• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.1062-1065
• /
• 2002

We have evaluated the ability of a time-delayed artificial neural network (TDANN) to predict muscle forces using only eletromyographic(EMG) signals. To achieve this goal, tendon forces and EMG signals were measured simultaneously in the gastrocnemius muscle of a dog while walking on a motor-driven treadmill. Direct measurements of tendon forces were performed using an implantable force transducer and EMG signals were recorded using surface electrodes. Under dynamic conditions, the relationship between muscle force and EMG signal is nonlinear and time-dependent. Thus, we adopted EMG amplitude estimation with adaptive smoothing window length. This approach improved the prediction ability of muscle force in the TDANN training. The experimental results indicated that dynamic tendon forces from EMG signals could be predicted using the TDANN, in vivo.

• Proceedings of the IEEK Conference
• /
• 2001.06e
• /
• pp.65-68
• /
• 2001

In the rehabilitation robotic arm systems for the disabled with spinal code injury, EMG signals are used in the control of the robotic arm. EMG signals are corrupted by many kinds of noises such as ECG signal, power noise and contact noise of electrode. Noise rejection improves the performance of the EMG pattern classification. In this paper, a variable bandwidth filter (VBF) and wavelet transform are used for the noise rejection of EMG signals and the comparison of SNR is given. Also, some statistical characteristics of features are investigated.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.843-850
• /
• 2017

The EMG amplitude estimator, which has been investigated as an indicator of muscle force, is utilized as the control input to artificial prosthetic limbs. This paper describes an application of the optimal EMG amplitude estimator to the surface EMG signals recorded during constant isometric %MVC (maximum voluntary contraction) for 30 seconds and reports on assessing performance of the amplitude estimator from the application. Surface EMG signals, a total of 198 signals, were recorded from biceps brachii muscle over the range of 20-80%MVC isometric contraction. To examine the estimator performance, a SNR(signal-to-noise ratio) was computed from each amplitude estimate. The results of the study indicate that ARV(average rectified value) and RMS(root mean square) amplitude estimation with forth order whitening filter and 250[ms] moving average window length are optimal and showed the mean SNR improvement of about 50%, 40% and 20% for each 20%MVC, 50%MVC and 80%MVC surface EMG signals, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.2
• /
• pp.291-296
• /
• 2014

Most of the statistical signal analysis processed in the time domain and the frequency domain are based on the assumption that the signal is weakly stationary(wide sense stationary). Therefore, it is necessary to know whether the surface EMG signals processed in the statistical basis satisfy the condition of weak stationarity. The purpose of this study is to analyze the accuracy of the Run-test, modified Run-test, RA(reverse arrangement)-test, and modified RA-test for assessing surface EMG signal stationarity. Six stationary and three non-stationary signals were simulated by using sine wave, AR(autoregressive) modeling, and real surface EMG. The simulated signals were tested for stationarity using nine different methods of Run-test and RA-test. The results showed that the modified Run-test method2 (mRT2) classified exactly the surface EMG signals by stationarity with 100% accuracy. This finding indicates that the mRT2 may be the best way for assessing stationarity in surface EMG signals.

• Journal of Biomedical Engineering Research
• /
• v.27 no.3
• /
• pp.101-109
• /
• 2006

It has been known that there is strong relationship between human voices and the movements of the articulatory facial muscles. In this paper, we utilize this knowledge to implement an automatic speech recognition scheme which uses solely surface electromyogram (EMG) signals. The EMG signals were acquired from three articulatory facial muscles. Preliminary, 10 Korean digits were used as recognition variables. The various feature parameters including filter bank outputs, linear predictive coefficients and cepstrum coefficients were evaluated to find the appropriate parameters for EMG-based speech recognition. The sequence of the EMG signals for each word is modelled by a hidden Markov model (HMM) framework. A continuous word recognition approach was investigated in this work. Hence, the model for each word is obtained by concatenating the subword models and the embedded re-estimation techniques were employed in the training stage. The findings indicate that such a system may have a capacity to recognize speech signals with an accuracy of up to 90%, in case when mel-filter bank output was used as the feature parameters for recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.84.4-84
• /
• 2001

In this paper, we present a method to classify electromyogram (EMG) signals which are utilized to be control signals for patient-responsive walker-supported system for paraplegics. Patterns of EMG signals for dierent walking motions are classied via adequate filtering, real EMG signal extraction, AR-modeling, and modified self-organizing feature map (MSOFM). More efficient signal processing is done via a data-reducing extraction algorithm. Moreover, MSOFM classifies and determines the classified results are presented for validation.

• Journal of TMJ Balancing Medicine
• /
• v.6 no.1
• /
• pp.1-4
• /
• 2016

We investigated the potential of electromyography (EMG) for diagnosing imbalance in the temporomandibular joint (TMJ) to apply functional cerebrospinal therapy (FCST). The electromyography signals were measured in the sternocleidomastoid muscle (SCM) in patients with temporomandibular disorder (TMD) while a FCST specialist conducted a restricted cervical rotation test. In addition, we also observed the changes in the electromyography signals according to pre-treatment or treatment with a TMJ balancing appliance (TBA), a customized TMJ balancing appliance (CBA), or a CBA with one paper bar. The right SCMs of the two patients with right TMJ imbalance had high EMG signals in the right cervical rotation test, while the left SCMs showed low EMG signals in the left rotation. In addition, the high EMG signals in the right SCMs decreased when using the TBA or the CBA, but the EMG signals of the left SCMs showed low EMG values during the treatments. Furthermore, the EMG signals of the right SCMs rose again after artificial imbalance of the right TMJ by the CBA with one paper bar. This case report demonstrated the potential of EMG as an objective diagnostic method for FCST.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.7
• /
• pp.1014-1019
• /
• 2013

Signal processing techniques based on fractional order calculus have been successfully applied in analyzing heavy-tailed non-Gaussian signals. It was found that the surface EMG signals from the muscles having nuero-muscular disease are best modeled by using the heavy-tailed non-gaussian random processes. In this regard, this paper describes an application of digital fractional order lowpass differentiators(FOLPD, weighted FOLPD) based on the fractional order calculus in detecting peaks of surface EMG signal. The performances of the FOLPD and WFOLPD are analyzed based on different filter length and varying MUAP wave shape from recorded and simulated surface EMG signals. As a results, the WFOLPD showed better SNR improving factors than the existing WLPD and to be more robust under the various surface EMG signals.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.8
• /
• pp.1128-1133
• /
• 2014

Most of the statistical signal analysis processed in the time domain and the frequency domain are based on the assumption that the signal is weakly stationary(wide sense stationary). Therefore, it is necessary to know whether the surface EMG signals processed in the statistical basis satisfy the condition of the weak stationarity. The purpose of this study is to find optimal segment length of surface EMG signal for assessing stationarity with the modified Run-test and RA-test. Ten stationary surface EMG signals were simulated by AR(autoregressive) modeling, and ten real surface EMG signals were recorded from biceps brachii muscle and then modified to have non-stationary structures. In condition of varying segment length from 20ms to 100ms, stationarity of the signals was tested by using six different methods of modified Run-test and RA-test. The results indicate that the optimal segment length for the surface EMG is 30ms~35ms, and the best way for assessing surface EMG signal stationarity is the modified Run-test (Run2) method using this optimal length.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.641-642
• /
• 1986

We present a method for the estimation of intramuscular electromyographic(EMG) signals from the given surface EMG signals. This method is based on representing the surface EMG signal as an autoregressive(AR) time model with a delayed intramuscular EMG signal as an input. The parameters of the time series model that transforms the intramuscular signal to the surface signal are identified. The identified model is then used in estimating the intramuscular signal from the surface signal.