The Experts below are selected from a list of 1692462 Experts worldwide ranked by ideXlab platform
Andrzej Cichocki - One of the best experts on this subject based on the ideXlab platform.
-
aggregation of sparse linear discriminant analyses for event related Potential classification in brain computer interface
International Journal of Neural Systems, 2014Co-Authors: Yu Zhang, Guoxu Zhou, Jing Jin, Qibin Zhao, Xingyu Wang, Andrzej CichockiAbstract:Two main issues for Event-Related Potential (ERP) classification in brain–computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classifi...
-
aggregation of sparse linear discriminant analyses for event related Potential classification in brain computer interface
International Journal of Neural Systems, 2014Co-Authors: Yu Zhang, Guoxu Zhou, Qibin Zhao, Xingyu Wang, Andrzej CichockiAbstract:Two main issues for Event-Related Potential (ERP) classification in brain–computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time. This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently l1-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples. Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of BCI.
Feng Duan - One of the best experts on this subject based on the ideXlab platform.
-
a dual stimuli approach combined with convolutional neural network to improve information transfer rate of event related Potential based brain computer interface
International Journal of Neural Systems, 2018Co-Authors: Wei Li, Mengfan Li, Huihui Zhou, Genshe Chen, Feng DuanAbstract:Increasing command generation rate of an Event-Related Potential-based brain-robot system is challenging, because of limited information transfer rate of a brain-computer interface system. To impro...
Yu Zhang - One of the best experts on this subject based on the ideXlab platform.
-
aggregation of sparse linear discriminant analyses for event related Potential classification in brain computer interface
International Journal of Neural Systems, 2014Co-Authors: Yu Zhang, Guoxu Zhou, Jing Jin, Qibin Zhao, Xingyu Wang, Andrzej CichockiAbstract:Two main issues for Event-Related Potential (ERP) classification in brain–computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classifi...
-
aggregation of sparse linear discriminant analyses for event related Potential classification in brain computer interface
International Journal of Neural Systems, 2014Co-Authors: Yu Zhang, Guoxu Zhou, Qibin Zhao, Xingyu Wang, Andrzej CichockiAbstract:Two main issues for Event-Related Potential (ERP) classification in brain–computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time. This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently l1-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples. Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of BCI.
Stephanie Bender - One of the best experts on this subject based on the ideXlab platform.
-
stimulus probability affects the visual n700 component of the event related Potential
Clinical Neurophysiology, 2020Co-Authors: Heike Althen, Tobias Banaschewski, Daniel Brandeis, Stephanie BenderAbstract:Abstract Objective To examine whether the occipito-temporal visual N700 component of the Event-Related Potential is sensitive to stimulus probabilities. Methods P1, N1, P3, and, in particular, the occipito-temporal N700 component of the Event-Related Potential were analysed in response to frequent and rare non-target letters of a continuous performance task in 200 healthy adolescents. Additionally, amplitude habituation with time was examined for the occipito-temporal N700 and N1 components. Results The visual P1, N1, and occipito-temporal N700 components were significantly larger in response to rare letters than to frequent letters, whereas the P3 component demonstrated no amplitude difference. Over time, the occipito-temporal N700 amplitude decreased in response to the rare letters, while the N1 amplitude increased, to both, frequent and rare letters. Conclusions This study provides first evidence that the visual occipito-temporal N700 is sensitive to stimulus probabilities, suggesting an enhanced post-processing of rare stimuli in secondary visual areas. The distinct habituation patterns of occipito-temporal N700 and N1 amplitudes distinguish repetition effects on stimulus post-processing (N700) from those on perception (N1). Significance The enhanced N700 component to rare stimuli might reflect an orienting response and underlying attentional processes. The N700 sensitivity to stimulus probabilities should be examined in patient groups with attentional deficits.
Wei Li - One of the best experts on this subject based on the ideXlab platform.
-
a dual stimuli approach combined with convolutional neural network to improve information transfer rate of event related Potential based brain computer interface
International Journal of Neural Systems, 2018Co-Authors: Wei Li, Mengfan Li, Huihui Zhou, Genshe Chen, Feng DuanAbstract:Increasing command generation rate of an Event-Related Potential-based brain-robot system is challenging, because of limited information transfer rate of a brain-computer interface system. To impro...
