TY - GEN

T1 - Classification of Local Field Potentials using Gaussian Sequence Model

AU - Banerjee, Taposh

AU - Choi, John

AU - Pesaran, Bijan

AU - Ba, Demba

AU - Tarokh, Vahid

N1 - Funding Information:
The work at both Harvard and NYU was supported by the Army Research Office MURI Contract Number W911NF-16-1-0368.
Publisher Copyright:
© 2018 IEEE.

PY - 2018/8/29

Y1 - 2018/8/29

N2 - A problem of classification of local field potentials (LFPs), recorded from the prefrontal cortex of a macaque monkey, is considered. An adult macaque monkey is trained to perform a memory based saccade. The objective is to decode the eye movement goals from the LFP collected during a memory period. The LFP classification problem is modeled as that of classification of smooth functions embedded in Gaussian noise. It is then argued that using minimax function estimators as features would lead to consistent LFP classifiers. The theory of Gaussian sequence models allows us to represent minimax estimators as finite dimensional objects. The LFP classifier resulting from this mathematical endeavor is a spectrum based technique, where Fourier series coefficients of the LFP data, followed by appropriate shrinkage and thresholding, are used as features in a linear discriminant classifier. The classifier is then applied to the LFP data to achieve high decoding accuracy. The function classification approach taken in the paper also provides a systematic justification for using Fourier series, with shrinkage and thresholding, as features for the problem, as opposed to using the power spectrum. It also suggests that phase information is crucial to the decision making.

AB - A problem of classification of local field potentials (LFPs), recorded from the prefrontal cortex of a macaque monkey, is considered. An adult macaque monkey is trained to perform a memory based saccade. The objective is to decode the eye movement goals from the LFP collected during a memory period. The LFP classification problem is modeled as that of classification of smooth functions embedded in Gaussian noise. It is then argued that using minimax function estimators as features would lead to consistent LFP classifiers. The theory of Gaussian sequence models allows us to represent minimax estimators as finite dimensional objects. The LFP classifier resulting from this mathematical endeavor is a spectrum based technique, where Fourier series coefficients of the LFP data, followed by appropriate shrinkage and thresholding, are used as features in a linear discriminant classifier. The classifier is then applied to the LFP data to achieve high decoding accuracy. The function classification approach taken in the paper also provides a systematic justification for using Fourier series, with shrinkage and thresholding, as features for the problem, as opposed to using the power spectrum. It also suggests that phase information is crucial to the decision making.

KW - Block-wise James-Stein estimator

KW - Gaussian sequence model

KW - brain machine interface (BMI

KW - minimax function estimators

KW - pinsker's theorem

UR - http://www.scopus.com/inward/record.url?scp=85053832160&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053832160&partnerID=8YFLogxK

U2 - 10.1109/SSP.2018.8450778

DO - 10.1109/SSP.2018.8450778

M3 - Conference contribution

AN - SCOPUS:85053832160

SN - 9781538615706

T3 - 2018 IEEE Statistical Signal Processing Workshop, SSP 2018

SP - 218

EP - 222

BT - 2018 IEEE Statistical Signal Processing Workshop, SSP 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th IEEE Statistical Signal Processing Workshop, SSP 2018

Y2 - 10 June 2018 through 13 June 2018

ER -