Brain machine interface using portable Near-InfraRed spectroscopy — Improvement of classification performance based on ICA analysis and self-proliferating LVQ

Abstract

Recently, the Brain-Machine Interface (BMI) has been expected to be applied to robotics and medical science field as a new intuitive interface. BMI measures human cerebral activities and uses them directly as an input signal to various instruments. The future goal of our research is to design a practical BMI system that can be used reliably in daily lives. In this paper, we will discuss a design method of a BMI system using a portable Near-InfraRed Spectroscopy (NIRS) device and then we will consider improving the performance of the learning vector quantization (LVQ) classifier by using the independent component analysis (ICA) and the self-proliferating function of neurons. The effectiveness of the proposed method is investigated in human imagery classification experiments.