KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Author: search.filters.author.Thang, Le Quoc

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Regularizing multi-bands Common Spatial Patterns (RMCSP): A data processing method for brain-computer interface
    (2015-05-13)
    Thang, Le Quoc
    ;
    Temiyasathit, Chivalai
    In this paper, we propose a novel approach which is called the Regularizing Multi-bands Common Spatial Patterns (RMCSP) that particularly used for processing motor-imagery based Electroencephalography (EEG) data in Brain-computer Interface (BCI). The usage of BCI is severely limited due to the inconvenience of large number of channels used in recording devices. Moreover, Common Spatial Patterns (CSP) is a very well-known algorithm for its efficiency, but it just can extract the spatial information of the brain signals. To address these issues, we introduce the RMCSP method that exploits data in spectral, temporal and spatial domains in order to increase the classification accuracy in BCI. In addition, RMCSP is designed to handle EEG with small number of channels. To verify the efficacy of our approach, we rigorously tested the performances of the method in 17 subjects, from BCI competition datasets, in both two-class and four-class problems. Results show that RMCSP approach can outperform normal CSP method by nearly 10% in terms of median classification accuracy. It also enables us to significantly reduce the number of channels used in the datasets without decreasing the performances of the subjects.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Increase performance of four-class classification for motor-imagery based brain-computer interface
    (2014-01-01)
    Thang, Le Quoc
    ;
    Temiyasathit, Chivalai
    Brain computer interface (BCI) is a system that provide a direct communication between human brain and external devices. BCIs which based on mental tasks of users are widely used for disabled or paralyzed patients, in order to help their mobility. Preprocessing techniques have been extensively developed to increase the signal-to-noise ratio and spatial distribution of the signals. Common Spatial Pattern (CSP) has shown to be a robust and effective method for processing Electroencephalogram (EEG) data. However, the results of CSP filter are still far from being completely explored. CSP was originally designed for two-class problem despite the fact that a practical application of Motor-imagery (MI) based BCI contains numbers of activities. It is necessary to design the classification algorithm which applicable to more than two-class problem. In this paper we investigate the performance of CSP by selecting optimal time slice and components for training CSP filters in four-class BCI by separating the four-class problem into multiple binary classifications. Our method is verified in the testing phase with four different types of classification approaches which are linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), linear support vector machines (LSVM), and support vector machines with radial basis function kernel (RBF-SVM). The result showed that, under the optimal time slice and components, the classification accuracy reach 78.82% for the best untrained subject in this dataset. © 2014 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Investigation of regularization theory for four-class classification in brain-computer interface
    (2014-01-01)
    Thang, Le Quoc
    ;
    Temiyasathit, Chivalai
    Common spatial patterns (CSP) is one of the most prevalent feature extraction approaches that has been used in Brain-computer interfaces (BCI) due to its simplicity and efficiency. Nevertheless, CSP suffers from the problems of sensitivity to noise and overfitting. To overcome these issues, the regularized CSP (RCSP) has been proposed recently. In addition, CSP was originally designed for two-class classification. However, a practical BCI usually needs four-class commands to be able to operate. Thus, there is a high demand for increasing the performance of multi-class BCI. In this paper, we provide a complete study of classification accuracy in multi-class BCI using regularization theory, and compare it with the standard CSP to determine the suitable method for feature extraction in BCI learning. Besides CSP, linear discriminant analysis (LDA) has shown its robust and widespread use for machine learning in BCI. LDA estimates covariance matrices from extracted features. But for high-dimensional features with only a small amount of training data given, the estimation may become imprecise. In the attempt of clarifying the regularizing effects in BCI, this paper also provides the classification results of the regularized LDA (RLDA). The performance evaluation of this work was taken on data from 9 subjects, from BCI competition datasets. Results show that the combination of standard CSP and LDA has a slightly better accuracy than the regularizing methods.