Neural Networks for Online Classification of Hand and Finger Movements Using Surface EMG signals

Tsenov, Georgi; Zeghbib, Abdelhafid; Палис, Ф.; Shoylev, N.; Mladenov, Valeri

doi:10.1109/neurel.2006.341203

Cited by 92 publications

(41 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This has allowed increased movement patterns to be classified beyond just grip, to include wrist flexion and extension, forearm pronation and supination [29,30], humeral rotation [31] and ulnar and radial deviation at the wrist [32], with the current trend moving towards identifying muscle patterns to control individual fingers [33][34][35][36]. However, it is important to note that pattern recognition is only capable of classifying these movements in sequence and not simultaneously (Fig.…”

Section: Pattern Recognition Controlmentioning

confidence: 99%

Prosthetic Myoelectric Control Strategies: A Clinical Perspective

et al. 2014

View full text Add to dashboard Cite

Control algorithms for upper limb myoelectric prostheses have been in development since the mid-1940s. Despite advances in computing power and in the performance of these algorithms, clinically available prostheses are still based on the earliest control strategies. The aim of this review paper is to detail the development, advantages and disadvantages of prosthetic control systems and to highlight areas that are current barriers for the transition from laboratory to clinical practice. Current surgical strategies and future research directions to achieve multifunctional control will also be discussed. The findings from this review suggest that regression algorithms may offer an alternative feed-forward approach to direct and pattern recognition control, while virtual rehabilitation environments and tactile feedback could improve the overall prosthetic control.

show abstract

Section: Pattern Recognition Controlmentioning

confidence: 99%

Prosthetic Myoelectric Control Strategies: A Clinical Perspective

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Some of the previous studies [15], [19]- [21] present that it is beneficial to use EMG signals of multiple channels. However, though the use of increased numbers of channels will increase the average classification accuracy, a reduced efficiency may be observed for the numbers of channels greater than four [17]. On the other hand, some researchers are interested in considering the best and significant features other than using multichannel EMG signals or a combination of these approaches [22].…”

Section: A Acquisition Of Emg Signalsmentioning

confidence: 99%

“…Additionally, the wavelet technique provides good frequency resolution at high frequencies. So the noise components in the desired signal can be isolated while important high-frequency transients are preserved [17]. The collected EMG signal for 4 different hand movements (left, right, up, down) are segmented of 500 data points for each type of motion.…”

Section: B Preprocessing and Feature Extractionmentioning

confidence: 99%

Design and Optimization of Levenberg-Marquardt based Neural Network Classifier for EMG Signals to Identify Hand Motions

Ibrahimy¹,

Ahsan²,

Khalifa³

2013

Measurement Science Review

View full text Add to dashboard Cite

“…The backpropagation rule propagates the errors through the network and allows adaptation of the hidden parameters. As one of the most common artificial neural networks (ANNs), the MLP has been widely used in pattern recognition models for sEMG signals [46]. A three-layer network consisting of one input layer, one hidden layers with a Sigmoid function, and one output layer with a Tanh function was used to set up the MLP classifier.…”

Section: Multilayer Perceptron (Mlp) Classifiermentioning

confidence: 99%

Recognition of sketching from surface electromyography

Chen

Zhong

Gong

et al. 2017

Neural Comput & Applic

View full text Add to dashboard Cite

The main objective of this study is to recognize sketching precisely and effectively in human computer interaction. A surface electromyography (sEMG) based sketching recognition method is proposed. We conducted an experiment in which we recorded the sEMG signals from the forearm muscles of two participants who were instructed to sketch seven basic one-stroke shapes. Subsequently, seven features of the sEMG time domain were extracted. After reducing data dimensionality using principal component analysis, these features were used as input vectors to a sketching recognition model based on Support Vector Machines (SVM). The performance of this model was compared to two other recognition models based on Multilayer perceptron (MLP) neural networks and Self Organization Feature Map (SOFM) neural networks. The average recognition rates for the seven basic one-stroke shapes of two participants achieved by the SVM-based and MLP-based models were both 98.5% in the test set, which were slightly superior to the performance of the SOFM classifier. Our results demonstrate the feasibility of converting forearm sEMG signals into sketching patterns.

show abstract

Neural Networks for Online Classification of Hand and Finger Movements Using Surface EMG signals

Cited by 92 publications

References 5 publications

Prosthetic Myoelectric Control Strategies: A Clinical Perspective

Prosthetic Myoelectric Control Strategies: A Clinical Perspective

Design and Optimization of Levenberg-Marquardt based Neural Network Classifier for EMG Signals to Identify Hand Motions

Recognition of sketching from surface electromyography

Contact Info

Product

Resources

About