Random Subspace Ensemble Learning for Functional Near-Infrared Spectroscopy Brain-Computer Interfaces.

Jaeyoung Shin

doi:10.3389/fnhum.2020.00236

Abstract

The feasibility of the random subspace ensemble learning method was explored to improve the performance of functional near-infrared spectroscopy-based brain-computer interfaces (fNIRS-BCIs). Feature vectors have been constructed using the temporal characteristics of concentration changes in fNIRS chromophores such as mean, slope, and variance to implement fNIRS-BCIs systems. The mean and slope, which are the most popular features in fNIRS-BCIs, were adopted. Linear support vector machine and linear discriminant analysis were employed, respectively, as a single strong learner and multiple weak learners. All features in every channel and available time window were employed to train the strong learner, and the feature subsets were selected at random to train multiple weak learners. It was determined that random subspace ensemble learning is beneficial to enhance the performance of fNIRS-BCIs.

Highlights

Ensemble learning has been applied actively in many different machine learning fields (Akram et al, 2015; Li et al, 2016; Ren et al, 2016; Hassan and Bhuiyan, 2017; Sagi and Rokach, 2018; Yaman et al, 2018; Zerrouki et al, 2018)
Different prediction performances were observed among linear discriminant analysis (LDA) classifiers (One-Way analysis of variance (ANOVA), p < 0.001)
The enhanced prediction performance of random subspace ensemble learning was validated to investigate the feasibility of ensemble learning based on the random subspace method

Summary

Introduction

Ensemble learning has been applied actively in many different machine learning fields (Akram et al, 2015; Li et al, 2016; Ren et al, 2016; Hassan and Bhuiyan, 2017; Sagi and Rokach, 2018; Yaman et al, 2018; Zerrouki et al, 2018) It is defined as a type of machine learning technique that takes advantage of multiple weak (i.e., straightforward but fair performance) learners instead of a single strong (i.e., sophisticated and powerful performance) learner to make high-quality predictions. This implies that the principle of collective intelligence being superior to an elite can be applied in the field of machine learning.

Methods

Results

Discussion

Conclusion