Recognition of MI-EEG signals using extended-LSR-based inductive transfer learning

TL;DR

This paper introduces a new transfer learning method to improve the recognition of motor imagery EEG signals in brain-computer interfaces.

Contribution

The novel method extends LSR-based inductive transfer learning to work across multiple intelligent models, enhancing generalization and performance.

Findings

The method effectively transfers knowledge from source to target domains with limited training data.

It outperforms existing methods by integrating multiple classic models like neural networks and fuzzy systems.

Experimental results confirm its effectiveness in MI-EEG signal recognition.

Abstract

Motor imagery electroencephalographic (MI-EEG) signal recognition is used in various brain–computer interface (BCI) systems. In most existing BCI systems, this identification relies on classification algorithms. However, generally, a large amount of subject-specific labeled training data is required to reliably calibrate the classification algorithm for each new subject. To address this challenge, an effective strategy is to integrate transfer learning into the construction of intelligent models, allowing knowledge to be transferred from the source domain to enhance the performance of models trained in the target domain. Although transfer learning has been implemented in EEG signal recognition, many existing methods are designed specifically for certain intelligent models, limiting their application and generalization.

To broaden application and generalization, an extended-LSR-based inductive transfer learning method is proposed to facilitate transfer learning across various classical intelligent models, including neural networks, Takagi-SugenoKang (TSK) fuzzy systems, and kernel methods.

The proposed method not only promotes the transfer of valuable knowledge from the source domain to improve learning performance in the target domain when target domain training data are insufficient but also enhances application and generalization by incorporating multiple classic base models. The experimental results demonstrate the effectiveness of the proposed method in MI-EEG signal recognition.

Figures