Adaptive Subspace Sampling for Class Imbalance Processing-Some clarifications, algorithm, and further investigation including applications to Brain Computer Interface

TL;DR

This paper extends and clarifies a method using Kohonen's ASSOM for oversampling in imbalanced classification, demonstrating its effectiveness on benchmark datasets and EEG-based Brain Computer Interface applications.

Contribution

It provides a detailed algorithm for oversampling with ASSOM, applies it to multiple BCI tasks, and compares its performance with other state-of-the-art methods.

Findings

The ASSOM-based method improves classification accuracy on imbalanced datasets.

It outperforms several existing methods in benchmark tests.

Effective in analyzing EEG data for BCI applications.

Abstract

Kohonen's Adaptive Subspace Self-Organizing Map (ASSOM) learns several subspaces of the data where each subspace represents some invariant characteristics of the data. To deal with the imbalance classification problem, earlier we have proposed a method for oversampling the minority class using Kohonen's ASSOM. This investigation extends that study, clarifies some issues related to our earlier work, provides the algorithm for generation of the oversamples, applies the method on several benchmark data sets, and makes application to three Brain Computer Interface (BCI) applications. First we compare the performance of our method using some benchmark data sets with several state-of-the-art methods. Finally, we apply the ASSOM-based technique to analyze the three BCI based applications using electroencephalogram (EEG) datasets. These tasks are classification of motor imagery , drivers' fatigue states, and phases of migraine. Our results demonstrate the effectiveness of the ASSOM-based meth od in dealing with imbalance classification problem.