ABSTRACT
Error self-detection based on error-related potentials (ErrP) is promising to improve the practicability of brain-computer interface systems. But the single trial recognition of ErrP is still a challenge that hinters the development of this technology. To assess the performance of different algorithms on decoding ErrP, this paper test four kinds of linear discriminant analysis algorithms, two kinds of support vector machines, logistic regression, and discriminative canonical pattern matching (DCPM) on two open accessed datasets. All algorithms were evaluated by their classification accuracies and their generalization ability on different sizes of training sets. The study results show that DCPM has the best performance. This study shows a comprehensive comparison of different algorithms on ErrP classification, which could give guidance for the selection of ErrP algorithm.
Subject(s)
Algorithms , Brain , Brain-Computer Interfaces , Discriminant Analysis , Electroencephalography , Support Vector MachineABSTRACT
Error related negativity (ERN) is generated in frontal and central cortical regions when individuals perceive errors. Because ERN has low signal-to-noise ratio and large individual difference, it is difficult for single trial ERN recognition. In current study, the optimized electroencephalograph (EEG) channels were selected based on the brain topography of ERN activity and ERN offline recognition rate, and the optimized EEG time segments were selected based on the ERN offline recognition rate, then the low frequency time domain and high frequency time-frequency domain features were analyzed based on wavelet transform, after which the ERN single detection algorithm was proposed based on the above procedures. Finally, we achieved average recognition rate of 72.0% ± 9.6% in 10 subjects by using the sample points feature in 0~3.9 Hz and the power and variance features in 3.9~15.6 Hz from the EEG segments of 200~600 ms on the selected 6 channels. Our work has the potential to help the error command real-time correction technique in the application of online brain-computer interface system.
ABSTRACT
Objective: To study the method of extracting somatosensory evoked potential better. Methods: This article com-pares an auto-reference, auto-correlative and adaptive interference cancellation theories and techniques (AAA-ICT) used to the single trial of somatosensory evoked potential (SEP) with the traditional superposition averaging. Results: By the intensive study and analysis of the somatosensory evoked potentials from the 80 human subjects whose nervous systems are normal, We can find that the traditional superposition averaging method has its reasonable connotation on the extraction of SEP except the inevitable defects. Conclusions: Meanwhile the AAA-ICT avoids its defects. R implements another jump for the SEP extrac-tion method and has a good clinical application value.