Yaozhang Pan

Resting state changes in functional connectivity correlate with movement recovery for BCI and robot-assisted upper-extremity training after stroke.

Background. Robot-assisted training may improve motor function in some hemiparetic patients after stroke, but no physiological predictor of rehabilitation progress is reliable. Resting state functional magnetic resonance imaging (RS-fMRI) may serve as a method to assess and predict changes in the motor network. Objective. The authors examined the effects of upper-extremity robot-assisted rehabilitation (MANUS) versus an electroencephalography-based brain computer interface setup with motor imagery (MI EEG-BCI) and compared pretreatment and posttreatment RS-fMRI. Methods. In all, 9 adults with upper-extremity paresis were trained for 4 weeks with a MANUS shoulder-elbow robotic rehabilitation paradigm. In 3 participants, robot-assisted movement began if no voluntary movement was initiated within 2 s. In 6 participants, MI-BCI–based movement was initiated if motor imagery was detected. RS-fMRI and Fugl-Meyer (FM) upper-extremity motor score were assessed before and after training. Results. The individual gain in FM scores over 12 weeks could be predicted from functional connectivity changes (FCCs) based on the pre-post differences in RS-fMRI measurements. Both the FM gain and FCC were numerically higher in the MI-BCI group. Increases in FC of the supplementary motor area, the contralesional and ipsilesional motor cortex, and parts of the visuospatial system with mostly association cortex regions and the cerebellum correlated with individual upper-extremity function improvement. Conclusion. FCC may predict the steepness of individual motor gains. Future training could therefore focus on directly inducing these beneficial increases in FC. Evaluation of the treatment groups suggests that MI is a potential facilitator of such neuroplasticity.

Quantifying Limb Movements in Epileptic Seizures Through Color-Based Video Analysis

This paper proposes a color-based video analytic system for quantifying limb movements in epileptic seizure monitoring. The system utilizes colored pyjamas to facilitate limb segmentation and tracking. Thus, it is unobtrusive and requires no sensor/marker attached to patients body. We employ Gaussian mixture models in background/foreground modeling and detect limbs through a coarse-to-fine paradigm with graph-cut-based segmentation. Next, we estimate limb parameters with domain knowledge guidance and extract displacement and oscillation features from movement trajectories for seizure detection/analysis. We report studies on sequences captured in an epilepsy monitoring unit. Experimental evaluations show that the proposed system has achieved comparable performance to EEG-based systems in detecting motor seizures.

Asymmetric Spatial Pattern for EEG-based emotion detection

Feature extraction has been a crucial and challenging task for EEG-based BCI applications mainly due to the problems of high-dimensionality and high noise level of EEG signals. In this paper we developed a novel feature extraction algorithm for EEG-based emotion detection problem. The proposed algorithm is derived from viewing EEG signals as the activation/deactivation of sources specific to the brain activities of interest. For binary classification problem, to be more specific, we consider the EEG signals for the two types of brain activities as characterized by the activation/deactivation of two discriminatory sources in the brain, with one source activated and the other one deactivated for one particular type of brain activities. The proposed algorithm, termed Asymmetric Spatial Pattern (ASP), extracts pairs of spatial filters, with each filter corresponding to only one of the two sources. The idea of ASP is neurologically plausible for certain situations. For example, according to the valence hypothesis of emotion, the left hemisphere is more activated in positive emotions and the right hemisphere is more activated in negative emotions. The effectiveness of the proposed algorithm is confirmed by application to real data for two types of EEG-based emotion detection problems: arousal detection (strong v.s. calm), and valence detection (positive v.s. negative). Experimental results on the real data also show that some of the asymmetric spatial patterns by ASP are consistent with the current neurophysiological findings on brain emotion processing.

Discriminative learning of propagation and spatial pattern for motor imagery eeg analysis

Effective learning and recovery of relevant source brain activity patterns is a major challenge to brain-computer interface using scalp EEG. Various spatial filtering solutions have been developed. Most current methods estimate an instantaneous demixing with the assumption of uncorrelatedness of the source signals. However, recent evidence in neuroscience suggests that multiple brain regions cooperate, especially during motor imagery, a major modality of brain activity for brain-computer interface. In this sense, methods that assume uncorrelatedness of the sources become inaccurate. Therefore, we are promoting a new methodology that considers both volume conduction effect and signal propagation between multiple brain regions. Specifically, we propose a novel discriminative algorithm for joint learning of propagation and spatial pattern with an iterative optimization solution. To validate the new methodology, we conduct experiments involving 16 healthy subjects and perform numerical analysis of the proposed algorithm for EEG classification in motor imagery brain-computer interface. Results from extensive analysis validate the effectiveness of the new methodology with high statistical significance.

Common frequency pattern for music preference identification using frontal EEG

In this paper, we investigate the use of 2-channel frontal EEG signal to classify two music preferences: like and dislike. The hypothesis for this investigation is that the frontal EEG signal contains sufficient information on the mental state of a subject for discriminating the preference of music of the subject. An experiment is performed to collect 2-channel frontal EEG data from 12 subjects by playing various types of music pieces and asking whether they like or dislike the music in order to obtain the true labels of their music preferences. We then propose a frequency band optimization method called common frequency pattern (CFP) for feature extraction and Linear SVM for classification to identify the music preference of the subjects from the 2-channel frontal EEG. The results of using the proposed method yield an average classification accuracy of 74.77% for a trial length of 30 s over the 12 subjects. Hence the experimental results show evidence that frontal EEG signal contains sufficient information to discriminate preference of music. Furthermore, the frequency band optimization results indicate that gamma band is essential for EEG-based music preference identification.

Seizure detection based on spatiotemporal correlation and frequency regularity of scalp EEG

In this paper, a robust seizure detection system using scalp EEG signal is presented. Two most important and obvious characteristics of seizure EEG, signal variance, and frequency synchronization are carefully chosen as seizure detection indexes. To extract the representation of EEG variance, a spatiotemporal correlation structure is constructed based on space-delay covariance matrices with multi-scale temporal delay. The frequency synchronization of EEG is represented by a regularity index derived from wavelet packet transform. The extracted representations are combined to form a high-dimensional feature vector with redundant information. In order to reduce the redundancy, feature selection is performed using mutual information (MI) based on best individual features. The optimized set of features form a more compact feature vector for each 2-s epoch of multi-channel EEG. Feature vectors are then classified into ictal or interictal class using a linear support vector machine (SVM). To evaluate the proposed seizure detection system, unbiased leave-one-session-out cross-validation using clinical routine EEG from 7 patients are performed in experiments. The proposed method obtains average accuracy of 91.44% and average latency of 6.82 s, which outperforms other 7 commonly used methods. It is also demonstrated that the performance of our method is more robust since the standard deviation of results among patients is smaller than other methods.

Cluster impurity and forward-backward error maximization-based active learning for EEG signals classification

This paper investigates how to apply active learning for the classification of motor imagery electroencephalography (EEG) signals to boost the performance for small training size. A new criterion is proposed to select the most representative and informative queries. The candidates are firstly chosen from the samples close to the center of the cluster that has the highest impurity of classes. A predefined number of such candidates and classifiers are forwardly buffered. Subsequently, the query is chosen such that the buffered classifiers can backward maximize the classification errors on labeled data. Experimental results conducted on the BCI competition IV data set IVb show the superior performance of the proposed active learning scheme, which is on average 5.12% higher in accuracy than that of the passive method by choosing the training size from 28 to 112.

Joint spatial-temporal filter design for analysis of motor imagery EEG

This paper addresses the key issue of discriminative feature extraction of electroencephalogram (EEG) signals in brain-computer interfaces. Recent advances in neuroscience indicate that multiple brain regions can be activated during motor imagery. The signal propagation among the regions can give rise to spurious effects in identifying event-related desynchronization/synchronization for discriminative motor imagery detection in conventional feature extraction methods. Particularly, we propose that computational models which account for both signal propagation and volume conduction effects of the source neuronal activities can more accurately describe EEG during the specific brain activities and lead to more effective feature extraction. To this end, we devise a unified model for joint learning of signal propagation and spatial patterns. The preliminary results obtained with real-world motor imagery EEG data sets confirm that the new methodology can improve classification accuracy with statistical significance.

Connectivity pattern modeling of motor imagery EEG

In this paper, the functional connectivity network of motor imagery based on EEG is investigated to understand brain function during motor imagery. In particular, partial directed coherence and directed transfer function measurements are applied to multi-channel EEG data to find out event related connectivity pattern with the direction and strength. The t-test is applied to these connectivity measurements to compare the network between motor imagery and the rest state. The possible relationship between this connectivity pattern and subjects performances are discussed. Based on the Granger causality analysis, a feature extraction method is proposed to compensate for nonstationarity in data. By attenuating the time-lagged correlation, this feature extraction method based on the multi-variate autoregression model is proposed to reduce the effects of noises caused by time propagation. The validity of the proposed method is verified through experimental studies with a two-class dataset, and significant improvement in term of classification accuracy is achieved.

Prefrontal cortical activation during arithmetic processing differentiated by cultures: A preliminary fNIRS study

Understanding the neural basis of arithmetic processes could play an important role in improving mathematical education. This study investigates the prefrontal cortical activation among subjects from different cultural backgrounds while performing two difficulty levels of mental arithmetic tasks. The prefrontal cortical activation is measured using a high density 206 channels fNIRS. 8 healthy subjects, consisting of 5 Asians and 3 Europeans, are included in this study. NIRS-SPM is used to compute hemoglobin response changes and generate brain activation map based on two contrasts defined as Easy versus Rest and Hard versus Rest. Differences between the Asian group and the European group are found in both contrasts of Easy versus Rest and Hard versus Rest. The results suggest people with different cultural backgrounds engage different neural pathways during arithmetic processing.