Motor Imagery EEG Signal Classification Using Minimally Random Convolutional Kernel Transform and Hybrid Deep Learning

2025-08-22

AI Summary

To address the challenges of non-stationarity, high inter-subject variability, and multi-class discrimination in motor imagery electroencephalography (MI-EEG) classification, this work introduces MiniRocket—the Minimally Random Convolutional Kernel Transform—for the first time to MI-EEG analysis. We propose a lightweight and efficient feature extraction pipeline, benchmarking against a CNN-LSTM hybrid model. MiniRocket employs randomly initialized convolutional kernels followed by temporal pooling to rapidly generate robust time-series features, enabling end-to-end classification via a linear classifier. Evaluated on the PhysioNet MI-EEG dataset, our approach achieves a mean classification accuracy of 98.63%, outperforming the CNN-LSTM baseline (98.06%) while substantially reducing computational overhead. This study establishes a new paradigm for MI-EEG analysis that balances high accuracy with low resource consumption, advancing the practical deployment of lightweight brain–computer interfaces.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: State Estimation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The brain-computer interface (BCI) establishes a non-muscle channel that enables direct communication between the human body and an external device. Electroencephalography (EEG) is a popular non-invasive technique for recording brain signals. It is critical to process and comprehend the hidden patterns linked to a specific cognitive or motor task, for instance, measured through the motor imagery brain-computer interface (MI-BCI). A significant challenge is presented by classifying motor imagery-based electroencephalogram (MI-EEG) tasks, given that EEG signals exhibit nonstationarity, time-variance, and individual diversity. Obtaining good classification accuracy is also very difficult due to the growing number of classes and the natural variability among individuals. To overcome these issues, this paper proposes a novel method for classifying EEG motor imagery signals that extracts features efficiently with Minimally Random Convolutional Kernel Transform (MiniRocket), a linear classifier then uses the extracted features for activity recognition. Furthermore, a novel deep learning based on Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) architecture to serve as a baseline was proposed and demonstrated that classification via MiniRocket's features achieves higher performance than the best deep learning models at lower computational cost. The PhysioNet dataset was used to evaluate the performance of the proposed approaches. The proposed models achieved mean accuracy values of 98.63% and 98.06% for the MiniRocket and CNN-LSTM, respectively. The findings demonstrate that the proposed approach can significantly enhance motor imagery EEG accuracy and provide new insights into the feature extraction and classification of MI-EEG.

Problem

• Classifying motor imagery EEG signals with high accuracy
• Overcoming nonstationarity and individual variability in EEG data
• Reducing computational cost while improving classification performance

Innovation

• Minimally Random Convolutional Kernel Transform feature extraction
• Hybrid CNN-LSTM deep learning architecture baseline
• Linear classification with MiniRocket features outperforms deep learning