Classification based on dynamic mode decomposition applied to brain recognition of context

SEBASTIÁN MARTÍNEZ; AZUL SILVA; DEMIAN GARCÍA VIOLINI; PIRIZ, JOAQUIN; BELLUSCIO, MARIANO; RICARDO S. SÁNCHEZ PEÑA

CHAOS, SOLITONS AND FRACTALS

PERGAMON-ELSEVIER SCIENCE LTD

Lugar: Amsterdam; Año: 2021

0960-0779

Local Field Potentials (LFPs) are easy to access electrical signals of the brain that represent the summation in theextracellular space, of currents originated within the neurons. As such, LFPs could contain information about ongoingcomputations in neuronal circuits and could potentially be used to design brain machine interface algorithms. Howeverhow brain computations could be decoded from LFPs is not clear. Within this context, a methodology for signalclassication is proposed in this study, particularly based on the Dynamic Mode Decomposition method, in conjunctionwith binary clustering routines based on supervised learning. Note that, although the classication methodology ispresented here in the context of a biological problem, it can be applied to a broad range of applications. Then, asa case-study, the proposed method is validated with the classication of LFP-based brain cognitive states. All theanalysis, signals, and results shown in this study consider real data measured in the hippocampus, in rats performingexploration tasks. Consequently, it is shown that, using the measured LFP, the method infers which context was theanimal exploring. Thus, evidence on the spatial codication in LFP signals is consequently provided, which still is anopen question in neuroscience.