The non-stationary nature of the electroencephalo-gram (EEG) poses a major challenge for the successful operation of a brain-computer interface (BCI) when deployed over multiple sessions. The changes between the early training measurements and the proceeding multiple sessions can originate as a result of alterations in the subject's brain process, new… (More)
This paper presents an overview of a multistage signal processing framework to tackle the main challenges in continuous control protocols for motor imagery based synchronous and self-paced BCIs. The BCI can be setup rapidly and automatically even when conducting an extensive search for subject-specific parameters. A new BCI-based game training paradigm… (More)
2) correlation coefficient rather than assessing overall systems performance via performance measure such as classification accuracy. Experimental results utilizing eight subjects are presented which demonstrate the effectiveness of the proposed methods for fast & efficient user-specific tuned BCI system.
This paper shows for the first time how a popular and successful filtering approach, known as the common spatial patterns (CSP) approach, compares to the neural time series prediction preprocessing (NTSPP) approach when applied in a 2-class EEG-based brain-computer interface (BCI), either using 2 or 60 EEG channels. Additionally, a novel NTSPP-CSP… (More)
The consistency and reliability of the brain computer interface (BCI) system is often questioned to be safe for controlling a wheelchair as BCIs characteristically experience a low signal-to-noise ratio and low classification accuracy. Electroencephalogram (EEG) acquired non-invasively consists of multiple time-series which are highly correlated because of… (More)
Recent work has shown that combining prediction based preprocessing based on neural-time-series-prediction-preprocessing (NTSPP) along with spectral filtering (SF) and common-spatial patterns (CSP) can significantly improve the performance of a motor imagery based brain-computer interface (BCI) involving two classes. This paper illustrates how these… (More)
1. Neural Time Series Prediction Preprocessing (NTSPP) was applied to all signals all subjects using the self-organizing fuzzy neural network (SOFNN). In a few cases subject performed slightly better without NTSPP however for the majority of subjects significant increases in the average accuracy were provided by NTSPP. NTSPP has been extended to work with… (More)