Transforming Motor Imagery Analysis: A Novel EEG Classification Framework Using AtSiftNet Method

Abstract

This paper presents an innovative approach for the Feature Extraction method using Self-Attention, incorporating various Feature Selection techniques known as the AtSiftNet method to enhance the classification performance of motor imaginary activities using electrophotography (EEG) signals. Initially, the EEG signals were sorted and then denoised using multiscale principal component analysis to obtain clean EEG signals. However, we also conducted a non-denoised experiment. Subsequently, the clean EEG signals underwent the Self-Attention feature extraction method to compute the features of each trial (i.e., 350×18). The best 1 or 15 features were then extracted through eight different feature selection techniques. Finally, five different machine learning and neural network classification models were employed to calculate the accuracy, sensitivity, and specificity of this approach. The BCI competition III dataset IV-a was utilized for all experiments, encompassing the datasets of five volunteers who participated in the competition. The experiment findings reveal that the average accuracy of classification is highest among ReliefF (i.e., 99.946%), Mutual Information (i.e., 98.902%), Independent Component Analysis (i.e., 99.62%), and Principal Component Analysis (i.e., 98.884%) for both 1 and 15 best-selected features from each trial. These accuracies were obtained for motor imagery using a Support Vector Machine (SVM) as a classifier. In addition, five-fold validation was performed in this paper to assess the fair performance estimation and robustness of the model. The average accuracy obtained through five-fold validation is 99.89%. The experiments' findings indicate that the suggested framework provides a resilient biomarker with minimal computational complexity, making it a suitable choice for advancing Motor Imagery Brain-Computer Interfaces (BCI).

Keywords: attention sift network (AtSiftNet); brain–computer interface (BCI); independent component analysis (ICA); motor imagery (MI); principal component analysis (PCA).

Figure 1

Proposed Framework for novel AtSiftNet method.

Figure 2

Block Diagram of (MSPCA).

Figure 3

A comparison graph between original EEG signal and Denoised signal.

Figure 4

Architecture of Self-attention feature extraction.

Figure 5

Classification accuracy (%) of all subjects and machine learning classifier.

Figure 6

3D bar chart of Sensitivity by using different classifiers.

Figure 7

Specificity of all subjects of MI task with all classifiers.

Figure 8

Performance parameters of Motor Imaginary dataset IV-a.

Figure 9

Specificity of MI dataset-Iva using SVM classifier.

Figure 10

Specificity of MI task dataset Iva using SVM classifier.

Figure 11

A graphical comparison between top one selected features and top 15 selected features.

Figure 12

Correlation Matrix for top 15 selected features.

Figure 13

Correlation Matrix for top 1 selected features.

Figure 14

Comparison of Accuracy (%) of both scenarios by using MIFs as feature selection and SVM as classifier.

Figure 15

A graphical visualization of Denoised and Non-denoised data.

Figure 16

Feature Extraction time of each subject.

Figure 17

Using all classifier training time of each subject.

Figure 18

Using all classifier Testing Time of each subject.

Figure 19

ROC curves and AUC values of feature selection technique.

Figure 20

ROC graphs by using MIFs as a feature selection technique.

Figure 21

Comparison of AUC values for top one selected features from each trial.

Figure 22

Comparison of AUC values for top 15 selected features from each trial.