- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE) - Edmonton, AB, Canada (2019.5.5-2019.5.8)] 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE) - Targets Illumination Region Effect on Laser RCS in Random Media for H-Wave Polarization
摘要： The classification accuracy of a brain–computer interface (BCI) frequently suffers from ill-posed and overfitting problems. To avoid and alleviate these problems, we propose a method of a multilinear discriminant analysis with constraints to augment parameter reduction, regularization, and additional prior information for event-related potential (ERP)-based BCIs. The method reduces the number of parameters by multilinearization, regularizes the ill-posedness via subspaces that constrain the parameter spaces, and incorporates a brain functional connectivity through the constraints. The experimental results show that the proposed method improved the classification accuracy rates in a single-trial ERP processing.
关键词： multilinear algebra,single-trial classification,linear discriminant analysis,Brain–computer/machine interface (BCI/BMI),event-related potentials,electroencephalogram (EEG)
更新于2025-09-23 15:21:01
-
[IEEE 2020 International Conference on Computation, Automation and Knowledge Management (ICCAKM) - Dubai, United Arab Emirates (2020.1.9-2020.1.10)] 2020 International Conference on Computation, Automation and Knowledge Management (ICCAKM) - Compact UWB Monopole antenna with WLAN and X-Band satellite filtering Characteristics
摘要： The classification accuracy of a brain–computer interface (BCI) frequently suffers from ill-posed and overfitting problems. To avoid and alleviate these problems, we propose a method of a multilinear discriminant analysis with constraints to augment parameter reduction, regularization, and additional prior information for event-related potential (ERP)-based BCIs. The method reduces the number of parameters by multilinearization, regularizes the ill-posedness via subspaces that constrain the parameter spaces, and incorporates a brain functional connectivity through the constraints. The experimental results show that the proposed method improved the classification accuracy rates in a single-trial ERP processing.
关键词： single-trial classification,Brain–computer/machine interface (BCI/BMI),electroencephalogram (EEG),event-related potentials,linear discriminant analysis,multilinear algebra
更新于2025-09-19 17:13:59