• 전자공학회논문지
• /
• 제53권3호
• /
• pp.143-150
• /
• 2016

본 논문에서는 안면근육 표면근전도를 기반으로 근육 조합 최적화를 통한 한국어 단모음 인식 방법을 제안한다. 표면근전도 신호는 한국어 단모음 발음에 따라 서로 다른 패턴과 근육 활성도를 보였다. 이전 연구에서 높은 인식 정확도를 보였던 RMS, VAR, MMAV1, MMAV2와 Cepstral Coefficients를 특징 추출 알고리즘으로 사용하였으며, QDA(Quadratic Discriminant Analysis)와 HMM(Hidden Markov Model)으로 한국어 단모음을 분류하였다. 트레이닝 단계에서 입력 받은 데이터로 근육조합을 최적화하고, 최적화 결과를 인식단계에 적용한다. 이때, 새로운 근전도 신호를 입력받고 한국어 단모음을 최종 인식한다. 실험결과 제안한 방법의 인식 정확도가 QDA에서 평균 85.7%, HMM에서 평균 75.1%를 보였다.

• International Journal of Control, Automation, and Systems
• /
• 제3권2호
• /
• pp.152-158
• /
• 2005

Commercial lower limb prostheses or orthotics help patients achieve a normal life. However, patients who use such aids need prolonged training to achieve a normal gait, and their fatigability increases. To improve patient comfort, this study proposed a method of predicting gait angle using neural networks and EMG signals. Experimental results using our method show that the absolute average error of the estimated gait angles is $0.25^{\circ}$. This performance data used reference input from a controller for the lower limb orthotic or prosthesis controllers while the patients were walking.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1491-1499
• /
• 2019

Insufficient sleep time and bad sleep quality causes many illnesses and it's research became more and more important. The most common method for measuring sleep quality is the polysomnography(PSG). The PSG is a test used to diagnose sleep disorders. The most common PSG data is obtained from the examiner, which attaches several sensors on a body and takes sleep overnight. However, most of the sleep stage classification in PSG are low accuracy of the classification. In this paper, we have studied algorithm for sleep level classification based on machine learning which can replace PSG. EEG, EOG, and EMG channel signals are studied and tested by using CNN algorithm. In order to compensate the performance, a mixed model using both CNN and DNN models is designed and tested for performance.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권4호
• /
• pp.300-308
• /
• 2004

Nowadays, many people have a lot of time on chair in their life. If the sitting posture is not correct, there is some trouble with the waist. And if the sitting posture goes on long time at a slant, it sometimes causes the hurts of waist or the deformded spinal column. A crouched posture is an obstacle to breath and it give rise to drowsiness because of the lack of oxygen. The sitting posture is a habit so that people can't feel it oneself and look over some kind of risks. The evaluation of the sitting posture is analyzed by measuring EMG of spinal both side of spinal-bones. In this paper, we can evaluate a right the sitting posture by analyzing the increase of the tention of muscle in one or the other side of muscles when the posture inclines one side and describes the usefulness of the signal of EMG to evaluate the influence of the sitting posture on waist.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1173-1178
• /
• 2005

This paper proposes an IPMC actuating system with a bio-mimetic function. EMG signals generated by an intended contraction of muscles in forearm are used for the actuation of the IPMC. To obtain higher actuation force of the IPMC, the single layered as thick as 800 [${\mu}$m] or multi-layered IPMC (Nafion) of which each layer can be as thick as 178 [${\mu}$m] are prepared. The experimental results using an implemented IPMC control system show a possibility and a usability of the bio-mimetic artificial muscle.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 1부
• /
• pp.222-227
• /
• 2007

본 논문에서는 지체장애인들이 유효한 말초신경신호를 이용하여 컴퓨터를 사용할 수 있는 인터페이스를 개발하였다. 손목의 움직임을 통해 아래팔 4부분으로부터 근전도 (electromyogram, EMG) 신호를 추출하였고, 다층 인식 신경망을 사용하여 사용자의 의도를 추출하였다. 이를 통하여 마우스 커서의 움직임을 제어하고, 마우스 버튼을 클릭하는 동작을 할 수 있으며, 시각 디스플레이 장치에 표시된 핸드폰 자판과 같은 유저 인터페이스를 통해 컴퓨터에 글자를 입력할 수 있게 하였다. 추가적으로 Fitts' law를 사용하여 본 인터페이스의 사용성을 평가하였고, 이를 기존연구와 비교함으로써 본 인터페이스의 효용성을 검증하였다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2000년도 춘계종합학술대회
• /
• pp.402-405
• /
• 2000

본 논문에서는 근육의 움직임에 의해 유발되는 전기적 신호인 근전도(EMC) 신호를 신경회로망을 통해 분류하여 인체의 움직임을 파악하는 방법을 제안한다 신호분류를 위한 신경회로망으로 학습에 의해 스스로 출력뉴런을 구성하는 SOM을 사용하였으며, 실험과 시뮬레이션을 통해 제안한 방식의 효과를 확인하였다.

• 대한인간공학회지
• /
• 제14권2호
• /
• pp.1-14
• /
• 1995

Neuromuscular difference between normal subjects and low-back pain patients has been identified in terms of neural excitation signal measured by Electromyography (EMG) under the dynamic flexion/extension trunk motion. Ten healthy subjects and ten low-back pain patients were recruited for this study. New parameters and normalization technique were introduced to quantify the muscle excitation pattern among the flexor-extensor pairs of muscles : rectus abdominis (RA)-erector spinae (ES at L1 and L5 level), external oblique (EO)-internal oblique (IO), rectus femoris (quadricep : QUD)-biceps femoris( hamstring : HAM), and tibialis anterior (TA)-gastrocnemius (GAS). Results indicated that the temporal EMG pattern such as peak timing difference between the hip flexor (QUD) and extensor (HAM) and the duration of coexcitation between ES at L5 and RA muscle pairs showed a statistically significant difference between normal subjects and low-back pain patients. Improtantly, this study presented a new technique to identify the dynamic muscle excitation pattern that canb be least affected by EMG-length-velocity relationship. Further study can performed to validate this method for clinical application to quantitatively identify the low-back pain patients in the future.

• 대한전자공학회논문지
• /
• 제25권3호
• /
• pp.335-342
• /
• 1988

In this paper, we proposed a new algorithm for EMG low frequency analysis. Through the power spectrum analysis of Gaussian's, Gamma's and Erlang's PDF(probability density function) based on the proposed algorithm, the proper PDF of IPI (inter pulse interval) representing the firing rate of muscle was suggested. In order to verify the proposed algorithm EMG signals of masseter and biceps muscle were detected by surface electrode and its power spectrum analysis was performed. The experimental results are compared with the computer simulaiton. As a result, the masseter muscle's IPI was fitted by Gamma PDF, having a 10Hz fundamental frequency including n(1+\ulcornerfp high harmnic frequency on 10% MVC(maximum voluntary contaraction). And the biceps muscle's IPI was fitted by Gaussian PDF, also it have a 14Hz fundamental frequency.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1989년도 춘계학술대회
• /
• pp.61-65
• /
• 1989

In this paper, a method of the measument the degree of the musule fatigue by Short Time Fourier Analysis of the EMG signals from human biceps in the action state is proposed. For this purpose, fatigue state and recovery state of 10 persons EMG signals are sampled. And then spectrum centroids are analyzed with respect to the change of sample time window. As result of 10 persons experiment, we know that person A is most good recovery stale.