Wavelet Shrinkage and Thresholding based Robust Classification for Brain Computer Interface

TL;DR

This paper introduces a wavelet shrinkage and thresholding based classifier for brain computer interface data, demonstrating robustness and high performance in decoding tasks from local field potentials.

Contribution

It proposes a novel wavelet-based classifier that is robust, consistent, and applicable to various time-series data, including brain signals.

Findings

High decoding accuracy achieved on LFP data

Classifier is robust under Gaussian noise

Applicable to diverse time-series classification tasks

Abstract

A macaque monkey is trained to perform two different kinds of tasks, memory aided and visually aided. In each task, the monkey saccades to eight possible target locations. A classifier is proposed for direction decoding and task decoding based on local field potentials (LFP) collected from the prefrontal cortex. The LFP time-series data is modeled in a nonparametric regression framework, as a function corrupted by Gaussian noise. It is shown that if the function belongs to Besov bodies, then using the proposed wavelet shrinkage and thresholding based classifier is robust and consistent. The classifier is then applied to the LFP data to achieve high decoding performance. The proposed classifier is also quite general and can be applied for the classification of other types of time-series data as well, not necessarily brain data.