A macaque monkey is trained to perform two different kinds of tasks, memoryaided and visually aided. In each task, the monkey saccades to eight possibletarget locations. A classifier is proposed for direction decoding and taskdecoding based on local field potentials (LFP) collected from the prefrontalcortex. The LFP time-series data is modeled in a nonparametric regressionframework, as a function corrupted by Gaussian noise. It is shown that if thefunction belongs to Besov bodies, then using the proposed wavelet shrinkage andthresholding based classifier is robust and consistent. The classifier is thenapplied to the LFP data to achieve high decoding performance. The proposedclassifier is also quite general and can be applied for the classification ofother types of time-series data as well, not necessarily brain data.
展开▼
