• 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.

• Journal of Biomedical Engineering Research
• /
• v.29 no.3
• /
• pp.205-211
• /
• 2008

A method of detecting the specific patterns related to hand motions using the surface EMG(electromyogram) on an arm is proposed and tested. To do this, we obtain separately modeling parameters based on the LP, Prony estimator, and calculate the latency shift value between channels by cross-correlation function. Then, the coefficients and latency shift value are applied to the detection method to classify the EMG signals related to hand motions. Compared with the conventional methods, the present method are more useful to detect the motion intention of the user as an input device in the mobile and wearable computing environments. And, We expect that the results of this study are helpful in the development of rehabilitation devices for the handicapped.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.213-220
• /
• 2024

Fall detection and prevention technologies play a pivotal role in ensuring the well-being of individuals, particularly those living independently, where falls can result in severe consequences. This paper addresses the challenge of accurate and quick fall detection by proposing a Bayesian probability-based measure applied to surface electromyography (sEMG) signals. The proposed algorithm based on a Bayesian filter that divides the sEMG signal into transient and steady states. The ratio of posterior probabilities, considering the inclusion or exclusion of the transient state, serves as a scale to gauge the dominance of the transient state in the current signal. Experimental results demonstrate that this approach enhances the accuracy and expedites the detection time compared to existing methods. The study suggests broader applications beyond fall detection, anticipating future research in diverse human-robot interface benefiting from the proposed methodology.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.6 no.1
• /
• pp.67-73
• /
• 2012

In this paper, Artificial Neural Network(ANN) based motion classification algorithm is proposed to classify wrist motions using surface electromyograms(sEMG). surface EMGs are obtained from two electrodes placed on the flexor carpi ulnaris muscle and extensor carpi ulnaris muscle of 26 subjects under no strain condition during wrist motions and used to recognize wrist motions such as up, down, left, right, and rest. Feature is extracted from obtained EMG signals in time domain for fast processing and used to classify wrist motions using ANN. DAMV, DASDV, MAV, and RMS were used as features and accuracies of motion classification based on ANN were 98.03% for DAMV, 97.97% for DASDV, 96.95% for MAV, 96.82% for RMS.

• Journal of Biomedical Engineering Research
• /
• v.34 no.4
• /
• pp.212-217
• /
• 2013

Falling is one of the major public problems to the elderly, resulting in limitations of daily living activities. It can be induced by the functional loss of the balance ability and muscle strength in the elderly. It has been, however, not well investigated to suggest an effective methodology improving the balance ability and muscle strength for the prevention of the falling due to lack of information about the characteristics of the balance and muscle activations responded to the dynamic motions. The aim of the current study is, therefore, to identify the characteristics of the balance and muscle activations responded to the dynamic motions in Anterior-Posterior(AP) and Medial Lateral(ML) directions. For that, a motion capture system with eight infrared cameras, surface electromyogram system and Wii Fit system with a customized variable unstable base were used and kinematic and kinetic data obtained from the systems were analyzed for five healthy male($24.8{\pm}3.3years$, $177.4{\pm}2.0cm$, $73.9{\pm}12.9kg$, $23.5{\pm}4.0kg/m$). The results showed that the characteristics of the balance and muscle activations were differently responded to between the dynamic motions in Anterior-Posterior(AP) and Medial Lateral(ML) directions. These findings may indicate that customized dynamic motions should be applied to the training of the balance ability and muscle strength for the effective prevention of the falling. This study may be meaningful to providing basic information to establish a guideline improving effectively the balance ability and muscle strength.

• Physical Therapy Korea
• /
• v.8 no.3
• /
• pp.11-26
• /
• 2001

In rehabilitation programs involving muscle re-education and endurance exercise, it is necessary to confirm when fatigue occurs. It is also necessary to quantify fatigue, to confirm whether the muscle has been exercised sufficiently. In general, as fatigue occurs, the force-generating ability of the muscle is reduced. If the median frequency (MDF) obtained from electromyogram (EMG) power spectrum is correlated highly with work, then the timing and degree of fatigue may be confirmed. This study examined the relationship between work and MDF obtained from the EMG power spectrum during repetitive isokinetic exercise. Surface EMG signals were collected from biceps brachii and vastus lateralis of 52 normal subjects (26 males, 26 females) at $120^{\circ}/sec$ and $60^{\circ}/sec$ while performing an isokinetic exercise. The exercise was finished at 25% of peak work. MDF data was obtained using a moving fast Fourier transformation (FFT), and random noise was removed using the inverse FFT, then a new MDF data was obtained from the main signal. There was a high correlation between work and MDF during repetitiv isokinetic exercise in the biceps brachii and vastus lateralis of males and the biceps brachii of females (r=.50~.77). However, there was a low correlation between work and MDF in the vastus lateralis of females (r=.06~.19).

• PNF and Movement
• /
• v.9 no.3
• /
• pp.11-17
• /
• 2011

Purpose : The purpose of this study was to analyze the effects of proprioceptive neuromuscular facilitation (PNF) leg flexion patterns according to the hip joint angle on electromyographic activity of the trunk. Methods : Thirty healthy adults volunteered to participate in this study. Subjects were required to complete following the PNF leg flexion patterns on three different hip joint flexion $30^{\circ}$, $60^{\circ}$ and $90^{\circ}$. An surface electromyogram (SEMG) was used to record the electromyographic activities of the trunk muscle in rectus abdominis, internal oblique abdominal, external oblique abdominal, erector spinae. The data were analyzed using the a repeated measures of one-way ANOVA with post-hoc Bonferroni's correction. Result : The results of this study are summarized as follows: The EMG activities of internal abdominal oblique and elector spinae muscle showed a statistically significant difference (p<.05). Conclusion : The result show that electromyographic activity of the trunk muscles significantly changed on PNF leg flexion patterns with difference hip joint angle. Therefore, this study used to basis for the intervention of the trunk muscle strength and stabilization.

• Journal of Biomedical Engineering Research
• /
• v.16 no.2
• /
• pp.157-166
• /
• 1995

The Electroencephalogram (EEG) and evoked potential (EP) t;ave widely been used for study of brain functions. The EEG and EP signals acquired from multi-channel electrodes placed on the head surface are often interfered by other relatively large physiological signals such as electromyogram (EMG) or electroculogram (EOG). Since these artifact-affected EEG signals degrade EEG mapping, the removal of the artifact-affected EEGs is one of the key elements in neuro-functional mapping. Conventionally this task has been carried out by human experts spending lots of examination time. In this paper a neural-network based classification is proposed to replace or to reduce human expert's efforts and time. From experiments, the neural-network based classification performs as good as human experts : variation of decisions between the neural network and human expert appears even smaller than that between human experts.

• Speech Sciences
• /
• v.11 no.1
• /
• pp.55-64
• /
• 2004

This study was to determine the effects of a massage and oro-facial exercise program on spastic dysarthric patients' lip muscle function using an electromyogram (EMG). Three subjects with Spastic Dysarthria participated in the study. The surface electrodes were positioned on the Levator Labii Superior Muscle (LLSM), Depressor Labii Inferior Muscle (DLIM), and Orbicularis Oris Muscle (OOM). To examine lip muscle function improvement, the EMG signals were analyzed in terms of RMS (Root Mean Square) values and Median Frequency. In addition, the diadochokinetic movements and the rate of sentence reading were measured. The results revealed that the RMS values were decreased and the Median Frequency moved to a high frequency area. Diadochokinesis and sentence reading rates were improved.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.1
• /
• pp.8-12
• /
• 2010

In this paper, we studied on AR model order decision for extraction of EMG median frequency by t-test and ANOVA and comparison of median frequency. And we extracted well-known parameters such as zero crossing rate(ZCR), low band energy(Band) and median frequency(MDF) from surface electromyogram (EMG). And we compared to evaluate themselves as measures for fatigue.