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

Abstract

Introduction: 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.

Methods: 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.

Results and discussion: 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.

Keywords: EEG; LSR; brain-computer interface; inductive transfer learning; motor imagery.

Figure 1

Differences between traditional machine learning (a) and transfer learning (b).

Figure 2

Framework of ELSR-TL.

Figure 3

Distribution of each subset from the BCI Competition Data Set IVa.

Figure 4

Representative MI-EEG signals for each subset of the BCI Competition Data Set IVa.

Algorithm 1

The ELSR-TL.

Figure 5

Features extracted from subset aa by TR-CSP.

Figure 6

Classification accuracies of 13 different methods, where the accuracies of the transfer learning methods represent the average accuracies across four different source domains with a fixed target domain.

Figure 7

Classification results of three feature extraction methods.

Figure 8

Specific differences of ELSR-TL (TSK) compared to other methods.

Figure 9

Accuracy changes with different values of four parameters: (a) M, (b) $\tau$ , (c) $\lambda$ , (d) $\beta$ .