• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.51-56
• /
• 2023

This study investigates the effect of sEMG sampling frequency on CNN learning performance at Korean finger number recognition application. Since the bigger sampling frequency of sEMG signals generates bigger size of input data and takes longer CNN's learning time. It makes making real-time system implementation more difficult and more costly. Thus, there might be appropriate sampling frequency when collecting sEMG signals. To this end, this work choose five different sampling frequencies which are 1,024Hz, 512Hz, 256Hz, 128Hz and 64Hz and investigates CNN learning performance with sEMG data taken at each sampling frequency. The comparative study shows that all CNN recognized Korean finger number one to five at the accuracy of 100% and CNN with sEMG signals collected at 256Hz sampling frequency takes the shortest learning time to reach the epoch at which korean finger number gestures are recognized at the accuracy of 100%.

• Journal of Biomedical Engineering Research
• /
• v.16 no.4
• /
• pp.507-516
• /
• 1995

The nonstationary identifier in the DCT domain is suggested in this study for the identification of AR parameters of above-lesion upper-trunk electromyographic (EMG) signals as a means of developing a reliable real time signal to control functional electrical stimulation (FES) in paraplegics to enable primitive walking. As paraplegic shifts his posture from one attitude to another, there is transition period where the signal is clearly nonstationary. Also as muscle fatigues, nonstationarities become more prevalent even during stable postures. So, it requires a develpment of time varying nonstationary EMG signal identifier. In this paper, time varying nonstationary EMG signals are transformed into DCT domain and the transformed EMG signals are modeled and analyzed in the transform domain. In the DCT domain, we verified reduction of condition number and increment of the smallest eigenvalue of input correlation matrix that influences numerical properties and mean square error were compared with SLS algorithm, and the proposed algorithm is implemented using IMS T-805 parallel processing computer for real time application.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.12
• /
• pp.129-137
• /
• 2013

As the usage of computer based systems continues to increase in our normal life, there are constant efforts to enhance the accessibility of information for handicapped people. For this, it is essential to develop new interface ways for physical disabled peoples by means of human-computer interface (HCI) or human-machine interface (HMI). In this paper, we developed HMI using electromyogram (EMG) and electrooculogram (EOG) for people with physical disabilities. Developed system is composed of two modules, hardware module for signal sensing and software module for feature extraction and pattern classification. To maximize ease of use, only two skin contact electrodes are attached on both ends of brow, and EOG and EMG are measured simultaneously through these two electrodes. From measured signal, nine kinds of command patterns are extracted and defined using signal processing and pattern classification method. Through Java based real-time monitoring program, developed system showed 92.52% of command recognition rate. In addition, to show the capability of the developed system on real applications, five different types of commands are used to control ER1 robot. The results show that developed system can be applied to disabled person with quadriplegia as a novel interface way.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.1
• /
• pp.55-64
• /
• 2004

Conventional bipolar surface electromyography(EMG) technique detects only the superimposed electromyographic activity of a large number of motor units due to its low spatial resolution. For the diagnosis of neuromuscular disorder, the information of single MU is required. In this paper, 9 channel array surface electrode system was as designed and MLoG filter was proposed. Also the MCPT(modified convolution processing technique)method was proposed for the improvement of MUAP resolution. For performance evaluation, power spectrum analysis of random data and raw EMG signal comparison of MUAP shape and quantitative estimation of SNR were executed. As a result, the MUAP resolution improvement of 32％ was obtained from the standpoint of the signal-to-noise ratio(SNR).

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.9
• /
• pp.560-567
• /
• 2003

EMG recordings of the electrical activity of muscle have proved to be a valuable tool in studying muscle function and reflex activity. SP(silent period) is elicited by a electrical stimulation on the chin during isometric contraction of jaw muscle. This paper proposes a model of the inhibitory reflex mechanism of jaw muscle after electrical stimulation. The SPs of jaw muscle after a electrical stimulation to the chin were divided into SP1 and SP2. SP1 is produced by the activation of periodontal receptors. The activation of nociceptors contributes to the SP2. As a result, the EMG signal generated by a proposed a model of inhibitory reflex mechanism is similar to real both EMG signal including SP1 and SP2. The present study have shown differences of SP1 and SP2 induced by inhibitory reflex mechanism.

• Journal of Biomedical Engineering Research
• /
• v.10 no.1
• /
• pp.11-16
• /
• 1989

This paper describes the AR model of EMG signal during maximum voluntary contraction. By comparing the AR coefficients and the reflection coefficients of the AR model with the median frequency of power spectrum, it is proved that muscle fatigue can be measured by the AR and the reflection coefficients. In the estimation procedure of AR model parameter, the autocorrelation method is superior to the covariance method, and it is determined that the optimal order is six. As the muscle becomes fatigue, the median frequency of power spectrum is declined, and the AR coefficient [$a_1$] and the reflection coefficient [$k_1$] are also decreased. Therefore the muscle fatigue can be measured by the AR parameter.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.6
• /
• pp.302-308
• /
• 2001

SVD(Singular Value Decomposition) filter for the suppression of EMG in multi-lead stress ECG is studied. SVD filter consists of two parts. In the first part, the basis vectors were chosen from the averaged singular vectors obtained from the decomposed noise-free ECG. The singular vector is computed from the stress ECG and is compared itself with basis vectors to know whether the noise exist in stress ECG. In the second part, the existing elimination method is used, when one(or two) channels is(or are) contaminated by noise. But the proposed enhanced SVD filter is used in case of having the noise in the many channels. During signal decomposition and reconstruction, the noise-free channel or the least noisy channel have the weight of 1, the next less noisy channel has the weight of 0.8. In this way, every channel was weighted by decreased of 0.2 in proportion to the amount of the added noise. For the evaluation of the proposed enhanced SVD filter, we compared the SNR computed by the enhanced SVD filter with the standard average filter for the noise-free signal added with artificial noise and the patient data. The proposed SVD filter showed better in the SNR than the standard average filter. In conclusion, we could find that the enhanced SVD filter is more proper in processing multi-lead stress ECG.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.1417-1418
• /
• 2013

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.7 no.2
• /
• pp.55-62
• /
• 2013

The exoskeleton robot to assist walking of hemiplegia patients or disabled persons has been studied in this paper. The exoskeleton robot with degrees of freedom of 2 axis has been developed and tested for joint motion. The obtained EMG signal from normal person was analyzed and the control signal was extracted from it for convenient and automotive performance of assistance robot to help hemiplegia patient walks as normal person does. the purpose of using FES(Functional Electrical Stimulation) for hemiplegia patient's walk is to restore damaged body function by this, but this could give fatal electrical shock to patients by wrong use or cause quick fatigue in muscle by continuous stimulation. The convenient movement of hemiplegia patients with minimum muscle fatigue was looked possibly by operation of assistance robot exoskeleton using control signal. and the walking assistance exoskeleton robot seemed works more efficiently than using FES stimulator. The experiment in this study was performed based on usual motion in our life like walking, standing-up, sitting-down, and particularly feedback control system using Piezo sensor along with button switch was applied for smooth swing motion in walking. The experiment also shows that hemiplegia patients can move conveniently by using electromyogram signal of healthy leg for the operation signal of assistance robot system attached at damaged symmetrical leg.

• Journal of information and communication convergence engineering
• /
• v.9 no.6
• /
• pp.743-746
• /
• 2011

An implementation for surface EMG network analysis and vertical control system of robotic arm is presented in this paper. The transmembranes are simulated by equivalent circuit and cable equation for propagation to be converted to circuit networks. The implementation is realized to be derived from the detecting EMG signal from 3 electrodes, and EMG transmembrane signals of human arm muscles are detected by several surface electrodes, high performance amplifier and filtering, converting analog to digital data and driving a servomotor for spontaneous robotic arm. The system is experimented by monitoring multiple steps vertical control angles corresponding to biceps muscle movement. The experimental results are that the vertical moving control level is measured to around 2 degrees and mean error ranges are lower 5%.