Inhyuk Moon - Academia.edu (original) (raw)

Papers by Inhyuk Moon

This paper proposes a novel real-time EMG pattern recognition for the control of a multifunction ... more This paper proposes a novel real-time EMG pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To cope with the nonstationary signal property of the EMG, features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear 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. We implement a real-time control system for a multifunction virtual hand. From experimental results, we show that all processes, including virtual hand control, are completed within 125 msec, and the proposed method is applicable to real-time myoelectric hand co...

A Novel Powered Gait Orthosis using Pneumatic Muscle Actuator

Path planning through recognizing the height of O" stacle

5th Korea-Russia International Symposium on Science and Technology. Proceedings. KORUS 2001 (Cat. No.01EX478)

... E.Flach and R.Hoffmann, Direct mean torque control of induction motor, in Proc. European Po... more ... E.Flach and R.Hoffmann, Direct mean torque control of induction motor, in Proc. European Power Electronics and Applications (EPE'97) Trondheim, Norway, Sept. 1997, pp.3672-3677. ... of biomedical Eng. Yonsei University Heungup, Wonju city, Kangwon Province 220-710. ...

Grip force modeling of a tendon-driven prosthetic hand

2008 International Conference on Control, Automation and Systems, 2008

ABSTRACT This paper describes a grip force analysis of a tendon-driven prosthetic hand. The grip ... more ABSTRACT This paper describes a grip force analysis of a tendon-driven prosthetic hand. The grip force is equivalent to tensile force transmitted by a link mechanism. Assuming that the tensile force to pull tendon is constant, the grip force according to the angle of MCP joint is analyzed by the statics. From experimental results, we show the maximum grip force of tendon-driven finger is 6N when the constant tensile force is 14N.

9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.

Air mattress is now used widely to prevent the pressure ulcer by reducing the localized pressure ... more Air mattress is now used widely to prevent the pressure ulcer by reducing the localized pressure peaks. In this paper an air-cell mattress and its pressure control method based on an approximate anthropometric model are presented. The air-cell mattress has eighteen cylindrical air cells made of porous material allowing air leakage to contribute in reducing the development of pressure ulcer by lowering the pressure peak, temperature and humidity. To determine an optimal air-cell pressure appropriate for each user, we divide the parts of the body into four sections such as head, trunk, hip, and leg. Then, the pressure of each section is independently calculated from the weight of each part based on the individual body height and weight and the approximate anthropometric model. Air supply system for the air-cell mattress is implemented by using four electronic solenoid valves and an air compressor, and it is driven by a real-time micro-controller. The experimental results for seven subjects shows that the proposed air-cell mattress is effective for the prevention of the pressure ulcer.

Control of IPMC-based Artificial Muscle for Myoelectric Hand Prosthesis

The First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006. BioRob 2006.

ABSTRACT This paper proposes an ionic polymer metal composite (IPMC) based artificial muscle to b... more ABSTRACT This paper proposes an ionic polymer metal composite (IPMC) based artificial muscle to be applicable to the myoelectric hand prosthesis. The IPMC consists of a thin polymer membrane with metal electrodes plated chemically on both faces, and it is widely applying to the artificial muscle because it is driven by relatively low input voltage. The control commands for the IPMC-based artificial muscle is given by electromyographic (EMG) signals obtained from human forearm. By an intended contraction of the human flexor carpi ulnaris and extensor carpi ulnaris muscles, we investigated the actuation behavior of the IPMC-based artificial muscle. To obtain higher actuation force of the IPMC, the single layered as thick as 800 [mum] or multi-layered IPMC of which each layer can be as thick as 178 [mum] are prepared. As a result, the bending force was up to the maximum 12[gf| from 1[gf] by actuating the single layered IPMC with 178 [mum], but the bending displacement was reduced to 6[mm] from 30[mm]. The experimental results using an implemented IPMC control system show a possibility and a usability of the bio-mimetic artificial muscle

Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)

This paper proposes an intelligent robotic wheelchair with user-friendly human-computer interface... more This paper proposes an intelligent robotic wheelchair with user-friendly human-computer interface (HCI) based on electromyogram (EMG) signal, face directional gesture, and voice. The user's intention is transfered to the wheelchair via the HCI, and then the wheelchair is controlled to the intended direction. Additionally, the wheelchair can detect and avoid obstacles autonomously wing sonar sensors. By combining HCI into the autonomous functions, it performs safe and reliable motions while considering the user's intention. The experimental results in the crowded environment show that the proposed robotic Wheelchair is feasible for the disabled and the elderly with severe motor disabilities.

A Supervised Feature Projection for Real-Time Multifunction Myoelectric Hand Control

2006 International Conference of the IEEE Engineering in Medicine and Biology Society, 2006

EMG pattern recognition is essential for the control of a multifunction myoelectric hand. The mai... more EMG pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study is to develop an efficient feature projection method for EMG pattern recognition. To this end, we propose a linear supervised feature projection that utilizes linear discriminant analysis (LDA). We first perform wavelet packet transform (WPT) to extract the feature vector from four channel EMG signals. For dimensionality reduction and clustering of the WPT features, the LDA incorporates class information into the learning procedure and finds a linear matrix to maximize the class separability for the projected features. Finally, the multilayer perceptron (MLP) classifies the LDA-reduced features into nine hand motions. To evaluate the performance of LDA for the WPT features, we compare LDA with three other feature projection methods. From a visualization and quantitative comparison, we show that LDA has better performance for the class separability, and the LDA-projected features improve the classification accuracy with a short processing time. We implemented a real-time control system for a multifunction myoelectric hand. In experiment, we show that the proposed method achieves 97.2% recognition accuracy, and that all processes, including the myoelectric hand control, are completed within 97 msec.

Wearable EMG-based HCI for Electric-Powered Wheelchair Users with Motor Disabilities

Proceedings of the 2005 IEEE International Conference on Robotics and Automation

... 30x80[mm] size, and a Li-Ion battery (7.2[V]) was employed as the system power. ... B. Contro... more ... 30x80[mm] size, and a Li-Ion battery (7.2[V]) was employed as the system power. ... B. Control of Electric-powered Wheelchair We applied the proposed HCI to control the electric-powered ... as shown in '04', he turns left direction by elevation of left shoulder for collision avoidance. ...

Control of multifunction myoelectric hand using a real-time EMG pattern recognition

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2005

Abstract - This paper proposes a novel real-time EMG pattern recognition for the control of a mul... more Abstract - This paper proposes a novel real-time EMG pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To cope with the nonstationary signal property of the EMG, features are extracted by wavelet packet transform. For ...

Self-localization from the panoramic views for autonomous mobile robots

5th Korea-Russia International Symposium on Science and Technology. Proceedings. KORUS 2001 (Cat. No.01EX478)

Abstract This paper describes a self-localization method for mobile robots using panoramic view i... more Abstract This paper describes a self-localization method for mobile robots using panoramic view images. A panoramic view image has the information of object locations from the viewer robot perspective and the direction between the objects at each position. Among ...

Modeling of Body Weight Support System for Person with Gait Disoder

2013 4th International Conference on Intelligent Systems, Modelling and Simulation, 2013

ABSTRACT This study designed a body weight support system controlling load on a patient during ga... more ABSTRACT This study designed a body weight support system controlling load on a patient during gait training. The designed system consisted of a tow device, elevation and rotation device, and load control device. The tow device tows a patient using an electric winch, and the elevation and rotation device elevates and rotates the body weight control system using a motor and bearings. And, the load control device controls load on a patient during gait training using elasticity force of two motors and spring. Load on a patient during gait training is measured by a load measurement sensor equipped in the load control system. The load control system controls load on a patient during gait training using the value measured by the load measurement sensor. This study modeled a body weight system to obtain design variables for motors and springs of the load control device by using a dynamics interpretation package, and made a control system to perform a control simulation of the body weight control system. Based on the simulation result, this study intended to design the proposed system as a system controlling load on a patient during gait training.

IEEE Transactions on Biomedical Engineering, 2006

This paper proposes a novel real-time electromyogram (EMG) pattern recognition for the control of... more This paper proposes a novel real-time electromyogram (EMG) pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To extract a feature vector from the EMG signal, we use a wavelet packet transform that is a generalized version of wavelet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of principal components analysis (PCA) and a self-organizing feature map (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 into a new feature space with high class separability. Finally, a multilayer perceptron (MLP) is used as the classifier. Using an analysis of class separability by feature projections, we show that the recognition accuracy depends more on the class separability of the projected features than on the MLP's class separation ability. Consequently, the proposed linear-nonlinear projection method improves class separability and recognition accuracy. We implement a real-time control system for a multifunction virtual hand. Our experimental results show that all processes, including virtual hand control, are completed within 125 ms, and the proposed method is applicable to real-time myoelectric hand control without an operational time delay.

Walker Gait Analysis of Powered Gait Orthosis for Paraplegic

IFMBE Proceedings

At KOREC, first of all, a prototype of a powered gait orthosis(PGO) has been developed to reduce ... more At KOREC, first of all, a prototype of a powered gait orthosis(PGO) has been developed to reduce the energy consumption and the muscle fatigue. Each hip joint of the PGO is flexed by an air muscle operated by pressurized air enabling the patient to walk. In this study, we compared gait characteristic of powered gait orthosis in parallel bar and walker about 3 paraplegic patients. As results, hip jont and pelvic angle is similar angle about RGO and PGO in parallel bar gait and walker gait. But gait speed and gait cycle parameter is decrease more than RGO gait. It will can improve by gait training about balance and speed.