Learning an EMG Controlled Game: Task-Specific Adaptations and Transfer

Dijk, Ludger van; Sluis, Corry K. van der; Dijk, Hylke W. van; Bongers, Raoul M.

doi:10.1371/journal.pone.0160817

Cited by 52 publications

(43 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The surface electromyogram signal [ 1 ] records muscle’s information by putting non-invasive surface sEMG electrodes on the skin. The electrical activity recorded by sEMG electrodes allows us to develop human-computer interface (HCI) system which has been employed in four major areas [ 2 ]: (1) Assistive technology (e.g., myoelectric controlled prosthesis [ 3 ], wheelchair [ 4 ] and assistive robots [ 5 ]), (2) Rehabilitative technology (e.g., sEMG-driven Exoskeletons [ 6 ] and serious games [ 7 , 8 ]), (3) Input technology (e.g., armbands and MCI [ 9 ]), and (4) Silent speech recognition [ 10 ]. Among these applications, sEMG-based hand gesture recognition plays an important and fundamental role for computers or assistive devices to understand human body language.…”

Section: Introductionmentioning

confidence: 99%

A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition

et al. 2018

View full text Add to dashboard Cite

The surface electromyography (sEMG)-based gesture recognition with deep learning approach plays an increasingly important role in human-computer interaction. Existing deep learning architectures are mainly based on Convolutional Neural Network (CNN) architecture which captures spatial information of electromyogram signal. Motivated by the sequential nature of electromyogram signal, we propose an attention-based hybrid CNN and RNN (CNN-RNN) architecture to better capture temporal properties of electromyogram signal for gesture recognition problem. Moreover, we present a new sEMG image representation method based on a traditional feature vector which enables deep learning architectures to extract implicit correlations between different channels for sparse multi-channel electromyogram signal. Extensive experiments on five sEMG benchmark databases show that the proposed method outperforms all reported state-of-the-art methods on both sparse multi-channel and high-density sEMG databases. To compare with the existing works, we set the window length to 200ms for NinaProDB1 and NinaProDB2, and 150ms for BioPatRec sub-database, CapgMyo sub-database, and csl-hdemg databases. The recognition accuracies of the aforementioned benchmark databases are 87.0%, 82.2%, 94.1%, 99.7% and 94.5%, which are 9.2%, 3.5%, 1.2%, 0.2% and 5.2% higher than the state-of-the-art performance, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Since EMG is an important source of neural information, it has been extensively studied in the field of human-machine interfacing [ 2 , 3 ]. Applications of EMG include the control of neurorehabilitation devices such as prostheses [ 4 , 5 ], rehabilitation robots [ 6 , 7 ], and identification of muscle anatomical structure [ 8 ], but also implementations in leisure activities such as sports [ 9 ] and computer games [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Spatial Feature for the Identification of Motor Tasks Using High-Density Electromyography

Jordanic

Rojas-Martínez

Mañanas

et al. 2017

Sensors

View full text Add to dashboard Cite

Estimation of neuromuscular intention using electromyography (EMG) and pattern recognition is still an open problem. One of the reasons is that the pattern-recognition approach is greatly influenced by temporal changes in electromyograms caused by the variations in the conductivity of the skin and/or electrodes, or physiological changes such as muscle fatigue. This paper proposes novel features for task identification extracted from the high-density electromyographic signal (HD-EMG) by applying the mean shift channel selection algorithm evaluated using a simple and fast classifier-linear discriminant analysis. HD-EMG was recorded from eight subjects during four upper-limb isometric motor tasks (flexion/extension, supination/pronation of the forearm) at three different levels of effort. Task and effort level identification showed very high classification rates in all cases. This new feature performed remarkably well particularly in the identification at very low effort levels. This could be a step towards the natural control in everyday applications where a subject could use low levels of effort to achieve motor tasks. Furthermore, it ensures reliable identification even in the presence of myoelectric fatigue and showed robustness to temporal changes in EMG, which could make it suitable in long-term applications.

show abstract

“…There is recent research that analyses myoelectric games to facilitate the transfer to a robotic prosthesis [16,18]. However, we were not able to find the literature where myoelectric games are tested with a homogeneous group of patients with SCI with no limb amputation.…”

Section: Resultsmentioning

confidence: 83%

“…There are interactive analyses with myoelectric prostheses in healthy subjects [16]. However, care must be taken with the patients with SCI or even with children, as muscle capabilities are reduced and the prosthesis can be harmful when it is not properly commanded.…”

Section: Discussionmentioning

confidence: 99%

Myoelectric Gaming in the Rehabilitation of Patients with C7 Spinal Cord Injury

et al. 2019

View full text Add to dashboard Cite

This paper analyses the role of myoelectric games in the rehabilitation of paraplegic patients. The University of Valladolid neuromuscular training system, UVa-NTS platform, which allows the myoelectric command of computer applications, has been introduced in rehabilitation sessions of a group of paraplegic patients. The experiments took place both at the University of Valladolid and at the National Hospital for Paraplegics of Toledo in Spain. A homogeneous population of five patients with a C7 spinal cord injury was compared with a group of control subjects. The myoelectric control was performed with the flexor carpi radialis and the extensor carpi radialis muscles. The myoelectric routines were timed and the game scores measured. Notwithstanding the reduced mobility of the patients, they achieved fast adaptation and better timings than the control subjects in the first experiment (p < 0.001), although this difference was reduced in further experiments. Both patients and control subjects played satisfactorily with the Myo-Pong game. However, the improvement in the scores was better for the control subjects between sessions (p = 0.009) when compared with the patients (p = 0.978). The results show that patients and control subjects were able to perform and reached similar scores. However, patients’ improvement in further rehabilitation sessions was lesser than when compared with the control subjects.

show abstract

Learning an EMG Controlled Game: Task-Specific Adaptations and Transfer

Cited by 52 publications

References 27 publications

A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition

A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition

A Novel Spatial Feature for the Identification of Motor Tasks Using High-Density Electromyography

Myoelectric Gaming in the Rehabilitation of Patients with C7 Spinal Cord Injury

Contact Info

Product

Resources

About