Intelligent Classification Technique of Hand Motor Imagery Using EEG Beta Rebound Follow-Up Pattern

Abstract

To apply EEG-based brain-machine interfaces during rehabilitation, separating various tasks during motor imagery (MI) and assimilating MI into motor execution (ME) are needed. Previous studies were focusing on classifying different MI tasks based on complex algorithms. In this paper, we implement intelligent, straightforward, comprehensible, time-efficient, and channel-reduced methods to classify ME versus MI and left- versus right-hand MI. EEG of 30 healthy participants undertaking motional tasks is recorded to investigate two classification tasks. For the first task, we first propose a “follow-up” pattern based on the beta rebound. This method achieves an average classification accuracy of 59.77% ± 11.95% and can be up to 89.47% for finger-crossing. Aside from time-domain information, we map EEG signals to feature space using extraction methods including statistics, wavelet coefficients, average power, sample entropy, and common spatial patterns. To evaluate their practicability, we adopt a support vector machine as an intelligent classifier model and sparse logistic regression as a feature selection technique and achieve 79.51% accuracy. Similar approaches are taken for the second classification reaching 75.22% accuracy. The classifiers we propose show high accuracy and intelligence. The achieved results make our approach highly suitable to be applied to the rehabilitation of paralyzed limbs.

Exploring the Role of Visual Guidance in Motor Imagery-Based Brain-Computer Interface: An EEG Microstate-Specific Functional Connectivity Study

“…All microstate features were retained. However, even without feature selection and using only microstate parameters, accuracy (80.27% across all six motions) higher than our former study [ 5 ] was achieved. In that study, an accuracy of 78.57% was achieved with 26 statistical, wavelet-based, and power parameters using the same dataset.…”

“…The EEG recording system consisted of the Brain Products actiCHamp Plus (EEG signal amplifier) and actiCAP slim (active EEG electrodes). More details of the recording system of the EEG signals and the experimental protocol can be found in our former work [ 5 ]. The dataset of this manuscript and our former work is the same.…”

“…Among BCI modalities, electroencephalography (EEG) is frequently used because of its high temporal resolution, noninvasiveness, and portability. EEG signals have shown an excellent ability to classify different motor conditions [ 5 ] and different motions during MI tasks [ 6 , 7 ]. In the former studies of EEG, many investigations have been focused on static features, which may lose important temporal information.…”

Intelligent Biosignal Processing in Wearable and Implantable Sensors

“…The study by Sawan et al [ 1 ] applies EEG-based brain-machine interfaces during medical rehabilitation, by separating various tasks during motor imagery (MI) and assimilating MI into motor execution (ME). The authors implement intelligent, straightforward, comprehensible, time-efficient, and channel-reduced methods to classify ME versus MI and left- versus right-hand MI.…”