Discrimination of Forearm's Motions by Surface EMG Signals using Neural Network
スポンサーリンク
概要
- 論文の詳細を見る
We tried to discriminate different forearms motions by surface EMG signals using neural network. In order to get a higher discrimination rate, the positions of electrodes were improved. We also tried to discriminate similar motions in order to clarify the limitation of the discrimination by surface EMG signals. Two experiments were carried out. One was to discriminate five different motions: grasp, wrist flexion, wrist extension, forearm pronation, and forearm supination (Experiment 1). The other was to discriminate four similar motions which have different quantitative definitions at grasp, wrist flexion/extension, or forearm pronatio/supination (Experiment 2). Four surface electrodes were placed on the skin above the main active muscles: short radial extensor m. of wrist, supinator m., long radial extensor m. of wrist, and ulnar flexor m. of wrist, considering anatomical functions of the forearms muscles. EMG signals were recorded during 2 sec while the subjects kept the motions. Recorded EMG signals were sampled at 200 msec intervals after full-wave rectifying and low-pass filtering. Therefore, the number of sampling data patterns of EMG signals was 10 for every motion. Three layers of neural network was used for discrimination. The number of units in the input layer is 4, and the number of units in the output layer is 5 or 4. In order to get the best discrimination rate of the motions, we changed the number of units in the hidden layer from 3 to 12. The neural network was trained by the back-propagation algorithm. In Experiment 1, the best average values of discrimination rates under three pattems of EMG signals for each subject were 96.0%, 98.0%, and 87.2% when the numbers of units in the hidden layer were 10, 11, and 3 respectively. In Experiment 2 using original EMG patterns, the best average values of discrimination rates at grasp, extension/flexion, and pronation/supination were 59.5%, 76.0%, and 25.0% respectively. By using normalized EMG patterns, these were 40.0%, 84.8%, and 55.5% respectively.
- 日本生理人類学会の論文
- 1996-11-01
著者
-
SAKAMOTO Kazuyoshi
Department of Industriam Management Engineerings, Faculty of Electro-Communications, The University
-
Itakura Naoaki
Department Of Communications And Systems The University Of Electro-communications
-
Itakura N
Department Of Communications And Systems Engineering The University Of Electro-communications
-
Itakura Naoaki
Department Of Communications And Systems Engineering University Of Electro-communications
-
Sakamoto Kazuyoshi
Department Of Communications And Systems Engineering The University Of Electro-communications
-
KINBARA Yoh
Department of Communications and Systems Engineering, The University of Electro-Communications
-
FUWA Teruhiko
Department of Communications and Systems Engineering, The University of Electro-Communications
-
Fuwa Teruhiko
Department Of Communications And Systems Engineering The University Of Electro-communications
-
Fuwa Teruhiko
Department Of Communications And Systems Engineering The University Of E!ectro-communications
-
Kinbara Yoh
Department Of Communications And Systems Engineering The University Of Electro-communications
関連論文
- 11 Influence of Hyperbaric Heliox Environment (31 ATA and He-0_2) on Microvibration and Electroencephalogram
- Influence of Hyperbaric Heliox Environment at 31ATA on Microvibration and Electroencephalogram in Four Divers
- Power Spectral Analysis of Intentional and Postural Tremor During a Simulated Heliox Dive to 31ATA
- Observation Study on Natural Walking in the Tokyo Metropolitan
- Relationship between physiological tremor and evoked EMG (H reflex) under drinking condition
- B-P11 The Study of Ki Energy using Breathing Method : The Flow and Reacting Patterns of Ki energy (Proceedings of the 40th Meeting of Japan Society of Physiological Anthropology)
- Discrimination of Forearm's Motions by Surface EMG Signals using Neural Network
- Estimation of Continuous Forearm's Motions by Surface EMG with Using Neural Network
- Chaos Analyses of Sleep EEG
- Effects of Muscle Length on Distribution of Muscle Fiber Conduction Velocity for M. Biceps Brachii
- A Visual Recognition of Moving Chinese Character
- 2-9 Quantification of Subjects' Breathing Method using the Index of Respiratory Regularity(Proceedings of the 56th Meeting of Japan Society of Physiological Anthropology)
- 2-3 Fundamental Investigation into Quantification of Respiratory Regularity(Proceedings of the 55th Meeting of Japan Society of Physiological Anthropology)
- Evaluation of Comfort for Color Light Based on Fuzzy Theory
- A Mathematical Model for Anisotropic Properties of Ventricular Muscle
- Effect of Muscle Length on Distribution of Muscle Fiber Conduction Velocity for M. Biceps Brachii
- The Influence of Location of Electrode on Muscle Fiber Conduction Velocity and EMG Power Spectrum during Voluntary Isometric Contraction Measured with Surface Array Electrodes
- Distribution of Muscle Fiber Conduction velocity of M. Biceps Brachii During Voluntary Isometric Contraction with Use of Surface Array Electrodes
- On the Visual Recognition of Moving Letter
- Characteristics of Physiological Tremor in Five Fingers and Evaluations of Fatigue of Fingers in Typing
- The examination of estimation method of Muscle Fiber Conduction Velocity using additional average method and cross-correlation thchnique.
- Eye movement in searching a character shown on a CRT-display
- The Influence of Drinking on Physiological Tremor and Reaction Time
- B-P4 An Estimation of Muscle Fiber Conduction Velocity Considering Maximum Cross Correlation Efficient Value Using Cross-Correlation Technique (Proceedings of the 40th Meeting of Japan Society of Physiological Anthropology)
- 1-8 Applicabilities of Transient Visual Evoked Potentials(Proceedings of the 57th Meeting of Japan Society of Physiological Anthropology)
- Histological skeletal muscle damage and surface EMG relationships following eccentric contractions
- A Study of Muscle Fiber Conduction Velocity in M. Masseter of Human
- B-P3 A Study of Muscle Fiber Conduction Velocity by Stationary Current Dipole Model (Proceedings of the 40th Meeting of Japan Society of Physiological Anthropology)
- Physiological Tremor under Pseudo-Fraction Gravity
- Monitoring Accumulative Fatigue of Finger by Autoregressive Modeling of Physiological Tremor
- Analysis of movement in sit-to-stand motion using parallel bars-one side support
- M-13 Realization of interactive eye-gaze-select interface (Proceedings of the 42nd Meeting of Japan Society of Physiological Anthropology)
- 20 A proposal of a method that judge an input-character on an eye gaze-select interface with a guide area (Proceedings of the 41st Meeting of Japan Society of Physiological Anthropology)
- II-2 Consideration of the calculation method of the fixation on a eye-gaze-select interface (Proceedings of the 40th Meeting of Japan Society of Physiological Anthropology)
- 2B-2-4 Analysis of non-input and input fixations for eye movements on a eye-gaze-select interface (Proceedings of the 39th Meeting of Japan Society of Physiological Anthropology)
- Effects of Weight Load on Physiological Tremor:The AR Representation
- On the distribution of muscle fiber conduction velocity (MFCV) with the use of surface EMG
- 1004 STUDY OF FUNCTION OF FINGERS BY PHYSIOLOGICAL TREMOR