ABSTRACT
Among various brain activity patterns, Steady State Visual Evoked Potential (SSVEP) based Brain Computer Inter-face (BCI) requires the least training time while carrying the fastest information transfer rate, making it highly suitable for deploying efficient self-paced BCI systems. In this study, we propose a Spectrum and Phase Adaptive CCA (SPACCA) for subject-and device-specific SSVEP-based BCI. Cross subject heterogeneity of spectrum distribution is taken into consideration to improve the prediction accuracy. We design a library of phase shifting reference signals to accommodate subjective and device-related response time lag. With the flexible reference signal generating approach, the system can be optimized for any specific flickering source, include LED, computer screen and mobile devices. We evaluated the performance of SPACCA using three sets of data that use LED, computer screen and mobile device (tablet) as stimuli sources respectively. The first two data sets are publicly available whereas the third data set is collected in our BCI lab. Across different data sets, SPACCA consistently performs better than the baseline, i.e. standard CCA approach. Statistical test to compare the overall results across three data sets yield a p-value of 1.66e-6, implying the improvement is significant.
Subject(s)
Brain-Computer Interfaces , Algorithms , Brain , Computer Systems , Electroencephalography , Evoked Potentials, Visual , Photic StimulationABSTRACT
Electrooculogram (EOG) artifact contamination is a common critical issue in general electroencephalogram (EEG) studies as well as in brain-computer interface (BCI) research. It is especially challenging when dedicated EOG channels are unavailable or when there are very few EEG channels available for independent component analysis based ocular artifact removal. It is even more challenging to avoid loss of the signal of interest during the artifact correction process, where the signal of interest can be multiple magnitudes weaker than the artifact. To address these issues, we propose a novel discriminative ocular artifact correction approach for feature learning in EEG analysis. Without extra ocular movement measurements, the artifact is extracted from raw EEG data, which is totally automatic and requires no visual inspection of artifacts. Then, artifact correction is optimized jointly with feature extraction by maximizing oscillatory correlations between trials from the same class and minimizing them between trials from different classes. We evaluate this approach on a real-world EEG dataset comprising 68 subjects performing cognitive tasks. The results showed that the approach is capable of not only suppressing the artifact components but also improving the discriminative power of a classifier with statistical significance. We also demonstrate that the proposed method addresses the confounding issues induced by ocular movements in cognitive EEG study.
Subject(s)
Artifacts , Brain/physiology , Cognition/physiology , Electroencephalography/methods , Electrooculography/methods , Pattern Recognition, Automated/methods , Algorithms , Discriminant Analysis , Eye Movements/physiology , Humans , Machine Learning , Reproducibility of Results , Sensitivity and SpecificityABSTRACT
This paper addresses the frame-based MR image reconstruction from undersampled k-space measurements by using a balanced â(1)-regularized approach. Analysis-based and synthesis-based approaches are two common methods in â(1)-regularized image restoration. They are equivalent under the orthogonal transform, but there exists a gap between them under redundant transform such as frame. Thus the third approach was developed to reduce the gap by penalizing the distance between the representation vector and the canonical frame coefficient of the estimated image, this balanced approach bridges the synthesis-based and analysis-based approaches and balances the fidelity, sparsity and smoothness of the solution. These frame-based approaches have been studied and compared for optical image restoration over the last few years. In this paper, we further study and compare these three approaches for the compressed sensing MR image reconstruction under redundant frame domain. These â(1)-regularized optimization problems are solved by using a variable splitting strategy and the classical alternating direction method of multiplier (ADMM). Numerical simulation results show that the balanced approach can reduce the gap between the analysis-based and synthesis-based approaches and are even better than these two approaches under our experimental conditions.
Subject(s)
Image Interpretation, Computer-Assisted/methods , Image Processing, Computer-Assisted , Magnetic Resonance Imaging , Algorithms , Models, TheoreticalABSTRACT
Falling asleep during driving is a serious problem that has resulted in fatal accidents worldwide. Thus, there is a need to detect driver drowsiness to counter it. This study analyzes the changes in the electroencephalography (EEG) collected from 4 subjects driving under monotonous road conditions using a driving simulator. The drowsiness level of the subjects is inferred from the time taken to react to events. The results from the analysis of the reaction time shows that drowsiness occurs in cycles, which correspond to short sleep cycles known as `microsleeps'. The results from a time-frequency analysis of the four frequency bands' power reveals differences between trials with fast and slow reaction times; greater beta band power is present in all subjects, greater alpha power in 2 subjects, greater theta power in 2 subjects, and greater delta power in 3 subjects, for fast reaction trials. Overall, this study shows that reaction time can be used to infer the drowsiness, and subject-specific changes in the EEG band power may be used to infer drowsiness. Thus the study shows a promising prospect of developing Brain-Computer Interface to detect driver drowsiness.
Subject(s)
Sleep Stages , Automobile Driving , Brain-Computer Interfaces , Electroencephalography , Humans , Reaction TimeABSTRACT
We developed an EEG- and audio-based sleep sensing and enhancing system, called iSleep (interactive Sleep enhancement apparatus). The system adopts a closed-loop approach which optimizes the audio recording selection based on user's sleep status detected through our online EEG computing algorithm. The iSleep prototype comprises two major parts: 1) a sleeping mask integrated with a single channel EEG electrode and amplifier, a pair of stereo earphones and a microcontroller with wireless circuit for control and data streaming; 2) a mobile app to receive EEG signals for online sleep monitoring and audio playback control. In this study we attempt to validate our hypothesis that appropriate audio stimulation in relation to brain state can induce faster onset of sleep and improve the quality of a nap. We conduct experiments on 28 healthy subjects, each undergoing two nap sessions - one with a quiet background and one with our audio-stimulation. We compare the time-to-sleep in both sessions between two groups of subjects, e.g., fast and slow sleep onset groups. The p-value obtained from Wilcoxon Signed Rank Test is 1.22e-04 for slow onset group, which demonstrates that iSleep can significantly reduce the time-to-sleep for people with difficulty in falling sleep.
Subject(s)
Sleep , Acoustic Stimulation , Algorithms , Amplifiers, Electronic , Brain , Electroencephalography , HumansABSTRACT
To address the nonstationarity issue in EEG-based brain computer interface (BCI), the computational model trained using the training data needs to adapt to the data from the test sessions. In this paper, we propose a novel adaptation approach based on the divergence framework. Cross-session changes can be taken into consideration by searching the discriminative subspaces for test data on the manifold of orthogonal matrices in a semi-supervised manner. Subsequently, the feature space becomes more consistent across sessions and classifiers performance can be enhanced. Experimental results show that the proposed adaptation method yields improvements in classification performance.
Subject(s)
Brain-Computer Interfaces , Electroencephalography/methods , Imagery, Psychotherapy , Motor Skills/physiology , Adaptation, Physiological , Algorithms , Calibration , Computer Simulation , Humans , Models, Statistical , Reproducibility of Results , Signal Processing, Computer-AssistedABSTRACT
Several functional neuroimaging studies had been performed to explore the sensorimotor function for motor imagery and passive movement, but there is scanty work that investigated the cortical activation pattern for passive movement using functional Near-Infrared Spectroscopy (fNIRS). This study investigated the cortical activation pattern from fNIRS data of 8 healthy subjects performing motor imagery and passive movement tasks using a Haptic Knob robot. Group averaged contrasts were defined as motor imagery versus idle and passive movement versus idle. The cortical activations for motor imagery appeared on the contralateral sensorimotor area, whereas the cortical activations for passive movement appeared on both contralateral and ipsilateral sensorimotor area. This result suggests that the performance of passive movement has a wider cortical activation compared to the performance of motor imagery.