Abstract: |
A brain-computer interface (BCI) includes a multichannel stimulator and a decoder. The multichannel stimulator is operatively connected to deliver stimulation pulses to a functional electrical stimulation (FES) device to control delivery of FES to an anatomical region. The decoder is operatively connected to receive at least one neural signal from at least one electrode operatively connected with a motor cortex. The decoder controls the multichannel stimulator based on the received at least one neural signal. The decoder comprises a computer programmed to process the received at least one neural signal using a deep neural network. The decoder may include a long short-term memory (LSTM) layer outputting to a convolutional layer in turn outputting to at least one fully connected neural network layer. The decoder may be updated by unsupervised updating. The decoder may be extended to include additional functions by transfer learning. |
Inventor: |
Schwemmer, Michael A. (Columbus, OH, US); Friedenberg, David A. (Worthington, OH, US); Skomrock, Nicholas D. (Columbus, OH, US) |
Applicant: |
Battelle Memorial Institute (Columbus, OH, US) |
Face Assignee: |
N/A |
Filed: |
2020-03-06 |
Issued: |
2020-09-10 |
Claims: |
34 |
|
US20200282223
|
1. A brain-computer interface (BCI) comprising:
(7)
(3)
|
|
23. An assistance method for assisting a patient having a spinal cord injury to manipulate an anatomical region of the patient that is paralyzed due to the spinal cord injury, the assistance method comprising:
(4)
(2)
|
|
29. An assistance system comprising:
(4)
(2)
|
|