Shiyun Shao

Automatic EEG Artifact Removal: A Weighted Support Vector Machine Approach With Error Correction

An automatic electroencephalogram (EEG) artifact removal method is presented in this paper. Compared to past methods, it has two unique features: 1) a weighted version of support vector machine formulation that handles the inherent unbalanced nature of component classification and 2) the ability to accommodate structural information typically found in component classification. The advantages of the proposed method are demonstrated on real-life EEG recordings with comparisons made to several benchmark methods. Results show that the proposed method is preferable to the other methods in the context of artifact removal by achieving a better tradeoff between removing artifacts and preserving inherent brain activities. Qualitative evaluation of the reconstructed EEG epochs also demonstrates that after artifact removal inherent brain activities are largely preserved.

Frequency-domain EEG source analysis for acute tonic cold pain perception

OBJECTIVE To investigate electrocortical responses to tonic cold pain by frequency-domain electroencephalogram (EEG) source analysis, and to identify potential electrocortical indices of acute tonic pain. METHODS Scalp EEG data were recorded from 26 healthy subjects under tonic cold pain (CP) and no-pain control (NP) conditions. EEG power spectra and the standardized low-resolution brain electromagnetic tomography (sLORETA) localized EEG cortical sources were compared between the two conditions in five frequency bands: 1-4 Hz, 4-8 Hz, 8-12 Hz, 12-18 Hz and 18-30 Hz. RESULTS In line with the EEG power spectral results, the source power significantly differed between the CP and NP conditions in 8-12 Hz (CPNP) in extensive brain regions. Besides, there were also significantly different 4-8 Hz and 12-18 Hz source activities between the two conditions. Among the significant source activities, the left medial frontal and left superior frontal 4-8 Hz activities, the anterior cingulate 8-12 Hz activity and the posterior cingulate 12-18 Hz activity showed significant negative correlations with subjective pain ratings. CONCLUSIONS The brains perception of tonic cold pain was characterized by cortical source power changes across different frequency bands in multiple brain regions. Oscillatory activities that significantly correlated with subjective pain ratings were found in the prefrontal and cingulate regions. SIGNIFICANCE These findings may offer useful measures for objective pain assessment and provide a basis for pain treatment by modulation of neural oscillations at specific frequencies in specific brain regions.

Effect of pain perception on the heartbeat evoked potential

OBJECTIVE To investigate the effect of acute tonic pain on the heartbeat-evoked potential (HEP) and to test whether or not pain perception can be reflected by the HEP. METHODS Simultaneous electroencephalogram (EEG) and electrocardiogram (ECG) were recorded from 21 healthy young adults in three conditions: passive no-task control, no-pain control and cold pain. The HEP was obtained by using ECG R-peaks as event triggers. RESULTS Prominent HEP deflection was observed in both control conditions mainly over the frontal and central locations, while it was significantly suppressed in the cold pain condition over the right-frontal, right-central and midline locations. A comparison of the data in the first and last 5 min of cold pain condition showed that lower subjective pain ratings were accompanied by higher HEP magnitudes. A correlation analysis showed that the mean HEP magnitude over the midline locations was significantly negatively correlated with subjective pain ratings. CONCLUSIONS Cold pain induces significant suppression of the HEP across a number of scalp locations, and the suppression is correlated with self-report of pain. SIGNIFICANCE The HEP has the potential to serve as an alternative pain measure.

Common Spatio-Temporal Pattern for Single-Trial Detection of Event-Related Potential in Rapid Serial Visual Presentation Triage

Searching for target images in large volume imagery is a challenging problem and the rapid serial visual presentation (RSVP) triage is potentially a promising solution to the problem. RSVP triage is essentially a cortically-coupled computer vision technique that relies on single-trial detection of event-related potentials (ERP). In RSVP triage, images are shown to a subject in a rapid serial sequence. When a target image is seen by the subject, unique ERP characterized by P300 are elicited. Thus, in RSVP triage, accurate detection of such distinct ERP allows for fast searching of target images in large volume imagery. The accuracy of the distinct ERP detection in RSVP triage depends on the feature extraction method, for which the common spatial pattern analysis (CSP) was used with limited success. This paper presents a novel feature extraction method, termed common spatio-temporal pattern (CSTP), which is critical for robust single-trial detection of ERP. Unlike the conventional CSP, whereby only spatial patterns of ERP are considered, the present proposed method exploits spatial and temporal patterns of ERP separately, providing complementary spatial and temporal features for high accurate single-trial ERP detection. Numerical study using data collected from 20 subjects in RSVP triage experiments demonstrates that the proposed method offers significant performance improvement over the conventional CSP method (corrected p -value <; 0.05, Pearson r=0.64) and other competing methods in the literature. This paper further shows that the main idea of CSTP can be easily applied to other methods.

Automatic identification and removal of artifacts in EEG using a probabilistic multi-class SVM approach with error correction

A novel electroencephalogram (EEG) artifact removal method is presented in this paper. The proposed method combines a probabilistic multi-class Support Vector Machine (SVM) and an error correction algorithm for component classification, where i) the probabilistic multi-class SVM is modified to properly handle the unbalanced nature of component classification and ii) the error correction algorithm is used to accommodate the structural information of the learning problem. The proposed component classifier was tested on real-life EEG data and it significantly outperformed the standard SVM used in the literature. A qualitative evaluation on the reconstructed EEG shows that the proposed artifact removal method greatly reduced the amount of artifacts while well preserving brain activities in almost all EEG epochs.

A spatio-temporal filtering approach to denoising of single-trial ERP in rapid image triage.

Conventional search for images containing points of interest (POI) in large-volume imagery is costly and sometimes even infeasible. The rapid image triage (RIT) system which is a human cognition guided computer vision technique is potentially a promising solution to the problem. In the RIT procedure, images are sequentially presented to a subject at a high speed. At the instant of observing a POI image, unique POI event-related potentials (ERP) characterized by P300 will be elicited and measured on the scalp. With accurate single-trial detection of such unique ERP, RIT can differentiate POI images from non-POI images. However, like other brain-computer interface systems relying on single-trial detection, RIT suffers from the low signal-to-noise ratio (SNR) of the single-trial ERP. This paper presents a spatio-temporal filtering approach tailored for the denoising of single-trial ERP for RIT. The proposed approach is essentially a non-uniformly delayed spatial Gaussian filter that attempts to suppress the non-event related background electroencephalogram (EEG) and other noises without significantly attenuating the useful ERP signals. The efficacy of the proposed approach is illustrated by both simulation tests and real RIT experiments. In particular, the real RIT experiments on 20 subjects show a statistically significant and meaningful average decrease of 9.8% in RIT classification error rate, compared to that without the proposed approach.

A bilinear feature extraction method for rapid serial visual presentation triage

Searching for target objects in large volume imagery is a challenging problem, and the rapid serial visual presentation (RSVP) triage based on the detection of event-related potentials (ERP) is potentially a promising solution to the problem. Due to the fact that ERP elicited by targets and those by non-targets differ not only on spatial patterns but temporal patterns, this paper proposes a feature extraction method namely bilinear common spatial pattern (BCSP), which is designed to capture discriminative spatio-temporal features of ERP for triage classification. The proposed method extends common spatial pattern (CSP) by incorporating the core idea of bilinear discriminant analysis (BDA) into it. Specifically, in addition to the spatial filters which CSP also looks for, BCSP acquires the temporal filters for learning the temporal patterns of ERP. Both the spatial filters and temporal filters are obtained by using the same Ramosers technique, but in an iterative manner. With discriminative temporal information involved, BCSP has manifested remarkable advantages in RSVP triage experiments, as demonstrated by a significant increase of 11.2% in average classification accuracy in comparison with CSP, with p < 0.001 in paired t-test.

Heartbeat Evoked Potential: A Neural Correlate of Pain Perception?

The present study examined the correlation between pain perception and the cardiac-cycle related brain evoked potential, termed the heartbeat-evoked potential (HEP). Electroencephalogram (EEG) and Lead-II electrocardiogram (ECG) were simultaneously recorded from 12 subjects. Prominent HEP was observed mainly over frontal-central-parietal regions in both no-task control and no-pain control conditions, while it was largely suppressed in cold pain condition elicited by hand immersion in 10oC cold water. The suppression of HEP in cold pain condition implies that the HEP could represent a neural correlate of pain perception.