Toward a Model-Based Predictive Controller Design in Brain–Computer Interfaces

Abstract

A first step in designing a robust and optimal model-based predictive controller (MPC) for brain–computer interface (BCI) applications is presented in this article. An MPC has the potential to achieve improved BCI performance compared to the performance achieved by current ad hoc, nonmodel-based filter applications. The parameters in designing the controller were extracted as model-based features from motor imagery task-related human scalp electroencephalography. Although the parameters can be generated from any model-linear or non-linear, we here adopted a simple autoregressive model that has well-established applications in BCI task discriminations. It was shown that the parameters generated for the controller design can as well be used for motor imagery task discriminations with performance (with 8–23% task discrimination errors) comparable to the discrimination performance of the commonly used features such as frequency specific band powers and the AR model parameters directly used. An optimal MPC has significant implications for high performance BCI applications.

Response of traveling waves to transient inputs in neural fields

“…This suggests there may also be a critical level of tissue excitability for wave genesis. For the control of epileptiform activity in the brain, a model-based predictive controller will most likely be necessary [53]. Thus, it would be useful to study the problem of terminating traveling pulses in neuronal network models with more details that address the complications of the in vivo problem.…”

“…Recently, the effect of spatial inhomogeneities in parameters was considered as a model of epileptic tissue [52]. Conceivably, the traveling pulses generated by regions of cortex prone to seizures could be controlled by some transient input to reduce pathological effects of such rogue activity [53].…”

A square root ensemble Kalman filter application to a motor-imagery brain-computer interface

“…Data were recorded with g.tec amplifier systems [6]. The same experimental paradigm with the same montage was used in our previous work [7]. …”

“…An ANN is a computational model based on biological neural networks and consists of an interconnected group of artificial neurons [7–10]. It can be treated as non-linear statistical data modeling tools that can be used to model complex relationships between inputs and outputs or to find patterns in data.…”

Investigation of the most appropriate mother wavelet for characterizing imaginary EEG signals used in BCI systems

“…Among these steps, feature extraction is the most challenging because choosing discriminating features directly affects the recognition rate of the BCI system. The relevant literature has proposed several feature extraction algorithms to represent BCI signals, which include wavelet transform [1,3], power spectral density [4], autoregressive (AR) parameters [5,6], amplitude of slow cortical potentials [7], and event-related (de)synchronization (ERD/ERS) features [8]. Among these techniques, continuous wavelet transform (CWT) has received the most attention from BCI researchers.…”