TY - GEN
T1 - Low-rank representation of neural activity and detection of submovements
AU - Chang, Young Hwan
AU - Chen, Mo
AU - Gowda, Suraj
AU - Overduin, Simon A.
AU - Carmena, Jose M.
AU - Tomlin, Claire
PY - 2013
Y1 - 2013
N2 - In this study, Robust Principal Component Analysis (RPCA) is applied to neural spike datasets to extract neural signatures that signify the onset of submovements, a type of motor primitive. Given neural activity recorded from rhesus macaques during a set of reaches between targets in a horizontal plane, we aim to identify common event-related neural features and validate sub movement-based motor primitives inferred from the hand velocity profiles. Such features represent common dynamic patterns across many experimental trials and may be used as a signature to detect discrete events such as submovement onset. We present RPCA, a method well suited for extracting data matrices' low-rank component and this method allows (1) removal of task-irrelevant signal from data, (2) identification of task-related dynamic patterns, and (3) detection of sub movements. We also explored using the Random Projection (RP) technique and applying RP to data prior to applying RPCA improved the sub movement prediction performance by de-sparsifying neural data while preserving certain statistical characteristics of aggregate neural activity.
AB - In this study, Robust Principal Component Analysis (RPCA) is applied to neural spike datasets to extract neural signatures that signify the onset of submovements, a type of motor primitive. Given neural activity recorded from rhesus macaques during a set of reaches between targets in a horizontal plane, we aim to identify common event-related neural features and validate sub movement-based motor primitives inferred from the hand velocity profiles. Such features represent common dynamic patterns across many experimental trials and may be used as a signature to detect discrete events such as submovement onset. We present RPCA, a method well suited for extracting data matrices' low-rank component and this method allows (1) removal of task-irrelevant signal from data, (2) identification of task-related dynamic patterns, and (3) detection of sub movements. We also explored using the Random Projection (RP) technique and applying RP to data prior to applying RPCA improved the sub movement prediction performance by de-sparsifying neural data while preserving certain statistical characteristics of aggregate neural activity.
UR - http://www.scopus.com/inward/record.url?scp=84902346292&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902346292&partnerID=8YFLogxK
U2 - 10.1109/CDC.2013.6760263
DO - 10.1109/CDC.2013.6760263
M3 - Conference contribution
AN - SCOPUS:84902346292
SN - 9781467357173
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 2544
EP - 2549
BT - 2013 IEEE 52nd Annual Conference on Decision and Control, CDC 2013
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 52nd IEEE Conference on Decision and Control, CDC 2013
Y2 - 10 December 2013 through 13 December 2013
ER -