Stepping-stones to Transhumanism: An EMG-controlled Low-cost Prosthetic Hand for Academia

Tatarian, Karen; Couceiro, Micael S.; Ribeiro, Eduardo Parente; Faria, Diego R.

doi:10.1109/is.2018.8710489

Cited by 11 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have noted that gesture classification with Myo has real-world application and benefits (Kaur et al 2016), showing that physiotherapy patients often exhibit much higher levels of satisfaction when interfacing via EMG and receiving digital feedback (Sathiyanarayanan and Rajan 2016). Likewise in the medical field, Myo has shown to be competitively effective with far more expensive methods of non-invasive electromyography in the rehabilitation of amputation patients (Abduo and Galster 2015), and following this, much work has explored the application of gesture classification for the control of a robotic hand (Ganiev et al 2016;Tatarian et al 2018). Since the armband is worn on the lower arm, the goal of the robotic hand is to be teleoperated by non-amputees and likewise to be operated by amputation patients in place of the amputated hand.…”

Section: Emg Gesture Classification and Calibrationmentioning

confidence: 99%

Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning

Kobylarz

Bird

Faria

et al. 2020

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

In this study, we present a transfer learning method for gesture classification via an inductive and supervised transductive approach with an electromyographic dataset gathered via the Myo armband. A ternary gesture classification problem is presented by states of 'thumbs up', 'thumbs down', and 'relax' in order to communicate in the affirmative or negative in a non-verbal fashion to a machine. Of the nine statistical learning paradigms benchmarked over 10-fold cross validation (with three methods of feature selection), an ensemble of Random Forest and Support Vector Machine through voting achieves the best score of 91.74% with a rule-based feature selection method. When new subjects are considered, this machine learning approach fails to generalise new data, and thus the processes of Inductive and Supervised Transductive Transfer Learning are introduced with a short calibration exercise (15 s). Failure of generalisation shows that 5 s of data per-class is the strongest for classification (versus one through seven seconds) with only an accuracy of 55%, but when a short 5 s per class calibration task is introduced via the suggested transfer method, a Random Forest can then classify unseen data from the calibrated subject at an accuracy of around 97%, outperforming the 83% accuracy boasted by the proprietary Myo system. Finally, a preliminary application is presented through social interaction with a humanoid Pepper robot, where the use of our approach and a most-common-class metaclassifier achieves 100% accuracy for all trials of a '20 Questions' game.

show abstract

Section: Emg Gesture Classification and Calibrationmentioning

confidence: 99%

Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning

Kobylarz

Bird

Faria

et al. 2020

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…By measuring and collecting the data of the electrical impulses with one of these commercial devices and combining it with state-of-the-art machine learning algorithms e.g. neural networks, and robust feature selection, the sampling rate drawback can be mitigated against and a high level of accuracy can still be achieved [16], [19]- [22].…”

Section: Related Workmentioning

confidence: 99%

“…Research using the Myo armband has shown how neural networks have been applied to sEMG signal classification i.e. convolutional neural networks (CNN) and Long Short Term Memory (LSTM) networks [8], [19], [23].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor

Millar

Siddique

Kerr

2020

2020 International Symposium on Community-Centric Systems (CcS)

View full text Add to dashboard Cite

The electrical activity of the muscles that control finger movements can be extracted during the performance of these movements and using machine learning techniques, the myoelectric signals can be decoded and classified according to the movement that generated the specific signal. The focus of this paper is to classify sEMG signal using easily accessible cheap hardware to capture the signal. Furthermore, to employ neural networks to classify the signal using established methodology i.e. feature extraction, with the highest possible accuracy. To classify these sEMG signals, an LSTM network has been developed and was able to classify 12 individual finger movements with accuracies reaching 90%.

show abstract

“…With better classification results come higher impact applications. In the domain of Human-Robot Interaction, the control of prosthetic devices [7]- [9], enabling telepresence within settings such as care assistance [10], [11], as well as within hazardous settings such as bomb disposal [12], and remote environments [13], as well as risk of potential injury [14]- [16] are just a few of many possible fields that successful knowledge transfer could potentially advance, through both improved classification ability and lower computational expense required to train models.…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain MLP and CNN Transfer Learning for Biological Signal Processing: EEG and EMG

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this work, we show the success of unsupervised transfer learning between Electroencephalographic (brainwave) classification and Electromyographic (muscular wave) domains with both MLP and CNN methods. To achieve this, signals are measured from both the brain and forearm muscles and EMG data is gathered from a 4-class gesture classification experiment via the Myo Armband, and a 3-class mental state EEG dataset is acquired via the Muse EEG Headband. A hyperheuristic multi-objective evolutionary search method is used to find the best network hyperparameters. We then use this optimised topology of deep neural network to classify both EMG and EEG signals, attaining results of 84.76% and 62.37% accuracy, respectively. Next, when pre-trained weights from the EMG classification model are used for initial distribution rather than random weight initialisation for EEG classification, 93.82%(+29.95) accuracy is reached. When EEG pre-trained weights are used for initial weight distribution for EMG, 85.12% (+0.36) accuracy is achieved. When the EMG network attempts to classify EEG, it outperforms the EEG network even without any training (+30.25% to 82.39% at epoch 0), and similarly the EEG network attempting to classify EMG data outperforms the EMG network (+2.38% at epoch 0). All transfer networks achieve higher pre-training abilities, curves, and asymptotes, indicating that knowledge transfer is possible between the two signal domains. In a second experiment with CNN transfer learning, the same datasets are projected as 2D images and the same learning process is carried out. In the CNN experiment, EMG to EEG transfer learning is found to be successful but not vice-versa, although EEG to EMG transfer learning did exhibit a higher starting classification accuracy. The significance of this work is due to the successful transfer of ability between models trained on two different biological signal domains, reducing the need for building more computationally complex models in future research.

show abstract

Stepping-stones to Transhumanism: An EMG-controlled Low-cost Prosthetic Hand for Academia

Cited by 11 publications

References 16 publications

Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning

Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning

LSTM Classification of sEMG Signals For Individual Finger Movements Using Low Cost Wearable Sensor

Cross-Domain MLP and CNN Transfer Learning for Biological Signal Processing: EEG and EMG

Contact Info

Product

Resources

About