scholarly journals Causes of Performance Degradation in Non-invasive Electromyographic Pattern Recognition in Upper Limb Prostheses

2018 ◽  
Vol 12 ◽  
Author(s):  
Iris Kyranou ◽  
Sethu Vijayakumar ◽  
Mustafa Suphi Erden
Keyword(s):  
Pattern Recognition ◽  
Upper Limb ◽  
Performance Degradation ◽  
Non Invasive ◽  
Upper Limb Prostheses

A review of invasive and non-invasive sensory feedback in upper limb prostheses

2017 ◽  
Vol 14 (6) ◽  
pp. 439-447 ◽  
Author(s):  
Pamela Svensson ◽  
Ulrika Wijk ◽  
Anders Björkman ◽  
Christian Antfolk
Keyword(s):  
Upper Limb ◽  
Sensory Feedback ◽  
Non Invasive ◽  
Upper Limb Prostheses

scholarly journals Users’ and therapists’ perceptions of myoelectric multi-function upper limb prostheses with conventional and pattern recognition control

PLoS ONE ◽  
2019 ◽  
Vol 14 (8) ◽  
pp. e0220899 ◽  
Author(s):  
Andreas W. Franzke ◽  
Morten B. Kristoffersen ◽  
Raoul M. Bongers ◽  
Alessio Murgia ◽  
Barbara Pobatschnig ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Upper Limb ◽  
Upper Limb Prostheses

scholarly journals Sensory Feedback in Upper Limb Prostheses

2020 ◽  
Vol 74 (5) ◽  
pp. 308-317
Author(s):  
Dace Dimante ◽  
Ināra Logina ◽  
Marco Sinisi ◽  
Angelika Krūmiņa
Keyword(s):  
Upper Limb ◽  
Visual Cues ◽  
Sensory Feedback ◽  
Movement Control ◽  
Major Step ◽  
Robotic Arms ◽  
Socioeconomic Groups ◽  
Myoelectric Prostheses ◽  
Non Invasive ◽  
Upper Limb Prostheses

Abstract Loss of an arm is a devastating condition that can cross all socioeconomic groups. A major step forward in rehabilitation of amputees has been the development of myoelectric prostheses. Current robotic arms allow voluntary movements by using residual muscle contraction. However, a significant issue is lack of movement control and sensory feedback. These factors play an important role in integration and embodiment of a robotic arm. Without feedback, users rely on visual cues and experience overwhelming cognitive demand that results in poorer use of a prosthesis. The complexity of the afferent system presents a great challenge of creating a closed-loop hand prosthesis. Several groups have shown progress providing sensory feedback for upper limb amputees using robotic arms. Feedback, although still limited, is achieved through direct implantation of intraneural electrodes as well as through non-invasive methods. Moreover, evidence shows that over time some amputees develop a phantom sensation of the missing limb on their stump. This phenomenon can occur spontaneously as well as after non-invasive nerve stimulation, suggesting the possibility of recreating a sensory homunculus of the hand on the stump. Furthermore, virtual reality simulation in combination with mechanical stimulation of skin could augment the sensation phenomenon, leading to better interface between human and robotic arms.

scholarly journals Adaptive Windowing Framework for Surface Electromyogram-Based Pattern Recognition System for Transradial Amputees

Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2402 ◽  
Author(s):  
Ali Al-Timemy ◽  
Guido Bugmann ◽  
Javier Escudero
Keyword(s):  
Pattern Recognition ◽  
Upper Limb ◽  
Time Domain ◽  
Window Size ◽  
Error Rates ◽  
Classification Error ◽  
Linear Discriminant ◽  
Emg Signal ◽  
Upper Limb Prosthesis ◽  
Upper Limb Prostheses

Electromyogram (EMG)-based Pattern Recognition (PR) systems for upper-limb prosthesis control provide promising ways to enable an intuitive control of the prostheses with multiple degrees of freedom and fast reaction times. However, the lack of robustness of the PR systems may limit their usability. In this paper, a novel adaptive time windowing framework is proposed to enhance the performance of the PR systems by focusing on their windowing and classification steps. The proposed framework estimates the output probabilities of each class and outputs a movement only if a decision with a probability above a certain threshold is achieved. Otherwise (i.e., all probability values are below the threshold), the window size of the EMG signal increases. We demonstrate our framework utilizing EMG datasets collected from nine transradial amputees who performed nine movement classes with Time Domain Power Spectral Descriptors (TD-PSD), Wavelet and Time Domain (TD) feature extraction (FE) methods and a Linear Discriminant Analysis (LDA) classifier. Nonetheless, the concept can be applied to other types of features and classifiers. In addition, the proposed framework is validated with different movement and EMG channel combinations. The results indicate that the proposed framework works well with different FE methods and movement/channel combinations with classification error rates of approximately 13% with TD-PSD FE. Thus, we expect our proposed framework to be a straightforward, yet important, step towards the improvement of the control methods for upper-limb prostheses.

Sign in / Sign up

Export Citation Format

Share Document