• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.900-902
• /
• 1999

본 연구에서는 유전알고리즘을 이용한 인간의 팔운동 근전신호의 기능분리에 관한 방법을 제시하였다. 6가지 기능의 팔운동 시에 근전신호의 특성을 유전알고리즘을 이용하여 기능분리 하였다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.12
• /
• pp.1248-1255
• /
• 2011

In daily life, another major role of human hand is a communicative function using hand gestures besides grasp function. Therefore, if amputees can express their intention by the prosthetic hand, they can much actively participate in social activities. Thus, this paper propose myoelectric multi-function prosthetic hand which can express 6 useful hand gestures such as Rock, Scissors, Paper, Indexing, Ok and Thumb-up. It was designed as under-actuated structure to minimize volume and weight of the prosthetic hand. Moreover, in order to effectively control various hand gestures by only two EMG sensors, we propose a control strategy that the signal type are expanded as "Strong" and "Light", and hand gestures are hierarchically classified for the intuitive control. Finally, we prove the validity of the developed prosthetic hand with the experiment.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2356-2358
• /
• 2004

This thesis aims to investigate new approaches to the control strategies of human arm movements and its application for the human interface. By analyzing myoelectric signal(MES) from the arm movements of the normal human subjects, neurological informations obtained patterned could be used to identify different movement patterns of the arm movement. In this paper Artificial neural network for separation of the contraction patterns of four kinds of arm movements, i.e. and flexion and extension of the elbow and adduction and abduction of the forearm were adopted through computer simulation and experiments results were compared with the experimental added-load arm movements.

• Journal of Biomedical Engineering Research
• /
• v.17 no.3
• /
• pp.379-386
• /
• 1996

This paper describes an approach for classifying myoelectric patterns using a multilayer perceptrons (MLP's) and hidden Markov models (HMM's) hybrid classifier. The dynamic aspects of EMG are important for tasks such as continuous prosthetic control or vari- ous 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 contrasts the multilayer feedforward networks are suitable for static patterns. Ank 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 MLP and HMM algorithms that might lead to further improved EMG recognition systems.

• The Journal of Korea Robotics Society
• /
• v.13 no.4
• /
• pp.265-271
• /
• 2018

The recent prosthetic technologies pursue to control multi-DOFs (degrees-of-freedom) hand and wrist. However, challenges such as high cost, wear-ability, and motion intent recognition for feedback control still remain for the use in daily living activities. The paper proposes a multi-channel knit band sensor to worn easily for surface EMG-based prosthetic control. The knitted electrodes were fabricated with conductive yarn, and the band except the electrodes are knitted using non-conductive yarn which has moisture wicking property. Two types of the knit bands are fabricated such as sixteen-electrodes for eight-channels and thirty-two electrodes for sixteen-channels. In order to substantiate the performance of the biopotential signal acquisition, several experiments are conducted. Signal to noise ratio (SNR) value of the knit band sensor was 18.48 dB. According to various forearm motions including hand and wrist, sixteen-channels EMG signals could be clearly distinguishable. In addition, the pattern recognition performance to control myoelectric prosthesis was verified in that overall classification accuracy of the RMS (root mean squares) filtered EMG signals (97.84%) was higher than that of the raw EMG signals (87.06%).

• Journal of Biomedical Engineering Research
• /
• v.25 no.6
• /
• pp.471-478
• /
• 2004

Electromyogram (EMC) signal generated by voluntary contraction of muscles is often used in a rehabilitation devices such as an upper limb prosthesis because of its distinct output characteristics compared to other bio-signals. This paper proposes an EMG-based human-computer interface (HCI) for the control of the above-elbow prosthesis or the wheelchair. To control such rehabilitation devices, user generates four commands by combining voluntary contraction of two different muscles such as levator scapulae muscles and flexor-extensor carpi ulnaris muscles. The muscle contraction is detected by comparing the mean absolute value of the EMG signal with a preset threshold value. However. since the time difference in muscle firing can occur when the patient tries simultaneous co-contraction of two muscles, it is difficult to determine whether the patient's intention is co-contraction. Hence, the use of the comparison method using a single threshold value is not feasible for recognizing such co-contraction motion. Here, we propose a novel method using double threshold values composed of a primary threshold and an auxiliary threshold. Using the double threshold method, the co-contraction state is easily detected, and diverse interface commands can be used for the EMG-based HCI. The experimental results with real-time EMG processing showed that the double threshold method is feasible for the EMG-based HCI to control the myoelectric prosthetic hand and the powered wheelchair.

• 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 the Ergonomics Society of Korea
• /
• v.33 no.2
• /
• pp.143-153
• /
• 2014

Objective: The aim of this study is to investigate the effects of trunk-forearm supported sitting on trunk flexion angle, trunk extensor fatigue and seat contact pressure. Background: The relationship between sitting posture and musculoskeletal disorders of the trunk extensor fatigue and seat contact pressure has been documented. The trunk-forearm support type ergonomic chair was devised from the fact that trunk-forearm support has been reported to reduce trunk extensor activity and discomfort. Method: Using three different sitting postures, upright ($P_1$), trunk-forearm supported ($P_2$) and normal sitting ($P_3$), six healthy subjects participated in the study. Motion capture system was used to collect head and trunk flexion angle, and surface electromyography (sEMG) was used to collect myoelectric signal of upper trapezius, lower trapezius, erector spinae, multifidus, and pressure mat system was used to measure seat contact pressure. Results: When trunk and forearm were supported by the ergonomic chair, higher head flexion angle showed upright > trunk-forearm supported > normal in order, and muscle fatigue showed less than upright and normal sitting. Mean seat contact pressure decreased 19% than upright sitting. But muscle fatigue was not affected by each condition. Conclusion: Trunk-forearm supported sitting of the ergonomic chair showed positive effect in respect of trunk and head flexion angle, trunk extensor fatigue, seat contact pressure. To acquire comprehensive understanding of the effectiveness of the ergonomic chair, further studies such as anatomical effects from measurement of external applied loading effect to the body from interface pressure analysis are required. Application: The results of the publishing trend analysis might help physiological effects of trunk-forearm support type chair.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.2 s.302
• /
• pp.39-48
• /
• 2005

This paper proposes a novel approach to recognize nine kinds of motion for a multifunction myoelectric hand, acquiring four channel EMG signals from electrodes placed on the forearm. To analyze EMG with properties of nonstationary signal, time-frequency features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a feature projection composed of PCA and SOFM. The dimensionality reduction by PCA simplifies the structure of the classifier, and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features to a new feature space with high class separability. Finally a multilayer neural network is employed as the pattern classifier. From experimental results, we show that the proposed method enhances the recognition accuracy, and makes it possible to implement a real-time pattern recognition.