Hyohyeong Kang

Composite Common Spatial Pattern for Subject-to-Subject Transfer

Common spatial pattern (CSP) is a popular feature extraction method for electroencephalogram (EEG) classification. Most of existing CSP-based methods exploit covariance matrices on a subject-by-subject basis so that inter-subject information is neglected. In this paper we present modifications of CSP for subject-to-subject transfer, where we exploit a linear combination of covariance matrices of subjects in consideration. We develop two methods to determine a composite covariance matrix that is a weighted sum of covariance matrices involving subjects, leading to composite CSP. Numerical experiments on dataset IVa in BCI competition III confirm that our composite CSP methods improve classification performance over the standard CSP (on a subject-by-subject basis), especially in the case of subjects with fewer number of training samples.

A hybrid NIRS-EEG system for self-paced brain computer interface with online motor imagery

BACKGROUND For a self-paced motor imagery based brain-computer interface (BCI), the system should be able to recognize the occurrence of a motor imagery, as well as the type of the motor imagery. However, because of the difficulty of detecting the occurrence of a motor imagery, general motor imagery based BCI studies have been focusing on the cued motor imagery paradigm. NEW METHOD In this paper, we present a novel hybrid BCI system that uses near infrared spectroscopy (NIRS) and electroencephalography (EEG) systems together to achieve online self-paced motor imagery based BCI. We designed a unique sensor frame that records NIRS and EEG simultaneously for the realization of our system. Based on this hybrid system, we proposed a novel analysis method that detects the occurrence of a motor imagery with the NIRS system, and classifies its type with the EEG system. RESULTS An online experiment demonstrated that our hybrid system had a true positive rate of about 88%, a false positive rate of 7% with an average response time of 10.36 s. COMPARISON WITH EXISTING METHOD(S) As far as we know, there is no report that explored hemodynamic brain switch for self-paced motor imagery based BCI with hybrid EEG and NIRS system. CONCLUSIONS From our experimental results, our hybrid system showed enough reliability for using in a practical self-paced motor imagery based BCI.

Bayesian common spatial patterns for multi-subject EEG classification

Multi-subject electroencephalography (EEG) classification involves algorithm development for automatically categorizing brain waves measured from multiple subjects who undergo the same mental task. Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative feature extraction method for EEG classification. Models in CSP or PCSP are trained on a subject-by-subject basis so that inter-subject information is neglected. In the case of multi-subject EEG classification, however, it is desirable to capture inter-subject relatedness in learning a model. In this paper we present a nonparametric Bayesian model for a multi-subject extension of PCSP where subject relatedness is captured by assuming that spatial patterns across subjects share a latent subspace. Spatial patterns and the shared latent subspace are jointly learned by variational inference. We use an infinite latent feature model to automatically infer the dimension of the shared latent subspace, placing Indian Buffet process (IBP) priors on our model. Numerical experiments on BCI competition III IVa and IV 2a dataset demonstrate the high performance of our method, compared to PCSP and existing Bayesian multi-task CSP models.

Bayesian Multi-task Learning for Common Spatial Patterns

Common spatial pattern (CSP) is a widely-used feature extraction method for electroencephalogram (EEG)classification and corresponding probabilistic models were recently developed, adopting a linear generative model for each class. These models are trained on a subject-by-subject basis so that inter-subject information is neglected. Moreover when only a few training samples are available for each subject, the performance is degraded. In this paper we employ Bayesianmulti-task learning so that subject-to-subject information is transferred in learning the model for a subject of interest. We present two probabilistic models where precision parameters of multivariate or matrix-variate Gaussian prior for the dictionary are shared across subjects. Numerical experiments on the BCI competition IV 2a dataset confirm that our methods improve classification performance over the standard CSP (on a subject-by-subject basis), especially in the case of subjects with fewer number of training samples.

Bayesian common spatial patterns with Dirichlet process priors for multi-subject EEG classification

Multi-subject electroencephalography (EEG) classification involves the categorization of brain waves measured from multiple subjects, each of whom undergoes the same mental task. Common spatial patterns (CSP) or probabilistic CSP (PCSP) are widely used for extracting discriminative features from EEG, although they are trained on a subject-by-subject basis and inter-subject information is neglected. Moreover, the performance is degraded when only a few training samples are available for each subject. In this paper, we present a method for Bayesian CSP with Dirichlet process (DP) priors, where spatial patterns (corresponding to basis vectors) are simultaneously learned and clustered across subjects using variational Bayesian inference, which facilitates a flexible mixture model where the number of components are also learned. Spatial patterns in the same cluster share the hyperparameters of their prior distributions, which means information transfer is facilitated among subjects with similar spatial patterns. Numerical experiments using the BCI competition IV 2a dataset demonstrated the high performance of our method, compared with existing PCSP and Bayesian CSP methods with a single prior distribution.

Bayesian multi-subject common spatial patterns with Indian Buffet process priors

Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative feature extraction method for electroencephalography (EEG) classification. Models in CSP or PCSP are trained on a subject-by-subject basis so that inter-subject information is not used. In the case of multi-subject EEG classification where brain waves recorded from multiple subjects who undergo the same mental task are available, it is desirable to capture inter-subject relatedness in learning a model. In this paper we present a nonparametric Bayesian model for a multi-subject extension of CSP where subject relatedness is captured by assuming that spatial patterns across subjects share a latent subspace. Spatial patterns and the shared latent subspace are jointly learned by variational inference. We use an infinite latent feature model to automatically infer the dimension of the shared latent subspace, placing Indian Buffet process (IBP) priors on our model. Numerical experiments on BCI competition IV 2a dataset demonstrate the high performance of our method, compared to PCSP and existing Bayesian multi-task CSP models.

Bayesian common spatial patterns

Common spatial patterns (CSP) or its probabilistic counterpart, probabilistic CSP (PCSP), is a popular discriminative feature extraction method for automatically classifying electroencephalography (EEG) brain waves. Models for CSP or PCSP are trained on a subject-by-subject basis, so inter-subject information, which might be available when brain waves are measured from multiple subjects who undergo the same mental task, is neglected. In this paper we present a brief overview of our recent work on how Bayesian multi-task learning is applied to multi-subject EEG classification, treating subjects as tasks to capture inter-subject relatedness in Bayesian treatment of PCSP.