Paper Info
Title
Classification of Elbow Electormyography Signals based on Directed Transfer Functions
Abstract
A new approach for classification of electromyography (EMG) of the flexion and extension signals is introduced here. Multivariate Autoregressive (MVAR) model has been applied to a two-channel set of EMG signals from the biceps and triceps muscles during flexion and extension positions of the elbow. The MVAR coefficients are then used to define the Directed Transfer Function (DTF), which estimates the strength of the direction of the signals flow between the channels. The maximum strength of the DTF was used as the frequency domain features (training data) for EMG classification via support vector machine (SVM) algorithm. As the features obtained from the experiment uniquely describe the flexion and extension, the classifier becomes linear which lead to low level of misclassification. The overall method described here has a potential to detect and classify the type and level of muscular disorder from the way the muscle signals interact with each other.
Year
DOI
Venue
2008
10.1109/BMEI.2008.135
BMEI (2)
Keywords
Field
DocType
maximum strength,low level,extension signal,signals flow,mvar coefficient,emg signal,multivariate autoregressive,elbow electormyography,emg classification,directed transfer functions,directed transfer function,extension position,signal processing,transfer functions,svm,frequency domain,frequency domain analysis,support vector machine,support vector machines,biomedical engineering
Frequency domain,Signal processing,Autoregressive model,Biceps,Pattern recognition,Computer science,Support vector machine,Electromyography,Transfer function,Artificial intelligence,Classifier (linguistics)
Conference
ISSN
Citations 
PageRank 
1948-2914
2
0.65
References 
Authors
3
3
Name
Order
Citations
PageRank
Rhonira Latif161.49
Saeid Sanei253072.63
Kianoush Nazarpour37519.08