Abstract
The classification accuracy in a myoelectric control system depends on choosing the optimal features that represent surface electromyographic (sEMG) signal, and selecting robust and fast classification algorithm. In this work, eight hand motions were classified using different extracted features from sEMG signals. The results of the experiment show that the classification rate of 97.41% was achieved using wavelet coefficients as feature vector and general regression neural network (GRNN) classifier. In addition, we found that the combination of sample entropy (SampEnt), root mean square (RMS), myopulse percentage rate (MYOP), and difference absolute standard deviation value (DASDV) achieved the highest classification rate of 95.68% using multilayer perceptron neural network (MLPNN) classifier.
Keywords: EMG signal processing, feature extraction , neural network, pattern recognition, prosthetic hand, wavelet analysis.
Recent Patents on Computer Science
Title:An Experimental Investigation of MLPNN and GRNN Classification Methods for Evaluation of Different sEMG-Extracted Features
Volume: 7 Issue: 1
Author(s): Firas A. Omari and Guohai Liu
Affiliation:
Keywords: EMG signal processing, feature extraction , neural network, pattern recognition, prosthetic hand, wavelet analysis.
Abstract: The classification accuracy in a myoelectric control system depends on choosing the optimal features that represent surface electromyographic (sEMG) signal, and selecting robust and fast classification algorithm. In this work, eight hand motions were classified using different extracted features from sEMG signals. The results of the experiment show that the classification rate of 97.41% was achieved using wavelet coefficients as feature vector and general regression neural network (GRNN) classifier. In addition, we found that the combination of sample entropy (SampEnt), root mean square (RMS), myopulse percentage rate (MYOP), and difference absolute standard deviation value (DASDV) achieved the highest classification rate of 95.68% using multilayer perceptron neural network (MLPNN) classifier.
Export Options
About this article
Cite this article as:
Omari A. Firas and Liu Guohai, An Experimental Investigation of MLPNN and GRNN Classification Methods for Evaluation of Different sEMG-Extracted Features, Recent Patents on Computer Science 2014; 7 (1) . https://dx.doi.org/10.2174/2213275907666140813194426
DOI https://dx.doi.org/10.2174/2213275907666140813194426 |
Print ISSN 2213-2759 |
Publisher Name Bentham Science Publisher |
Online ISSN 1874-4796 |
Related Articles
-
Cell-based Treatment of Cerebral Palsy: Still a Long Way Ahead
Current Stem Cell Research & Therapy Prevalence of Analgesic Use and Pain in People with and without Dementia or Cognitive Impairment in Aged Care Facilities: A Systematic Review and Meta-Analysis
Current Clinical Pharmacology Recent Advances in Physical Delivery Enhancement of Topical Drugs
Current Pharmaceutical Design Supplements, Diets and Other Complementary and Alternative Interventions in Adolescent Mental Health
Adolescent Psychiatry Medicinal Chemistry of 2,2,4-Substituted Morpholines
Current Medicinal Chemistry Water and Ion Channels: Crucial in the Initiation and Progression of Apoptosis in Central Nervous System?
Current Neuropharmacology Drug-Induced Liver Injury: Mechanisms, Types and Biomarkers
Current Medicinal Chemistry Excitotoxic Mechanisms in Non-Motor Dysfunctions and Levodopa- Induced Dyskinesia in Parkinson's Disease: The Role of the Interaction Between the Dopaminergic and the Kynurenine System
Current Medicinal Chemistry Translational Methods for Non-Invasive Electrical Stimulation to Facilitate Gait Rehabilitation Following Stroke - The Future Directions
Neuroscience and Biomedical Engineering (Discontinued) New Perspectives in HCV Therapy: Entry Inhibitors
Recent Patents on Anti-Infective Drug Discovery Recent Advances in Delivery Through the Blood-Brain Barrier
Current Topics in Medicinal Chemistry Clinical Importance of Assessment of Type 2 Diabetes Mellitus with Visceral Obesity. A Japanese Perspective
Current Diabetes Reviews Metabolism of HDL and its Regulation
Current Medicinal Chemistry Molecular Manipulation of G Protein coupled Receptors A New Avenue into Drug Discovery
Current Medicinal Chemistry Pelvic Floor Ultrasound
Current Medical Imaging Oxidative Stress in Schizophrenia
Current Neuropharmacology 1950 MHz Electromagnetic Fields Ameliorate Aβ Pathology in Alzheimer’s Disease Mice
Current Alzheimer Research Effective Inhibition of Foam Cells Formation by Tanshinone IIA in RAW264.7 Macrophages Induced with LDL Isolated from Hypercholesterolemia Patients: A Proteomic Analysis
Current Proteomics Design of Broad-Spectrum Inhibitors of Influenza A Virus M2 Proton Channels: A Molecular Modeling Approach
Current Computer-Aided Drug Design Modulation of Hepatic MRP3/ABCC3 by Xenobiotics and Pathophysiological Conditions: Role in Drug Pharmacokinetics
Current Medicinal Chemistry