•Action observation therapy can be used for rehabilitation of Parkinson's disease.•Motor imagery practice can be used for rehabilitation of Parkinson's disease.•Rehabilitation for Parkinson's disease ...might combine action observation and motor imagery.•Action observation and motor imagery involve both cortical and sub-cortical processes.
This article discusses recent evidence supporting the use of action observation therapy and motor imagery practice for rehabilitation of Parkinson's disease. A main question that emerges from the review regards the different effectiveness of these approaches and the possibility of integrating them into a single method to enhance motor behaviour in subjects with Parkinson’s disease. In particular, the reviewed studies suggest that action observation therapy can have a positive effect on motor facilitation of patients and that a long-term rehabilitation program based on action observation therapy or motor imagery practice can bring some benefit on their motor recovery. Moreover, the paper discusses how the research on the combined use of action observation and motor imagery for motor improvements in healthy subjects may encourage the combined use of action observation therapy and motor imagery practice for therapeutic aims in Parkinson's disease. To date, this hypothesis has never been experimented.
Motor imagery (MI) or the mental simulation of action is now increasingly being studied using neuroimaging techniques such as positron emission tomography and functional magnetic resonance imaging. ...The booming interest in capturing the neural underpinning of MI has provided a large amount of data which until now have never been quantitatively summarized. The aim of this activation likelihood estimation (ALE) meta-analysis was to provide a map of the brain structures involved in MI. Combining the data from 75 papers revealed that MI consistently recruits a large fronto-parietal network in addition to subcortical and cerebellar regions. Although the primary motor cortex was not shown to be consistently activated, the MI network includes several regions which are known to play a role during actual motor execution. The body part involved in the movements, the modality of MI and the nature of the MI tasks used all seem to influence the consistency of activation within the general MI network. In addition to providing the first quantitative cortical map of MI, we highlight methodological issues that should be addressed in future research.
Goal: Sensorimotor-based brain-computer interfaces (BCIs) have achieved successful control of real and virtual devices in up to three dimensions; however, the traditional sensor-based paradigm limits ...the intuitive use of these systems. Many control signals for state-of-the-art BCIs involve imagining the movement of body parts that have little to do with the output command, revealing a cognitive disconnection between the user's intent and the action of the end effector. Therefore, there is a need to develop techniques that can identify with high spatial resolution the self-modulated neural activity reflective of the actions of a helpful output device. Methods: We extend previous EEG source imaging (ESI) work to decoding natural hand/wrist manipulations by applying a novel technique to classifying four complex motor imaginations of the right hand: flexion, extension, supination, and pronation. Results: We report an increase of up to 18.6% for individual task classification and 12.7% for overall classification using the proposed ESI approach over the traditional sensor-based method. Conclusion: ESI is able to enhance BCI performance of decoding complex right-hand motor imagery tasks. Significance: This study may lead to the development of BCI systems with naturalistic and intuitive motor imaginations, thus facilitating broad use of noninvasive BCIs.
In order to improve the performance of motor imagery brain–computer interface (BCI) based on deep learning algorithm, here, the authors propose an electrode channel combination method. Although motor ...imagery electro-encephalography (EEG) signals which contain different electrode channels on the scalp surface have an effect on the classification performance, the effect of different electrode channel combinations has not been systematically explored. With the two deep learning models the authors constructed, the authors list some different electrode channel combinations to classify the left fist and right fist motor imagery EEG signals. The results show that the more the number of channels in these combinations, the higher the classification accuracy. However, when the number of channels exceeds 11, the classification accuracy increases slowly, and the classification effect is rarely improved. Therefore, the authors obtain an optimal electrode channel combination to use the electrode channels efficiently and to improve the performance of motor imagery BCI based on deep learning algorithms.
Electroencephalography (EEG)-based brain-computer interfaces (BCIs), particularly those using motor-imagery (MI) data, have the potential to become groundbreaking technologies in both clinical and ...entertainment settings. MI data is generated when a subject imagines the movement of a limb. This paper reviews state-of-the-art signal processing techniques for MI EEG-based BCIs, with a particular focus on the feature extraction, feature selection and classification techniques used. It also summarizes the main applications of EEG-based BCIs, particularly those based on MI data, and finally presents a detailed discussion of the most prevalent challenges impeding the development and commercialization of EEG-based BCIs.
Electroencephalography (EEG) motor imagery (MI) signals have recently gained a lot of attention as these signals encode a person’s intent of performing an action. Researchers have used MI signals to ...help disabled persons, control devices such as wheelchairs and even for autonomous driving. Hence decoding these signals accurately is important for a Brain–Computer interface (BCI) system. But EEG decoding is a challenging task because of its complexity, dynamic nature and low signal to noise ratio. Convolution neural network (CNN) has shown that it can extract spatial and temporal features from EEG, but in order to learn the dynamic correlations present in MI signals, we need improved CNN models. CNN can extract good features with both shallow and deep models pointing to the fact that, at different levels relevant features can be extracted. Fusion of multiple CNN models has not been experimented for EEG data. In this work, we propose a multi-layer CNNs method for fusing CNNs with different characteristics and architectures to improve EEG MI classification accuracy. Our method utilizes different convolutional features to capture spatial and temporal features from raw EEG data. We demonstrate that our novel MCNN and CCNN fusion methods outperforms all the state-of-the-art machine learning and deep learning techniques for EEG classification. We have performed various experiments to evaluate the performance of the proposed CNN fusion method on public datasets. The proposed MCNN method achieves 75.7% and 95.4% on the BCI Competition IV-2a dataset and the High Gamma Dataset respectively. The proposed CCNN method based on autoencoder cross-encoding achieves more than 10% improvement for cross-subject EEG classification.
•Multi CNN models with different layers and filters for robust EEG feature extraction.•Fusion model for merging multiple CNNs for EEG classification.•Use of transfer learning and pretraining to further improve EEG decoding accuracy.•Autoencoders cross-subject feature reconstruction to achieve better results.
This study investigated the effects of numerical imagery alone on spinal motor nerve function and motor skills. The motor imagery of a force regulation task with pinch movements of the thumb and ...index finger can be divided into three types of imagery: numeric imagery, which is the image of digital numbers displayed in the pinch force value; muscle contraction imagery, which is the image of muscle contraction; and sensory imagery, which is the image of the sensation of pressing on the sensor. A questionnaire was administered as a pretest to nine healthy participants (mean age: 20.8 years) who had not previously used numeric imagery. During a resting trial, F waves were elicited from the abductor pollicis brevis muscle by stimulation of the median nerve on the non-dominant hand side. The F-wave was subsequently elicited during an imagery trial in which a numerical image was provided. The task of reaching 50% contraction strength was performed before and after the imagery task. Spinal motor nerve function did not differ between the resting and imagery tasks. Moreover, a difference in absolute error between the pinch task before and after the imagery task was absent. However, the participants with decreased motor accuracy were characterized by increased excitability of the spinal motor nerve function compared to those with improved motor accuracy.
This study investigated the effects of numerical imagery alone on spinal motor nerve function and motor skills. The motor imagery of a force regulation task with pinch movements of the thumb and ...index finger can be divided into three types of imagery: numeric imagery, which is the image of digital numbers displayed in the pinch force value; muscle contraction imagery, which is the image of muscle contraction; and sensory imagery, which is the image of the sensation of pressing on the sensor. A questionnaire was administered as a pretest to nine healthy participants (mean age: 20.8 years) who had not previously used numeric imagery. During a resting trial, F waves were elicited from the abductor pollicis brevis muscle by stimulation of the median nerve on the non-dominant hand side. The F-wave was subsequently elicited during an imagery trial in which a numerical image was provided. The task of reaching 50% contraction strength was performed before and after the imagery task. Spinal motor nerve function did not differ between the resting and imagery tasks. Moreover, a difference in absolute error between the pinch task before and after the imagery task was absent. However, the participants with decreased motor accuracy were characterized by increased excitability of the spinal motor nerve function compared to those with improved motor accuracy.
The availability of large and varied Electroencephalogram (EEG) datasets, rapidly advances and inventions in deep learning techniques, and highly powerful and diversified computing systems have all ...permitted to easily analyzing those datasets and discovering vital information within. However, the classification process of EEG signals and discovering vital information should be robust, automatic, and with high accuracy. Motor Imagery (MI) EEG has attracted us due to its significant applications in daily life.
This paper attempts to achieve those goals throughout a systematic review of the state-of-the-art studies within this field of research. The process began by intensely surfing the well-known specialized digital libraries and, as a result, 40 related papers were gathered. The papers were scrutinized upon multiple noteworthy technical issues, among them deep neural network architecture, input formulation, number of MI EEG tasks, and frequency range of interest.
Deep neural networks build robust and automated systems for the classification of MI EEG recordings by exploiting the whole input data throughout learning salient features. Specifically, convolutional neural networks (CNN) and hybrid-CNN (h-CNN) are the dominant architectures with high performance in comparison to public datasets with other types of architectures. The MI related datasets, input formulation, frequency ranges, and preprocessing and regularization methods were also reviewed.
This review gives the required preliminaries in developing MI EEG-based BCI systems. The review process of the published articles in the last five years aims to help in choosing the appropriate deep neural network architecture and other hyperparameters for developing those systems.
Brain complexity and non-stationary nature of electroencephalography (EEG) signal make considerable challenges for the accurate identification of different motor-imagery (MI) tasks in brain–computer ...interface (BCI). In the proposed Letter, a novel framework is proposed for the automated accurate classification of MI tasks. First, raw EEG signals are denoised with multiscale principal component analysis. Secondly, denoised signals are decomposed by empirical wavelet transform into different modes. Thirdly, the two-dimensional (2D) modelling of modes is introduced to identify the variations of different signals. Fourthly, a single geometrical feature name as, a summation of distance from each point relative to a coordinate centre is extracted from 2D modelling of modes. Finally, the extracted feature vectors are provided to the feedforward neural network and cascade forward neural networks for classification check. The proposed study achieved 95.3% of total classification accuracy with 100% outcome for subject with very small training samples, which is outperforming existing methods on the same database.