Evaluation of fractal dimension estimation methods for feature extraction in motor imagery based brain computer interface

Fractal Dimension as a discriminative feature for high accuracy classification in motor imagery EEG-based brain-computer interface

BACKGROUND AND OBJECTIVE

The brain-computer interface (BCI) technology acquires human brain electrical signals, which can be effectively and successfully used to control external devices, potentially supporting subjects suffering from motor impairments in the interaction with the environment. To this aim, BCI systems must correctly decode and interpret neurophysiological signals reflecting the intention of the subjects to move. Therefore, the accurate classification of single events in motor tasks represents a fundamental challenge in ensuring efficient communication and control between users and BCIs. Movement-associated changes in electroencephalographic (EEG) sensorimotor rhythms, such as event-related desynchronization (ERD), are well-known features of discriminating motor tasks. Fractal dimension (FD) can be used to evaluate the complexity and self-similarity in brain signals, potentially providing complementary information to frequency-based signal features.

METHODS

In the present work, we introduce FD as a novel feature for subject-independent event classification, and we test several machine learning (ML) models in behavioural tasks of motor imagery (MI) and motor execution (ME).

RESULTS

Our results show that FD improves the classification accuracy of ML compared to ERD. Furthermore, unilateral hand movements have higher classification accuracy than bilateral movements in both MI and ME tasks.

CONCLUSIONS

These results provide further insights into subject-independent event classification in BCI systems and demonstrate the potential of FD as a discriminative feature for EEG signals.

Evaluation of electroencephalography analysis methods

The extraction of expressive features from an electroencephalography (EEG) signal is necessary for classification of movement and movement imagination of the limbs. We introduce different preprocessing and feature extraction algorithms for this purpose and develop an algorithm that selects features by their feature importance. This selection is used as an evaluation measure for features, their preprocessing algorithms and the EEG electrodes. Our results show that most influential features for signal interpretation are: common spatial patterns, fractal dimensions, as well as, variance and standard deviation of the preprocessed data. We show that preprocessing with continuous wavelet transforms outperforms the other tested preprocessing algorithms. Furthermore, we show that high gamma frequencies (70-90 Hz) contain more information than the lower μ-rhythms (8-12 Hz) where event-related-desynchronization (ERD) is known to occur. The important EEG electrodes for this classification task are located in the left and right back of the motor-cortex. The proposed algorithm can be further used to create subject-specific and performance models for real-time classification.

Motor Imagery EEG Classification for Patients with Amyotrophic Lateral Sclerosis Using Fractal Dimension and Fisher's Criterion-Based Channel Selection

Motor imagery is based on the volitional modulation of sensorimotor rhythms (SMRs); however, the sensorimotor processes in patients with amyotrophic lateral sclerosis (ALS) are impaired, leading to degenerated motor imagery ability. Thus, motor imagery classification in ALS patients has been considered challenging in the brain–computer interface (BCI) community. In this study, we address this critical issue by introducing the Grassberger–Procaccia and Higuchi’s methods to estimate the fractal dimensions (GPFD and HFD, respectively) of the electroencephalography (EEG) signals from ALS patients. Moreover, a Fisher’s criterion-based channel selection strategy is proposed to automatically determine the best patient-dependent channel configuration from 30 EEG recording sites. An EEG data collection paradigm is designed to collect the EEG signal of resting state and the imagination of three movements, including right hand grasping (RH), left hand grasping (LH), and left foot stepping (LF). Five late-stage ALS patients without receiving any SMR training participated in this study. Experimental results show that the proposed GPFD feature is not only superior to the previously-used SMR features (mu and beta band powers of EEG from sensorimotor cortex) but also better than HFD. The accuracies achieved by the SMR features are not satisfactory (all lower than 80%) in all binary classification tasks, including RH imagery vs. resting, LH imagery vs. resting, and LF imagery vs. resting. For the discrimination between RH imagery and resting, the average accuracies of GPFD in 30-channel (without channel selection) and top-five-channel configurations are 95.25% and 93.50%, respectively. When using only one channel (the best channel among the 30), a high accuracy of 91.00% can still be achieved by the GPFD feature and a linear discriminant analysis (LDA) classifier. The results also demonstrate that the proposed Fisher’s criterion-based channel selection is capable of removing a large amount of redundant and noisy EEG channels. The proposed GPFD feature extraction combined with the channel selection strategy can be used as the basis for further developing high-accuracy and high-usability motor imagery BCI systems from which the patients with ALS can really benefit.

Effect of tDCS stimulation of motor cortex and cerebellum on EEG classification of motor imagery and sensorimotor band power

Background

Transcranial direct current stimulation (tDCS) is a technique for brain modulation that has potential to be used in motor neurorehabilitation. Considering that the cerebellum and motor cortex exert influence on the motor network, their stimulation could enhance motor functions, such as motor imagery, and be utilized for brain-computer interfaces (BCIs) during motor neurorehabilitation.

Methods

A new tDCS montage that influences cerebellum and either right-hand or feet motor area is proposed and validated with a simulation of electric field. The effect of current density (0, 0.02, 0.04 or 0.06 mA/cm²) on electroencephalographic (EEG) classification into rest or right-hand/feet motor imagery was evaluated on 5 healthy volunteers for different stimulation modalities: 1) 10-minutes anodal tDCS before EEG acquisition over right-hand or 2) feet motor cortical area, and 3) 4-seconds anodal tDCS during EEG acquisition either on right-hand or feet cortical areas before each time right-hand or feet motor imagery is performed. For each subject and tDCS modality, analysis of variance and Tukey-Kramer multiple comparisons tests (p <0.001) are used to detect significant differences between classification accuracies that are obtained with different current densities. For tDCS modalities that improved accuracy, t-tests (p <0.05) are used to compare μ and β band power when a specific current density is provided against the case of supplying no stimulation.

Results

The proposed montage improved the classification of right-hand motor imagery for 4 out of 5 subjects when the highest current was applied for 10 minutes over the right-hand motor area. Although EEG band power changes could not be related directly to classification improvement, tDCS appears to affect variably different motor areas on μ and/or β band.

Conclusions

The proposed montage seems capable of enhancing right-hand motor imagery detection when the right-hand motor area is stimulated. Future research should be focused on applying higher currents over the feet motor cortex, which is deeper in the brain compared to the hand motor cortex, since it may allow observation of effects due to tDCS. Also, strategies for improving analysis of EEG respect to accuracy changes should be implemented.

Using Fractal and Local Binary Pattern Features for Classification of ECOG Motor Imagery Tasks Obtained from the Right Brain Hemisphere

The feature extraction and classification of brain signal is very significant in brain–computer interface (BCI). In this study, we describe an algorithm for motor imagery (MI) classification of electrocorticogram (ECoG)-based BCI. The proposed approach employs multi-resolution fractal measures and local binary pattern (LBP) operators to form a combined feature for characterizing an ECoG epoch recording from the right hemisphere of the brain. A classifier is trained by using the gradient boosting in conjunction with ordinary least squares (OLS) method. The fractal intercept, lacunarity and LBP features are extracted to classify imagined movements of either the left small finger or the tongue. Experimental results on dataset I of BCI competition III demonstrate the superior performance of our method. The cross-validation accuracy and accuracy is 90.6% and 95%, respectively. Furthermore, the low computational burden of this method makes it a promising candidate for real-time BCI systems.

Fractals properties of EEG during event-related desynchronization of motor imagery

Chaos and fractal dimension are emerging modalities for the research of electroencephalogram (EEG) signal processing. The capability of measuring non-linear characteristics of the fractal dimension enables new methodologies to identify distinct brain activities. Recent studies on the topic focus on utilizing various types of fractals as features in order to design better brain state classification system. However, we have little insight about the EEG signals projected in fractal dimension. In this paper, we investigate the relationship between the non-linear characteristics of ongoing EEG signals and event-related desynchronization (ERD) during motor imagery. We observed a considerable synchronization between ERD and fractal dimension. This finding suggests further usage of chaos and fractal theory in investigating brain activities.