Systems and methods for decoding intended symbols from neural activity
Systems and methods for decoding intended symbols from neural activity in accordance with embodiments of the invention are illustrated. One embodiment includes a symbol decoding system for brain-computer interfacing, including a neural signal recorder implanted into a brain of a user, and a symbol decoder, the symbol decoder including a processor, and a memory, where the memory includes a symbol decoding application capable of directing the processor to obtain neural signal data from the neural signal recorder, estimate a symbol from the neural signal data using a symbol model, and perform a command associated with the symbol.
1. A system for decoding symbols from neural activity, comprising:
a neural signal recorder implanted into a brain of a user; and
a symbol decoder, the symbol decoder comprising:
a processor; and
a memory, where the memory comprises a symbol decoding application capable of directing the processor to:
obtain neural signal data from the neural signal recorder;
temporally bin the neural signal data to create at least one neural population time series;
convert the at least one neural population time series into at least one time probability series; and
identify a most likely symbol intended by the user from the at least one time probability series after a time delay triggered by identification of a high probability of a new character in the at least one time probability series;
and
perform a command associated with the identified most likely symbol.
2. The system of claim 1 , wherein the neural signal recorder is a microelectrode array.
3. The system of claim 1 , wherein the symbol model is a neural network.
4. The system of claim 3 , wherein the symbol model is selected from the group consisting of: recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and temporal convolutional networks.
5. The system of claim 1 , wherein the symbol model is a hidden Markov model.
6. The system of claim 1 , wherein each bin is between 10 ms and 300 ms.
7. The system of claim 1 , wherein the memory further comprises a symbol database comprising:
a plurality of symbols; and
a plurality of commands;
wherein each symbol in the plurality of symbols is associated with a command.
8. The system of claim 7 , wherein the symbols in the symbol database are difference maximized.
9. The system of claim 7 , wherein commands in the plurality of commands are computer functions.
10. A method for decoding symbols from neural activity, comprising:
obtaining neural signal data from a neural signal recorder implanted in the head of a user and configured to record neural signals from a brain of the user;
temporally binning the neural signal data to create at least one neural population time series;
converting the at least one neural population time series into at least one time probability series; and
identifying a most likely symbol from the at least one time probability series after a time delay triggered by identification of a high probability of a new character in the at least one time probability series;
and
perform a command associated with the identified most likely symbol using an output device.
11. The method of claim 10 , wherein the neural signal recorder is a microelectrode array.
12. The method of claim 10 , wherein the symbol model is a neural network.
13. The method of claim 12 , wherein the symbol model is selected from the group consisting of: recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and temporal convolutional networks.
14. The method of claim 10 , wherein the symbol model is a hidden Markov model.
15. The method of claim 10 , wherein each bin is between 10 ms and 300 ms.
16. The method of claim 10 , wherein the performed command is associated with the estimated symbol in a database comprising:
a plurality of symbols; and
a plurality of commands;
wherein each symbol in the plurality of symbols is associated with a command.
17. The method of claim 16 , wherein the symbols in the symbol database are difference maximized.
18. The method of claim 16 , wherein commands in the plurality of commands are computer functions.