Wavelet Shrinkage and Thresholding based Robust Classification for Brain\n Computer Interface

2017/10/27 by Taposh Banerjee, Banerjee, Taposh, John Choi +7
Computer Science · Neuroscience · #Applications (stat.AP) #EEG and Brain-Computer Interfaces #FOS: Computer and information sciences #Methodology (stat.ME) #Neural Networks and Applications #Neural dynamics and brain function

paper · pdf · doi:10.48550/arxiv.1710.10279

openalex publication_date 2017/10/27 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28

Abstract

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

Related

• Classification of Local Field Potentials using Gaussian Sequence Model
• Spatial Filtering for Brain Computer Interfaces: A Comparison between the Common Spatial Pattern and Its Variant
• A framework for detection and classification of events in neural activity
• Minimax-optimal decoding of movement goals from local field potentials\n using complex spectral features
• Multiclass Common Spatial Pattern for EEG based Brain Computer Interface\n with Adaptive Learning Classifier