flexion, abduction, and external rotation range of motion (ROM) using a universal goniometer, fear of movement using the fear avoidance belief questionnaire (FABQ), pain with the visual analogue scale, and functional disability using the shoulder pain and disability index (SPADI) was done by a blinded assessor. Results: Statistically significant difference was seen within both the groups for all the outcomes. In terms of increasing abduction ROM as well as reducing fear of movement, pain, and functional disability, the GMI group was significantly better than control group. However, both groups were equally effective for improving flexion and external rotation ROM. Conclusions: Addition of GMI to the conventional physiotherapy proved to be superior to conventional physiotherapy alone in terms of reducing pain, kinesiophobia, and improving shoulder function for stage I and II of FS.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.2083-2085
• /
• 2009

Brain Computer Interface (BCI) is a communication pathway between devices (computers) and human brain. It treats brain signals in real-time basis and discriminates some information of what human brain is doing. In this work, we develop a EEG BCI system using a feature extraction such as common spatial pattern (CSP) and a classifier using Fisher linear discriminant analysis (FLDA). Two-class EEG motor imagery movement datasets with both cued and uncued are tested to verify its feasibility.

• 인지과학
• /
• 제21권2호
• /
• pp.309-338
• /
• 2010

본 논문에서는 사지가 마비되어 신체를 움직이지 못하지만 뇌의 기능은 살아있는 장애인들을 위하여, 생각만으로 외부의 장치를 제어할 수 있도록 하는 뇌-컴퓨터 인터페이스(BCI: Brain-Computer Interface) 기술을 연구하였다. 신경생리학 분야에서의 연구 결과에 의하면, 신체를 움직이는 상상을 할 경우, 뇌의 운동/감각 피질 영역에서는 $\beta$파(14-26 Hz)와 $\mu$파(8-12 Hz)가 억제/증가되는 ERD/ERS(Event-Related Desynchronization / Synchronization) 현상이 발생한다고 알려져 있다. 본 연구에서는 이를 기반으로 혀, 발, 왼손, 오른손의 동작 상상을 자극으로 이용하여 변화하는 뇌 신호 패턴을 실시간으로 분석하여 피험자의 생각을 읽을 수 있도록 하였으며, 상 하 좌 우의 네 방향으로 이동할 수 있도록 하는 마우스 제어 인터페이스를 구현하였다. 동작 상상 시 발생하는 뇌 신경 활동의 변화를 관측하기 위해서 뇌에 손상을 주지 않으면서도 높은 시간 해상도로 측정이 가능한 비침습적 뇌전도(EEG: ElectroEncephaloGraphy)를 이용하였다. 그러나 뇌전도 신호는 특성상 신호의 크기가 미약하고, 잡음의 영향을 많아 분석이 어렵다. 따라서 이를 극복하기 위해 통계적 방법을 기반으로 한 기계학습 기법인 CSP(Common Spatial Pattern)와 선형판별 분석(Linear Discriminant Analysis)을 이용하여 서로 다른 동작 상상에 의해 발생하는 뇌 신호들 간의 분산이 최대가 되도록 신호를 변환하여 인식 성능을 높일 수 있었다. 또한 분석된 뇌 신호의 시각화를 통해, 기존에 알려진 뇌의 해부학적, 신경생리학적 지식과 일치하는 ERD/ERS 현상이 발생하는 것을 확인할 수 있었다.

• 한국지능시스템학회논문지
• /
• 제22권6호
• /
• pp.793-798
• /
• 2012

In this paper, we explored the new method for extracting feature from the electroencephalography (EEG) signal based on linear regression technique with the orthonormal polynomial bases. At first, EEG signals from electrodes around motor cortex were selected and were filtered in both spatial and temporal filter using band pass filter for alpha and beta rhymic band which considered related to the synchronization and desynchonization of firing neurons population during motor imagery task. Signal from epoch length 1s were fitted into linear regression with Legendre polynomials bases and extract the linear regression weight as final features. We compared our feature to the state of art feature, power band feature in binary classification using support vector machine (SVM) with 5-fold cross validations for comparing the classification accuracy. The result showed that our proposed method improved the classification accuracy 5.44% in average of all subject over power band features in individual subject study and 84.5% of classification accuracy with forward feature selection improvement.