Adaptive artificial limbs: a real-time approach to prediction and anticipation

Pilarski, Patrick M.; Dawson, Michael R.; Degris, Thomas; Carey, Jason P.; Chan, K. Ming; Hebert, Jacqueline S.; Sutton, Richard S.

doi:10.1109/mra.2012.2229948

Cited by 56 publications

(51 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear kernel function gave better accuracy than other kernels. [1] Three different SVM classifier was implemented according to different feature sets extracted from HD-sEMG data  Classifier-based on H features.  Classifier-based on the combined average intensity and H features denoted as (AIH).…”

Section: E Performance Of Classifiermentioning

confidence: 99%

“…These prostheses increase the abilities of amputees and other patients that suffer from physical damage or cognitive functions as a result of disease, injury, and aging. [1] Myoelectric control is divided into two categories: pattern recognition approach and the conventional system (Direct control). In the direct control, each pair of opposite muscle site controls one motion of the prostheses.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HD-sEMG Gestures Recognition by SVM Classifier for Controlling Prosthesis

Jaber¹,

Rashid²

2019

IJCCCE

View full text Add to dashboard Cite

Electromyography signals (EMG) are an important source to infer motion intention. It has been broadly applied in human-machine interfacing to control the neurorehabilitation devices such as prosthesis and rehabilitation robot. HD-sEMG is a muscle's activity recorded at the delimited area of the skin using 2D array electrode. This strategy permits the analysis of sEMG signals in both temporal and spatial domain. Recent studies display that the spatial distribution of HD-EMG maps improves the recognition of tasks. This work investigates the use of HD-EMG recording to control upper limb prosthesis. The classification of eight hand gestures of able-bodied subjects was developed. Three feature sets were presented in this work. HOG features, time domain features(TD) and the combination of HOG and average intensity features (AIH). Combination of features possibly improved the performance of the classifier. Results show that the combined of intensity features and HOG features achieved higher performance of classifier than other features (Acc=99.37%, P=98.375%, S=97.5%)

show abstract

Section: E Performance Of Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

HD-sEMG Gestures Recognition by SVM Classifier for Controlling Prosthesis

Jaber¹,

Rashid²

2019

IJCCCE

View full text Add to dashboard Cite

show abstract

“…By building up a relationship with a user that is based on learned sensorimotor knowledge i.e., expectations about how the user and their prosthesis will interact , a limb controller can potentially improve and adapt over time to enhance the user s control experience. 11,12 In real-time machine learning, machine intelligence is used to learn about and adapt to user-specific situations that may be challenging or even impossible for the users to overcome on their own. Using these learned details as a basis for modulating control, an amputee user can be presented with a clear and consistent interface that promotes rapid training and proficient use of the myoelectric prosthesis.…”

Section: New Opportunities Through Real-time Machine Learningmentioning

confidence: 99%

Novel Control Strategies for Arm Prostheses : A Partnership between Man and Machine

2015

View full text Add to dashboard Cite

“…Adaptive algorithms are used to regularly update the existing training data based on different adaptive strategies. There has been successful research papers on improving classification accuracy with adaptive techniques [13,14,20]. An example would be Sensinger et al [15], noted that unsupervised methods that rely on high confidence of classification could provide implementable degrees of accuracy, yet could suffer over-training over long periods of time.…”

Section: Introductionmentioning

confidence: 99%

Preliminary Results of EMG-Based Hand Gestures for Long Term Use

Boyd

Fang

2017

Intelligent Robotics and Applications

View full text Add to dashboard Cite

The application of pattern recognition techniques to Electromyography (EMG) signals has shown great potential for robust, natural, prostheses control. Despite promising development in EMG pattern recognition techniques, the non-stationary properties of these signals may render these techniques ineffective after a period of time, subsequently demanding frequent recalibration during long term use. Potentially one method to reduce the impact of non-stationary traits of EMG signals is through attempting to construct a training dataset that represents this gradual change in the signal. In this paper, we investigate the potential impact of data selection schemes for inter-day motion recognition, across a period of five days of high density data recording with an LDA classifier, and present our preliminary findings. This paper proves that training a classifier with data from several spaced points of a single day can improve its inter-day performance which subsequently supports the long term use of prosthesis. Therefore the work presented here may aid in furthering our understanding of the physiological changes in EMG signals and how they may be exploited to further improve the robustness of pattern recognition methods for long term use.

show abstract

Adaptive artificial limbs: a real-time approach to prediction and anticipation

Cited by 56 publications

References 18 publications

HD-sEMG Gestures Recognition by SVM Classifier for Controlling Prosthesis

HD-sEMG Gestures Recognition by SVM Classifier for Controlling Prosthesis

Novel Control Strategies for Arm Prostheses : A Partnership between Man and Machine

Preliminary Results of EMG-Based Hand Gestures for Long Term Use

Contact Info

Product

Resources

About