• Journal of Electrical Engineering and information Science
• /
• v.2 no.6
• /
• pp.20-27
• /
• 1997

We present a method of electromyographic(EMG) pattern recognition to identify motion commands for the control of a prosthetic arm by evidence accumulation with multiple parameters. Integral absolute value, variance, autoregressive(AR) model coefficients, linear cepstrum coefficients, and adaptive cepstrum vector are extracted as feature parameters from several time segments of the EMG signals. Pattern recognition is carried out through the evidence accumulation procedure using the distances measured with reference parameters. A fuzzy mapping function is designed to transform the distances for the application of the evidence accumulation method. Results are presented to support the feasibility of the suggested approach for EMG pattern recognition.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.199-202
• /
• 1996

In this paper, we suggested the combination of HMM(Hidden Markov Model) and MLP (Multi-Layer Perceptron) with GA(genetic algorithm) for a recognition of EMG signals. To describe EMG signal's dynamic properties, HMM algorithm was adapted and due to its outstanding abilities in static signal classification MLP was connected as a real processor. We also used GA( Genetic Algorithm) for improving MLP's learning rate. Experimental results showed that the suggested classifier gave higher EMG signal recognition rates with faster learning time than other one.

• Journal of the Ergonomics Society of Korea
• /
• v.11 no.1
• /
• pp.81-92
• /
• 1992

A two-dimensional static biochemical model of lower extremity in the seated posture was developed to assess muscular activities of lower extremity required for a variety of foot pedal operations. We found that the double linear optimization method that has been used for modelling articulated body segments does no predict the forces generated by biarticular muscles reasonably, so the revised double linear optimization scheme was used to consider the synergistic effects of biarticular muscles in our model, assuming that the muscle forces are distributed proportionally based on their physiological cross sectional area. The model incorporated three rigid body se- gments with six muscles to represnet lower extremity. For the model validation, three male subjects performed the experiments in which EMG activities of six lower extremity muscles were measured. Predicted muscle forces were compare with the corresponding EMG amplitudes and it showed no statistical difference. The model being developed can be used to design and assess pedal and foot-related tool design.

• Proceedings of the KOSOMBE Conference
• /
• v.1991 no.11
• /
• pp.25-29
• /
• 1991

In the field of prosthesis arm control, tile pattern classification of the EMG signal is a required basis process and also the estimation of force from col looted EMG data is another necessary duty. But unfortunately, what we've got is not real force but an EMG signal which contains the information of force. This is the reason why he estimate the force from the EMG data. In this paper, when we handle the EMG signal to estimate the force, spatial prewhitening process is applied from which the spatial correlation between the channels are removed. And after the orthogonal transformation, which is used in the force estimation process the transformed signal is inputed into the probabilistic model for pattern classification. To verify the different results of the multiple channels, SNR(signal to noire ratio) function is introduced.

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.48-57
• /
• 2003

This paper describes an approach for classifying myoelectric patterns using a multilayer perceptrons (MLP's) with genetic algorithm and hidden Markov models (HMM's) hybrid classifier. Genetic Algorithms play a role of selecting Multilayer Perceptron's optimized initial connection weights by its typical global search. The dynamic aspects of EMG are important for tasks such as continuous prosthetic control or various time length EMG signal recognition, which have not been successfully mastered by the most neural approaches. It is known that the hidden Markov model (HMM) is suitable for modeling temporal patterns. In contrast, the multilayer feedforward networks are suitable for static patterns. And, a lot of investigators have shown that the HMM's to be an excellent tool for handling the dynamical problems. Considering these facts, we suggest the combination of ANN and HMM algorithms that might lead to further improved EMG recognition systems.

• Journal of Biomedical Engineering Research
• /
• v.40 no.6
• /
• pp.242-249
• /
• 2019

Forearm electromyography (EMG) generated by wrist movements has been widely used to develop an electrical prosthetic hand, but EMG generated by finger movements has been rarely used even though 20% of amputees lose fingers. The goal of this study is to improve the classification performance of different finger movements using a deep learning algorithm, and thereby contributing to the development of a high-performance finger-based prosthetic hand. Ten participants took part in this study, and they performed seven different finger movements forty times each (thumb, index, middle, ring, little, fist and rest) during which EMG was measured from the back of the right hand using four bipolar electrodes. We extracted mean absolute value (MAV), root mean square (RMS), and mean (MEAN) from the measured EMGs for each trial as features, and a 5x5-fold cross-validation was performed to estimate the classification performance of seven different finger movements. A long short-term memory (LSTM) model was used as a classifier, and linear discriminant analysis (LDA) that is a widely used classifier in previous studies was also used for comparison. The best performance of the LSTM model (sensitivity: 91.46 ± 6.72%; specificity: 91.27 ± 4.18%; accuracy: 91.26 ± 4.09%) significantly outperformed that of LDA (sensitivity: 84.55 ± 9.61%; specificity: 84.02 ± 6.00%; accuracy: 84.00 ± 5.87%). Our result demonstrates the feasibility of a deep learning algorithm (LSTM) to improve the performance of classifying different finger movements using EMG.

• Proceedings of the KOSOMBE Conference
• /
• v.1993 no.11
• /
• pp.145-150
• /
• 1993

It is an important component of the diagnosis to research the morphological changes of EMG in pathological conditions. In order to provide an EMG signal resulting from a predetermined neuromuscular pathophysiology, we have initially developed a mathmatical model of electromyographic interference pattern(IP). It can be used to study the variation of the IP resulting from morphological and electrophysiological changes occurring in disease states, because the model computes the IP from the underlying fiber and muscle structure. We performed quantative analysis or the model output, focusing on IPs resulting from simulations of dystrophic fiber loss and the MU denervation and reinnervation typical of neuropathies. To discribe the characteristics of IPs associated with these pathologies, a set of frequency domain discriptors, activity, mobility, and complexity were used, as well as several measures of the spectral density function. These discriptors demonstrate distinct patterns of variation corresponding to morphological changes observed in disease states, and closely with results obtained from the classical method, turn/amp technique.

• Proceedings of the ESK Conference
• /
• 1994.04a
• /
• pp.124-135
• /
• 1994

A biomechanical model of lower extremity in seated postures was developed to assess muscular activities of lower extremity involved in a variety of foot pedal operations. It is found that nonlinear optimization method which has been used for modeling the articulated body segments does not predict the forces generated from biarticular muscles reasonably, so the revised nonlinear optimization scheme was employed to consider the synergistic effects of biarticular muscles in the model, assuming that the muscle forces are distributed proportionally based on their physiological cross sectional area and moment arm. The model incorporated four rigid body segments with the nine muscles to represent lower extreimity. For the model valida- tion, three male subjects performed the experiments in which EMG activities of the nine lower extremity muscles were measured. Predicted muscle forces were compared with the corresponding EMG amplitudes and it showed no statistical difference. The developed model can be used to design and to assess the pedals and foot-related equipments design.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.4
• /
• pp.382-392
• /
• 2023

Objective : The use of indocyanine green videoangiography (ICG-VA) to assess blood flow in the brain during cerebrovascular surgery has been increasing. Clinical studies on ICG-VA have predominantly focused on qualitative analysis. However, quantitative analysis numerical modelling for time profiling enables a more accurate evaluation of blood flow kinetics. In this study, we established a multiple exponential modified Gaussian (multi-EMG) model for quantitative ICG-VA to understand accurately the status of cerebral hemodynamics. Methods : We obtained clinical data of cerebral blood flow acquired the quantitative analysis ICG-VA during cerebrovascular surgery. Varied asymmetric peak functions were compared to find the most matching function form with clinical data by using a nonlinear regression algorithm. To verify the result of the nonlinear regression, the mode function was applied to various types of data. Results : The proposed multi-EMG model is well fitted to the clinical data. Because the primary parameters-growth and decay rates, and peak center and heights-of the model are characteristics of model function, they provide accurate reference values for assessing cerebral hemodynamics in various conditions. In addition, the primary parameters can be estimated on the curves with partially missed data. The accuracy of the model estimation was verified by a repeated curve fitting method using manipulation of missing data. Conclusion : The multi-EMG model can possibly serve as a universal model for cerebral hemodynamics in a comparison with other asymmetric peak functions. According to the results, the model can be helpful for clinical research assessment of cerebrovascular hemodynamics in a clinical setting.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.10
• /
• pp.831-841
• /
• 1991

A combined model of probabilistic and MLP(multi layer perceptron) model is proposed for the pattern classification of EMG( electromyogram) signals. The MLP model has a problem of not guaranteeing the global minima of error and different quality of approximations to Bayesian probabilities. The probabilistic model is, however, closely related to the estimation error of model parameters and the fidelity of assumptions. A proper combination of these will reduce the effects of the problems and be robust to input variations. Proposed model is able to get the MAP(maximum a posteriori probability) in the probabilistic model by estimating a priori probability distribution using the MLP model adaptively. This method minimize the error probability of the probabilistic model as long as the realization of the MLP model is optimal, and this is a good combination of the probabilistic model and the MLP model for the usage of MLP model reliability. Simulation results show the benefit of the proposed model compared to use the Mlp and the probabilistic model seperately and the average calculation time fro classification is about 50ms in the case of combined motion using an IBM PC 25 MHz 386model.