Limits...
Feasibility of using combined EMG and kinematic signals for prosthesis control: A simulation study using a virtual reality environment.

Blana D, Kyriacou T, Lambrecht JM, Chadwick EK - J Electromyogr Kinesiol (2015)

Bottom Line: Transhumeral amputation has a significant effect on a person's independence and quality of life.The offline training had a target of 4° for flexion/extension and 8° for pronation/supination, which it easily exceeded (2.7° and 5.5° respectively).During online testing, all subjects completed the target-reaching task with path efficiency of 78% and minimal overshoot (1.5%).

View Article: PubMed Central - PubMed

Affiliation: Institute for Science and Technology in Medicine, Keele University, UK. Electronic address: d.blana@keele.ac.uk.

No MeSH data available.


Related in: MedlinePlus

An example of the input (panels A, B and C) and output (panel D) ANN training data. Panel A shows the six processed EMG signals, panel B shows the angular velocity of the humerus IMU, and panel C shows the linear acceleration of the humerus IMU. Panel D shows the elbow flexion/extension and forearm pronation/supination calculated based on the IMU on the humerus and forearm.
© Copyright Policy - CC BY
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4940208&req=5

f0015: An example of the input (panels A, B and C) and output (panel D) ANN training data. Panel A shows the six processed EMG signals, panel B shows the angular velocity of the humerus IMU, and panel C shows the linear acceleration of the humerus IMU. Panel D shows the elbow flexion/extension and forearm pronation/supination calculated based on the IMU on the humerus and forearm.

Mentions: Fig. 3 shows an example of the data used to train the ANN. Panel A shows the rectified and filtered EMG data, and panels B and C show the humerus IMU velocity and acceleration data. These 12 signals were the inputs to the ANN, while the outputs were elbow flexion/extension and forearm pronation/supination, calculated from the IMU on the humerus and forearm, shown in panel D. For all participants, six neurons in the hidden layer were sufficient to achieve the required offline accuracy, as shown in Table 1. ANN training with such as small number of neurons was extremely fast (less than 1 min) so the overall training phase required less than 15 min for all participants.


Feasibility of using combined EMG and kinematic signals for prosthesis control: A simulation study using a virtual reality environment.

Blana D, Kyriacou T, Lambrecht JM, Chadwick EK - J Electromyogr Kinesiol (2015)

An example of the input (panels A, B and C) and output (panel D) ANN training data. Panel A shows the six processed EMG signals, panel B shows the angular velocity of the humerus IMU, and panel C shows the linear acceleration of the humerus IMU. Panel D shows the elbow flexion/extension and forearm pronation/supination calculated based on the IMU on the humerus and forearm.
© Copyright Policy - CC BY
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4940208&req=5

f0015: An example of the input (panels A, B and C) and output (panel D) ANN training data. Panel A shows the six processed EMG signals, panel B shows the angular velocity of the humerus IMU, and panel C shows the linear acceleration of the humerus IMU. Panel D shows the elbow flexion/extension and forearm pronation/supination calculated based on the IMU on the humerus and forearm.
Mentions: Fig. 3 shows an example of the data used to train the ANN. Panel A shows the rectified and filtered EMG data, and panels B and C show the humerus IMU velocity and acceleration data. These 12 signals were the inputs to the ANN, while the outputs were elbow flexion/extension and forearm pronation/supination, calculated from the IMU on the humerus and forearm, shown in panel D. For all participants, six neurons in the hidden layer were sufficient to achieve the required offline accuracy, as shown in Table 1. ANN training with such as small number of neurons was extremely fast (less than 1 min) so the overall training phase required less than 15 min for all participants.

Bottom Line: Transhumeral amputation has a significant effect on a person's independence and quality of life.The offline training had a target of 4° for flexion/extension and 8° for pronation/supination, which it easily exceeded (2.7° and 5.5° respectively).During online testing, all subjects completed the target-reaching task with path efficiency of 78% and minimal overshoot (1.5%).

View Article: PubMed Central - PubMed

Affiliation: Institute for Science and Technology in Medicine, Keele University, UK. Electronic address: d.blana@keele.ac.uk.

No MeSH data available.


Related in: MedlinePlus