scholarly journals Scale-Dependent Signal Identification in Low-Dimensional Subspace: Motor Imagery Task Classification

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Qingshan She ◽  
Haitao Gan ◽  
Yuliang Ma ◽  
Zhizeng Luo ◽  
Tom Potter ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Clustering Algorithm ◽  
Gaussian Mixture ◽  
Dimensional Subspace ◽  
Support Vector ◽  
Imagery Task ◽  
Common Spatial Pattern ◽  
Significant Information ◽  
Low Dimensional ◽  
Composite Data

Motor imagery electroencephalography (EEG) has been successfully used in locomotor rehabilitation programs. While the noise-assisted multivariate empirical mode decomposition (NA-MEMD) algorithm has been utilized to extract task-specific frequency bands from all channels in the same scale as the intrinsic mode functions (IMFs), identifying and extracting the specific IMFs that contain significant information remain difficult. In this paper, a novel method has been developed to identify the information-bearing components in a low-dimensional subspace without prior knowledge. Our method trains a Gaussian mixture model (GMM) of the composite data, which is comprised of the IMFs from both the original signal and noise, by employing kernel spectral regression to reduce the dimension of the composite data. The informative IMFs are then discriminated using a GMM clustering algorithm, the common spatial pattern (CSP) approach is exploited to extract the task-related features from the reconstructed signals, and a support vector machine (SVM) is applied to the extracted features to recognize the classes of EEG signals during different motor imagery tasks. The effectiveness of the proposed method has been verified by both computer simulations and motor imagery EEG datasets.

Speaker Identification in Total Variability Space

2013 ◽  
Vol 401-403 ◽  
pp. 1489-1492
Author(s):  
Qiang Li ◽  
Ming Bing Zhao ◽  
Yong Feng
Keyword(s):  
Speaker Identification ◽  
Gaussian Mixture ◽  
Dimensional Subspace ◽  
Identification System ◽  
Accurate Identification ◽  
Identification Rate ◽  
Total Variability ◽  
Rate Improvement ◽  
Low Dimensional ◽  
The Given

Gaussian Mixture Model-Universal Background Model based approaches have been popular used for speaker identification task. But in real complex environment the identification system performs too much worse than in laboratory, and the main reason is the mismatch of the training and testing channel and also the variability of the speaker himself. In this paper we introduce i-vector to the speaker identification system. In i-vector approach, a low dimensional subspace called total variability space is used to estimate both speaker and channel variability. Baum-Welch statistics are first computed over the given UBM to estimate the total variability. From the experiment results, we obtain 2.44% relative accurate identification rate improvement when using total variability space to compensate the mismatch of the variabilities from both the speaker and channel.

scholarly journals Sensorized Assessment of Dynamic Locomotor Imagery in People with Stroke and Healthy Subjects

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4545
Author(s):  
Daniela De Bartolo ◽  
Valeria Belluscio ◽  
Giuseppe Vannozzi ◽  
Giovanni Morone ◽  
Gabriella Antonucci ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Lower Limbs ◽  
Imagery Task ◽  
Experimental Conditions ◽  
Significant Information ◽  
Imagery Training ◽  
Mental Chronometry ◽  
Sinusoidal Waveform ◽  
Reaction Forces ◽  
Measurement Units

Dynamic motor imagery (dMI) is a motor imagery task associated with movements partially mimicking those mentally represented. As well as conventional motor imagery, dMI has been typically assessed by mental chronometry tasks. In this paper, an instrumented approach was proposed for quantifying the correspondence between upper and lower limb oscillatory movements performed on the spot during the dMI of walking vs. during actual walking. Magneto-inertial measurement units were used to measure limb swinging in three different groups: young adults, older adults and stroke patients. Participants were tested in four experimental conditions: (i) simple limb swinging; (ii) limb swinging while imagining to walk (dMI-task); (iii) mental chronometry task, without any movement (pure MI); (iv) actual level walking at comfortable speed. Limb swinging was characterized in terms of the angular velocity, frequency of oscillations and sinusoidal waveform. The dMI was effective at reproducing upper limb oscillations more similar to those occurring during walking for all the three groups, but some exceptions occurred for lower limbs. This finding could be related to the sensory feedback, stretch reflexes and ground reaction forces occurring for lower limbs and not for upper limbs during walking. In conclusion, the instrumented approach through wearable motion devices adds significant information to the current dMI approach, further supporting their applications in neurorehabilitation for monitoring imagery training protocols in patients with stroke.

scholarly journals Recognition of EEG Signal Motor Imagery Intention Based on Deep Multi-View Feature Learning

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3496
Author(s):  
Jiacan Xu ◽  
Hao Zheng ◽  
Jianhui Wang ◽  
Donglin Li ◽  
Xiaoke Fang
Keyword(s):  
Frequency Domain ◽  
Motor Imagery ◽  
Recognition Performance ◽  
Feature Learning ◽  
Feature Representation ◽  
Support Vector ◽  
Imagery Task ◽  
Learning Method ◽  
Eeg Signals ◽  
Time Frequency

Recognition of motor imagery intention is one of the hot current research focuses of brain-computer interface (BCI) studies. It can help patients with physical dyskinesia to convey their movement intentions. In recent years, breakthroughs have been made in the research on recognition of motor imagery task using deep learning, but if the important features related to motor imagery are ignored, it may lead to a decline in the recognition performance of the algorithm. This paper proposes a new deep multi-view feature learning method for the classification task of motor imagery electroencephalogram (EEG) signals. In order to obtain more representative motor imagery features in EEG signals, we introduced a multi-view feature representation based on the characteristics of EEG signals and the differences between different features. Different feature extraction methods were used to respectively extract the time domain, frequency domain, time-frequency domain and spatial features of EEG signals, so as to made them cooperate and complement. Then, the deep restricted Boltzmann machine (RBM) network improved by t-distributed stochastic neighbor embedding(t-SNE) was adopted to learn the multi-view features of EEG signals, so that the algorithm removed the feature redundancy while took into account the global characteristics in the multi-view feature sequence, reduced the dimension of the multi-visual features and enhanced the recognizability of the features. Finally, support vector machine (SVM) was chosen to classify deep multi-view features. Applying our proposed method to the BCI competition IV 2a dataset we obtained excellent classification results. The results show that the deep multi-view feature learning method further improved the classification accuracy of motor imagery tasks.

scholarly journals Relative Power Correlates With the Decoding Performance of Motor Imagery Both Across Time and Subjects

2021 ◽  
Vol 15 ◽  
Author(s):  
Qing Zhou ◽  
Jiafan Lin ◽  
Lin Yao ◽  
Yueming Wang ◽  
Yan Han ◽  
...  
Keyword(s):  
Motor Imagery ◽  
Supplementary Motor Area ◽  
Support Vector ◽  
Relative Power ◽  
Common Spatial Pattern ◽  
Neurophysiological Mechanism ◽  
Computer Interfaces ◽  
Performance Variation ◽  
Performance Variations ◽  
And Task

One of the most significant challenges in the application of brain-computer interfaces (BCI) is the large performance variation, which often occurs over time or across users. Recent evidence suggests that the physiological states may explain this performance variation in BCI, however, the underlying neurophysiological mechanism is unclear. In this study, we conducted a seven-session motor-imagery (MI) experiment on 20 healthy subjects to investigate the neurophysiological mechanism on the performance variation. The classification accuracy was calculated offline by common spatial pattern (CSP) and support vector machine (SVM) algorithms to measure the MI performance of each subject and session. Relative Power (RP) values from different rhythms and task stages were used to reflect the physiological states and their correlation with the BCI performance was investigated. Results showed that the alpha band RP from the supplementary motor area (SMA) within a few seconds before MI was positively correlated with performance. Besides, the changes of RP between task and pre-task stage from theta, alpha, and gamma band were also found to be correlated with performance both across time and subjects. These findings reveal a neurophysiological manifestation of the performance variations, and would further provide a way to improve the BCI performance.

scholarly journals Sparse Representation-Based Extreme Learning Machine for Motor Imagery EEG Classification

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Qingshan She ◽  
Kang Chen ◽  
Yuliang Ma ◽  
Thinh Nguyen ◽  
Yingchun Zhang
Keyword(s):  
Sparse Representation ◽  
Extreme Learning Machine ◽  
Motor Imagery ◽  
Vital Role ◽  
Superior Performance ◽  
Common Spatial Pattern ◽  
Significant Information ◽  
Feature Representations ◽  
Novel Approach ◽  
Learning Machine

Classification of motor imagery (MI) electroencephalogram (EEG) plays a vital role in brain-computer interface (BCI) systems. Recent research has shown that nonlinear classification algorithms perform better than their linear counterparts, but most of them cannot extract sufficient significant information which leads to a less efficient classification. In this paper, we propose a novel approach called FDDL-ELM, which combines the discriminative power of extreme learning machine (ELM) with the reconstruction capability of sparse representation. Firstly, the common spatial pattern (CSP) algorithm is adopted to perform spatial filtering on raw EEG data to enhance the task-related neural activity. Secondly, the Fisher discrimination criterion is employed to learn a structured dictionary and obtain sparse coding coefficients from the filtered data, and these discriminative coefficients are then used to acquire the reconstructed feature representations. Finally, a nonlinear classifier ELM is used to identify these features in different MI tasks. The proposed method is evaluated on 2-class Datasets IVa and IIIa of BCI Competition III and 4-class Dataset IIa of BCI Competition IV. Experimental results show that our method achieved superior performance than the other existing algorithms and yielded the accuracies of 80.68%, 87.54%, and 63.76% across all subjects in the above-mentioned three datasets, respectively.

scholarly journals COMPARISONS BETWEEN MOTOR AREA EEG AND ALL-CHANNELS EEG FOR TWO ALGORITHMS IN MOTOR IMAGERY TASK CLASSIFICATION

2014 ◽  
Vol 26 (03) ◽  
pp. 1450040 ◽  
Author(s):  
Siuly ◽  
Yan Li ◽  
Peng Wen
Keyword(s):  
Motor Imagery ◽  
Binary Logistic Regression ◽  
Classification Performance ◽  
Least Square ◽  
Motor Area ◽  
Support Vector ◽  
Imagery Task ◽  
Task Classification ◽  
Svm Algorithm ◽  
The Brain

This article reports on a comparative study to identify electroencephalography (EEG) signals during motor imagery (MI) for motor area EEG and all-channels EEG in the brain–computer interface (BCI) application. In this paper, we present two algorithms: CC-LS-SVM and CC-LR for MI tasks classification. The CC-LS-SVM algorithm combines the cross-correlation (CC) technique and the least square support vector machine (LS-SVM). The CC-LR algorithm assembles the CC technique and binary logistic regression (LR) model. These two algorithms are implemented on the motor area EEG and the all-channels EEG to investigate how well they perform and also to test which area EEG is better for the MI classification. These two algorithms are also compared with some existing methods which reveal their competitive performance during classification. Results on both datasets, IVa and IVb from BCI Competition III, show that the CC-LS-SVM algorithm performs better than the CC-LR algorithm on both the motor area EEG and the all-channels EEG. The results also demonstrate that the CC-LS-SVM algorithm performs much better for the all-channels EEG than for the motor area EEG. Furthermore, the LS-SVM-based approach can correctly identify the discriminative MI tasks, demonstrating the algorithm's superiority in classification performance over some existing methods.

scholarly journals The classification of motor imagery response: an accuracy enhancement through the ensemble of random subspace k-NN

2021 ◽  
Vol 7 ◽  
pp. e374
Author(s):  
Mamunur Rashid ◽  
Bifta Sama Bari ◽  
Md Jahid Hasan ◽  
Mohd Azraai Mohd Razman ◽  
Rabiu Muazu Musa ◽  
...  
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Motor Imagery ◽  
Communication Strategy ◽  
Support Vector ◽  
Random Subspace ◽  
Common Spatial Pattern ◽  
Feature Selection Technique ◽  
Linear Discriminant ◽  
Feature Dimension

Brain-computer interface (BCI) is a viable alternative communication strategy for patients of neurological disorders as it facilitates the translation of human intent into device commands. The performance of BCIs primarily depends on the efficacy of the feature extraction and feature selection techniques, as well as the classification algorithms employed. More often than not, high dimensional feature set contains redundant features that may degrade a given classifier’s performance. In the present investigation, an ensemble learning-based classification algorithm, namely random subspace k-nearest neighbour (k-NN) has been proposed to classify the motor imagery (MI) data. The common spatial pattern (CSP) has been applied to extract the features from the MI response, and the effectiveness of random forest (RF)-based feature selection algorithm has also been investigated. In order to evaluate the efficacy of the proposed method, an experimental study has been implemented using four publicly available MI dataset (BCI Competition III dataset 1 (data-1), dataset IIIA (data-2), dataset IVA (data-3) and BCI Competition IV dataset II (data-4)). It was shown that the ensemble-based random subspace k-NN approach achieved the superior classification accuracy (CA) of 99.21%, 93.19%, 93.57% and 90.32% for data-1, data-2, data-3 and data-4, respectively against other models evaluated, namely linear discriminant analysis, support vector machine, random forest, Naïve Bayes and the conventional k-NN. In comparison with other classification approaches reported in the recent studies, the proposed method enhanced the accuracy by 2.09% for data-1, 1.29% for data-2, 4.95% for data-3 and 5.71% for data-4, respectively. Moreover, it is worth highlighting that the RF feature selection technique employed in the present study was able to significantly reduce the feature dimension without compromising the overall CA. The outcome from the present study implies that the proposed method may significantly enhance the accuracy of MI data classification.

scholarly journals A Comprehensive sLORETA Study on the Contribution of Cortical Somatomotor Regions to Motor Imagery

2019 ◽  
Vol 9 (12) ◽  
pp. 372
Author(s):  
Mustafa Yazici ◽  
Mustafa Ulutas ◽  
Mukadder Okuyan
Keyword(s):  
Motor Imagery ◽  
Classification Performance ◽  
Support Vector ◽  
Problem Solution ◽  
Mu Rhythm ◽  
Eeg Signals ◽  
Common Spatial Pattern ◽  
Cortical Sources ◽  
Cortical Level ◽  
Source Signals

Brain–computer interface (BCI) is a technology used to convert brain signals to control external devices. Researchers have designed and built many interfaces and applications in the last couple of decades. BCI is used for prevention, detection, diagnosis, rehabilitation, and restoration in healthcare. EEG signals are analyzed in this paper to help paralyzed people in rehabilitation. The electroencephalogram (EEG) signals recorded from five healthy subjects are used in this study. The sensor level EEG signals are converted to source signals using the inverse problem solution. Then, the cortical sources are calculated using sLORETA methods at nine regions marked by a neurophysiologist. The features are extracted from cortical sources by using the common spatial pattern (CSP) method and classified by a support vector machine (SVM). Both the sensor and the computed cortical signals corresponding to motor imagery of the hand and foot are used to train the SVM algorithm. Then, the signals outside the training set are used to test the classification performance of the classifier. The 0.1–30 Hz and mu rhythm band-pass filtered activity is also analyzed for the EEG signals. The classification performance and recognition of the imagery improved up to 100% under some conditions for the cortical level. The cortical source signals at the regions contributing to motor commands are investigated and used to improve the classification of motor imagery.

scholarly journals Developing a Motor Imagery-Based Real-Time Asynchronous Hybrid BCI Controller for a Lower-Limb Exoskeleton

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7309
Author(s):  
Junhyuk Choi ◽  
Keun Tae Kim ◽  
Ji Hyeok Jeong ◽  
Laehyun Kim ◽  
Song Joo Lee ◽  
...  
Keyword(s):  
Real Time ◽  
Motor Imagery ◽  
Lower Limb ◽  
Neurological Disorders ◽  
Support Vector ◽  
Svm Classifier ◽  
Eeg Signals ◽  
Common Spatial Pattern ◽  
Lower Limb Exoskeleton ◽  
Electroencephalogram Eeg

This study aimed to develop an intuitive gait-related motor imagery (MI)-based hybrid brain-computer interface (BCI) controller for a lower-limb exoskeleton and investigate the feasibility of the controller under a practical scenario including stand-up, gait-forward, and sit-down. A filter bank common spatial pattern (FBCSP) and mutual information-based best individual feature (MIBIF) selection were used in the study to decode MI electroencephalogram (EEG) signals and extract a feature matrix as an input to the support vector machine (SVM) classifier. A successive eye-blink switch was sequentially combined with the EEG decoder in operating the lower-limb exoskeleton. Ten subjects demonstrated more than 80% accuracy in both offline (training) and online. All subjects successfully completed a gait task by wearing the lower-limb exoskeleton through the developed real-time BCI controller. The BCI controller achieved a time ratio of 1.45 compared with a manual smartwatch controller. The developed system can potentially be benefit people with neurological disorders who may have difficulties operating manual control.

Sign in / Sign up

Export Citation Format

Share Document