System and method for decoding and behaviorally validating memory consolidation during sleep from EEG after waking experience
Described is a system for decoding and validating memory consolidation. During operation, the system receives electroencephalographic (EEG) data while a subject is performing a specific task. Nuisance signals are then removed from the EEG data, resulting in a nuisance free signal. Skill feature vectors are generated from the nuisance free signal using time-invariant feature extraction. A skill classifier can then be trained for the specific task based on the skill feature vectors to generate a subject specific model regarding a memory replay for the specific task. Finally, electrodes in a neural cap are activated based on the memory replay.
1. A system for decoding and validating memory consolidation, the system comprising:
one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations of:
receiving waking task electroencephalographic (EEG) data;
removing nuisance signals from the waking task EEG data, resulting in a nuisance free signal;
generating skill feature vectors from the nuisance free signal using time-invariant feature extraction; and
training a skill classifier for a specific task based on the skill feature vectors to generate a specific model regarding a memory replay for the specific task;
activating one or more electrodes in a neural cap based on the memory replay.
2. The system as set forth in claim 1 , further performing operations of: receiving sleep EEG data; identifying phases of slow-wave sleep in the sleep EEG data to identify phase-locked segments; generating a test feature vector from the phase-locked segments using time-invariant feature extraction; classifying the test feature vector for the specific task, the classification including a confidence value; and if the confidence value exceeds a predetermined threshold, then designating the phase-locked segments as a memory replay for the specific task.
3. The system as set forth in claim 2 , wherein the skill feature vectors include spectral, coherence, and wavelet feature vectors.
4. The system as set forth in claim 1 , wherein the skill feature vectors include spectral, coherence, and wavelet feature vectors.
5. A computer program product for decoding and validating memory consolidation, the computer program product comprising:
a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
receiving waking task electroencephalographic (EEG) data;
removing nuisance signals from the waking task EEG data, resulting in a nuisance free signal;
generating skill feature vectors from the nuisance free signal using time-invariant feature extraction; and
training a skill classifier for a specific task based on the skill feature vectors to generate a specific model regarding a memory replay for the specific task;
activating one or more electrodes in a neural cap based on the memory replay.
6. The computer program product as set forth in claim 5 , further comprising instructions for causing the one or more processors to perform operations of: receiving sleep EEG data; identifying phases of slow-wave sleep in the sleep EEG data to identify phase-locked segments; generating a test feature vector from the phase-locked segments using time-invariant feature extraction; classifying the test feature vector for the specific task, the classification including a confidence value; and if the confidence value exceeds a predetermined threshold, then designating the phase-locked segments as a memory replay for the specific task.
7. The computer program product as set forth in claim 6 , wherein the skill feature vectors include spectral, coherence, and wavelet feature vectors.
8. The computer program product as set forth in claim 5 , wherein the skill feature vectors include spectral, coherence, and wavelet feature vectors.
9. A computer implemented method for decoding and validating memory consolidation, the method comprising an act of:
causing one or more processers to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
receiving waking task electroencephalographic (EEG) data;
removing nuisance signals from the waking task EEG data, resulting in a nuisance free signal;
generating skill feature vectors from the nuisance free signal using time-invariant feature extraction; and
training a skill classifier for a specific task based on the skill feature vectors to generate a specific model regarding a memory replay for the specific task
activating one or more electrodes in a neural cap based on the memory replay.
10. The method as set forth in claim 9 , further performing acts of: receiving sleep EEG data; identifying phases of slow-wave sleep in the sleep EEG data to identify phase-locked segments; generating a test feature vector from the phase-locked segments using time-invariant feature extraction; classifying the test feature vector for the specific task, the classification including a confidence value; and if the confidence value exceeds a predetermined threshold, then designating the phase-locked segments as a memory replay for the specific task.
11. The method as set forth in claim 10 , wherein the skill feature vectors include spectral, coherence, and wavelet feature vectors.
12. The method as set forth in claim 9 , wherein the skill feature vectors include spectral, coherence, and wavelet feature vectors.