Neural prosthesis with fuzzy logic control system
A neural prosthesis for providing a signal indicative of a predicted event from a cycle of events includes a signal-acquisition system for receiving a neural signal, and a fuzzy-logic inference system for receiving, from the signal acquisition system, a signal indicative of a current location within the cycle of events. The fuzzy-logic inference system is configured to predict a successive event in the cycle of events.
1. A neural prosthesis for providing a signal indicative of a predicted event from a cycle of events, the neural prosthesis comprising:
a signal-acquisition system for receiving a neural signal;
a first fuzzy-logic inference system for receiving, from the signal acquisition system, a signal indicative of a current location within the cycle of events, the fuzzy-logic inference system being configured to predict a successive event in the cycle of events;
a supervisory controller for receiving an output of the fuzzy-logic inference system, the supervisory controller including
a memory for storing data indicative of at least one preceding predicted event in the cycle of events, and
a comparator to impose constraints on the successive event at least in part on the basis of the preceding predicted event; and
a second fuzzy-logic inference system configured to provide, at least in part on the basis of an output received from the comparator, a signal indicative of a predicted event.
2. The neural prosthesis of claim 1 , wherein the comparator is configured to implement a rule requiring that the successive event be selected in a manner consistent with an order of events in the cycle.
3. The neural prosthesis of claim 1 , wherein the comparator is configured to implement a rule requiring that the successive event be consistent with a preceding event of the cycle.
4. The neural prosthesis of claim 1 , further comprising a stimulus delivery system in communication with the second fuzzy-logic inference system, the stimulus delivery system configured to generate a stimulating signal at least in part on the basis of a signal indicative of a predicted event.
5. The neural prosthesis of claim 1 , wherein the signal-acquisition system comprises electrodes for receiving an electro-myographic signal.
6. The neural prosthesis of claim 5 , wherein the electrodes comprise surface mounted electrodes.
7. The neural prosthesis of claim 5 , wherein the electrodes comprise implantable electrodes.
8. The neural prosthesis of claim 1 , wherein the first fuzzy inference system comprises a Sugeno type system.
9. The neural prosthesis of claim 1 , wherein the second fuzzy logic inference system comprises a Sugeno type system.
10. The neural prosthesis of claim 1 , wherein the first fuzzy inference system comprises an adaptive neuro-fuzzy inference system.
11. A neural prosthesis for providing a signal predicting a successive gait event, the neural prosthesis comprising:
a signal-acquisition system for receiving a neural signal;
a first fuzzy-logic inference system for receiving a signal from the signal acquisition system, the first fuzzy-logic inference system being configured to predict a candidate successive event at least in part on the basis of the signal;
a supervisory controller for receiving data indicative of the candidate successive event from the first fuzzy-logic inference system, the supervisory controller comprising
a memory for storing data indicative of a preceding predicted gait event provided by the first fuzzy-logic inference system; and
a comparator to impose constraints on a successive gait event at least in part on the basis of the preceding predicted gait event;
a stimulus delivery system in communication with the supervisory controller, the stimulus delivery system being configured to generate a stimulating signal at least in part on the basis of the signal indicative of the predicted event; and
a second fuzzy-logic inference system configured to provide, at least in part on the basis of an output received from the comparator, a signal indicative of a predicted event.
12. The neural prosthesis of claim 11 , wherein the first fuzzy-logic inference system comprises an adaptive neuro-fuzzy inference system.
13. In a neural prosthesis, a method for providing a signal indicative of a predicted event from a cycle of events, the method comprising:
receiving a neural signal indicative of a current location within the cycle of events;
applying a fuzzy-logic inference algorithm to the neural signal;
storing data indicative of at least one preceding predicted event in the cycle of events;
identifying a constraint on the basis of the preceding predicted event;
imposing the constraint on the successive event;
receiving an output indicative of the successive event following imposition of the constraint thereon; and
applying an additional fuzzy-logic algorithm to provide a signal indicative of a predicted event.
14. The method of claim 13 , further comprising predicting a successive event in the cycle of events on the basis of an output of the fuzzy-logic inference algorithm.
15. The method of claim 13 , wherein identifying a constraint comprises requiring that the successive event be selected in a manner consistent with an order of events in the cycle.
16. The method of claim 13 , wherein identifying a constraint comprises requiring that the successive event be consistent with a preceding event of the cycle.
17. The method of claim 13 , further comprising generating a stimulus signal at least in part on the basis of a signal indicative of a predicted event.
18. The method of claim 13 , wherein receiving a neural signal comprises receiving an electro-myographic signal.
19. The method of claim 13 , wherein applying a fuzzy inference algorithm comprises applying a Sugeno type algorithm.
20. The method of claim 13 , wherein applying a fuzzy inference algorithm comprises applying an adaptive neuro-fuzzy inference algorithm.