Application US20200282223

MEETING BRAIN-COMPUTER INTERFACE USER PERFORMANCE EXPECTATIONS USING A DEEP NEURAL NETWORK DECODING FRAMEWORK
[+] Show Details

US20200282223

1. A brain-computer interface (BCI) comprising: (7) (3)

a multichannel stimulator operatively connected to deliver stimulation pulses to a functional electrical stimulation (FES) device to control delivery of FES to an anatomical region; and

a decoder operatively connected to receive at least one neural signal from at least one electrode operatively connected with a motor cortex and to control the multichannel stimulator based on the received at least one neural signal;

wherein the decoder comprises a computer programmed to process the received at least one neural signal using a deep neural network.

2. The BCI of claim 1 wherein the deep neural network includes a long short-term memory (LSTM) layer in which hidden units in the LSTM layer use a hard-sigmoid activation function and an output of the LSTM layer uses a hyperbolic tangent activation. (0)

3. The BCI of claim 1 wherein the deep neural network includes a one-dimensional convolutional layer. (2) (0)

6. The BCI of claim 1 wherein the deep neural network includes at least one fully connected neural network layer. (2) (0)

10. The BCI of claim 1 wherein the deep neural network comprises a long short-term memory (LSTM) layer outputting to a convolutional layer in turn outputting to at least one fully connected neural network layer. (6) (0)

11. The BCI of claim 10 wherein hidden units in the LSTM layer use a hard-sigmoid activation function and an output of the LSTM layer uses a hyperbolic tangent activation. (0)

12. The BCI of claim 10 wherein the convolutional layer is a one-dimensional convolutional layer. (0)

13. The BCI of claim 10 wherein the convolutional layer performs convolution in the time domain only. (0)

14. The BCI of claim 10 wherein an activation function for an output of the convolutional layer is a leaky-rectified linear unit (0)

15. The BCI of claim 10 wherein the at least one fully connected neural network layer includes a fully connected neural network layer that uses a rectified linear unit activation function. (0)

16. The BCI of claim 10 wherein the deep neural network further includes an output neural network layer wherein the fully connected neural network layer outputs to the output neural network layer and the output neural network layer has units corresponding to a set of possible intended movements plus rest. (1) (0)

18. The BCI of claim 1 wherein the decoder comprises the computer programmed to process the received at least one neural signal using the at least one deep neural network and not using a Support Vector Machine (SVM). (1) (0)

20. The BCI of claim 1 wherein: (0) (2)

21. An assistance device for assisting a patient having a spinal cord injury to manipulate an anatomical region that is paralyzed due to the spinal cord injury, the assistance device comprising: (1) (3)

a BCI as set forth in claim 1; and

a functional electrical stimulation (FES) device disposed on the anatomical region and including electrodes configured to deliver FES to the anatomical region;

wherein the multichannel stimulator of the BCI is operatively connected to deliver stimulation pulses to the FES device to control delivery of FES to the anatomical region.

22. The assistance device of claim 21 further comprising: (0) (1)

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)

applying a decoder to at least one neural signal received from at least one electrode operatively connected with a motor cortex of the patient to generate a predicted movement of the anatomical region, wherein the decoder comprises a computer programmed to process the at least one neural signal using a deep neural network to generate the predicted movement of the anatomical region; and

performing functional electrical stimulation (FES) to cause the predicted movement of the anatomical region using a multichannel stimulator that is operatively connected to deliver stimulation pulses to a functional electrical stimulation (FES) device operatively connected to the anatomical region.

24. The assistance method of claim 23 wherein the deep neural network comprises a long short-term memory (LSTM) layer outputting to a convolutional layer in turn outputting to at least one fully connected neural network layer. (1) (0)

26. The assistance method of claim 23 wherein the deep neural network includes an output neural network layer having units corresponding to a set of possible intended movements plus rest, and the assistance method further comprises: (0) (2)

27. The assistance method of claim 23 wherein the decoder comprises the computer programmed to process the received at least one neural signal using the at least one deep neural network and not using a Support Vector Machine (SVM). (0)

28. The assistance method of claim 23 further comprising: (0) (1)

29. An assistance system comprising: (4) (2)

a brain-computer interface (BCI) comprising a computer operatively connected to receive at least one neural signal from a patient and programmed to apply a decoder to the at least one neural signal to generate a predicted movement, wherein the decoder comprises a deep neural network; and

an assistive device, the BCI operatively connected to control the assistive device to perform the predictive movement.

30. The assistance system of claim 29 wherein the assistive device comprises a functional electrical stimulation (FES) device, a robotic arm, a computer cursor, or a communication device. (0)

31. The assistance system of claim 29 wherein the deep neural network comprises a long short-term memory (LSTM) layer outputting to a convolutional layer in turn outputting to at least one fully connected neural network layer. (1) (0)

33. The assistance system of claim 29 wherein the deep neural network includes an output neural network layer having units corresponding to a set of possible intended movements plus rest, and the computer is further programmed to: (0) (2)

34. The assistance system of claim 29 wherein the computer is further programmed to perform unsupervised updating of the decoder using the at least one neural signal labeled with the predicted movement generated by applying the decoder to the at least one neural signal. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20200282223

MEETING BRAIN-COMPUTER INTERFACE USER PERFORMANCE EXPECTATIONS USING A DEEP NEURAL NETWORK DECODING FRAMEWORK

Patent Matrix® Search