Jia Hui Teo’s research while affiliated with University of Science Malaysia and other places

A single-channel electroencephalography (EEG) device, despite being widely accepted due to convenience, ease of deployment and suitability for use in complex environments, typically poses a great challenge for reactive brain-computer interface (BCI) applications particularly when a continuous command from users is desired to run a motorized actuator with different speed profiles. In this study, a combination of an inconspicuous visual stimulus and voluntary eyeblinks along with a machine learning-based decoder is considered as a new reactive BCI paradigm to increase the degree of freedom and minimize mismatches between the intended dynamic command and transmitted control signal. The proposed decoder is constructed based on Gaussian Process model (GPM) which is a nonparametric Bayesian approach that has the advantages of being able to operate on small datasets and providing measurements of uncertainty on predictions. To evaluate the effectiveness of the proposed method, the GPM is compared against other competitive techniques which include k-Nearest Neighbors, linear discriminant analysis, support vector machine, ensemble learning and neural network. Results demonstrate that a significant improvement can be achieved via the GPM approach with average accuracy reaching over 96% and mean absolute error of no greater than 0.8 cm/s. In addition, the analysis reveals that while the performances of other existing methods deteriorate with a certain type of stimulus due to signal drifts resulting from the voluntary eyeblinks, the proposed GPM exhibits consistent performance across all stimuli considered, thereby manifesting its generalization capability and making it a more suitable option for dynamic commands with a single-channel EEG-controlled actuator.

In this study, inconspicuous visual stimuli with hidden targets are considered as a new paradigm for reactive brain-computer interface (BCI) applications suitable for actuating a motorized system with a dynamic command from user. To drive the motor’s control signal level as close as possible to the targeted dynamic command via wireless transmission, an embeddable intelligent control scheme is introduced to improve the overall electroencephalography (EEG)-based decoding strategy of the BCI system. The proposed technique which can induce motivated attention only requires a single EEG channel, and the intelligent control scheme is constructed with a decoder consisting of a multilayer perceptron (MLP) neural network and a recursive digital Boxcar filter to suppress the influence of noise and ocular artifacts that are typically caused by user’s involuntary movements. Results from thirty subjects showed that the predictive ability of the BCI system was significantly improved via the proposed decoder compared to the performance of MLP models alone and those with low pass and Kalman filters which were two existing methods commonly used to alleviate the aforementioned perturbations in real-time applications. The BCI’s predictive ability could also be further enhanced by selecting a suitable stimulus to construct a generic MLP model for each gender due to notable performance disparities between male and female groups. The findings of this study will have the potential to increase the degree of freedom in reactive BCI applications particularly when embedded control systems with multiple actuator speeds or accelerations are desired such as those used to control mobile robotics.