Variable Selection for Motor Cortical Control of Directions

In our previous work, a non-stereotypical brain machine interface system was implemented with freely-moving rats, and a nonlinear support vector machine (SVM) classifier was used to map neural signals in the rats' motor cortices onto a set of discrete classes of directions (left and right). In this paper, we provide a comprehensive analysis about the selection of neurons and temporal parameters, which is critical to the success of the system. We also show that pre-processing by principal component analysis (PCA) can reduce dimensions and improve accuracy