Frontiers in Neuroinformatics · 2018 · 94 citations · 51 references
EngineeringComputer ScienceNeuroscienceCognitive NeuroscienceHuman-computer InteractionNeural EngineeringBrain-computer InterfacesElectroencephalogram Signal ProcessingElectroencephalographyMental ImageryNeural InterfacesNeural Recording TechnologiesBinary ClassificationBrain-computer Interface ClassificationClassification AccuracyClassification Algorithms For Brain-computer InterfacesElectroencephalography-based Brain-computer InterfacesFunctional Near-infrared SpectroscopyHybrid Brain-computer InterfacesMotor Imagery Classification
Hybrid BCI systems that combine EEG and NIRS have been shown to improve binary classification accuracy, but ternary classification with such systems remains largely unexplored. The authors aim to use a ternary hybrid EEG‑NIRS BCI to classify mental arithmetic, motor imagery, and idle states, thereby increasing the information transfer rate while preserving accuracy. They placed EEG electrodes over the prefrontal and motor cortices and NIRS optodes on the forehead, decomposed the ternary task into three one‑versus‑one binary problems, applied multi‑band common spatial patterns, and evaluated performance with 10×10‑fold cross‑validation using shrinkage linear discriminant analysis and a meta‑classification scheme. The hybrid system achieved 82.2 % accuracy (vs.
The performance of a brain-computer interface (BCI) can be enhanced by simultaneously using two or more modalities to record brain activity, which is generally referred to as a hybrid BCI. To date, many BCI researchers have tried to implement a hybrid BCI system by combining electroencephalography (EEG) and functional near-infrared spectroscopy (NIRS) to improve the overall accuracy of binary classification. However, since hybrid EEG-NIRS BCI, which will be denoted by hBCI in this paper, has not been applied to ternary classification problems, paradigms and classification strategies appropriate for ternary classification using hBCI are not well investigated. Here we propose the use of an hBCI for the classification of three brain activation patterns elicited by mental arithmetic, motor imagery, and idle state, with the aim to elevate the information transfer rate (ITR) of hBCI by increasing the number of classes while minimizing the loss of accuracy. EEG electrodes were placed over the prefrontal cortex and the motor cortex, and NIRS optodes were placed only on the forehead. The ternary classification problem was decomposed into three binary classification problems using the "one-versus-one" classification strategy to apply the multi-band common spatial patterns filter to EEG data. A 10 × 10-fold cross validation was performed using shrinkage linear discriminant analysis to evaluate the average classification accuracies for EEG-BCI, NIRS-BCI, and hBCI when the meta-classification method was adopted to enhance classification accuracy. The ternary classification accuracies for EEG-BCI, NIRS-BCI, and hBCI were 76.1 ± 12.8, 64.1 ± 9.7, and 82.2 ± 10.2%, respectively. The classification accuracy of the proposed hBCI was thus significantly higher than those of the other BCIs (p < 0.005). The average ITR for the proposed hBCI was calculated to be 4.70 ± 1.92 bits/minute, which was 34.3% higher than that reported for a previous binary hBCI study.
51
Regularized Discriminant Analysis
Jerome H. Friedman · Journal of the American Statistical Association · 1989 · 2.3K citations · Full text
Optimizing Spatial filters for Robust EEG Single-Trial Analysis
Benjamin Blankertz, Ryota Tomioka, Steven Lemm et al. · IEEE Signal Processing Magazine · 2008 · 2.1K citations