Signal Processing and Control Group, ISVR, University of Southampton, Southampton SO17 1BJ, UK.
Comput Intell Neurosci. 2007;2007:41468. doi: 10.1155/2007/41468.
We propose a technique based on independent component analysis (ICA) with constraints, applied to the rhythmic electroencephalographic (EEG) data recorded from a brain-computer interfacing (BCI) system. ICA is a technique that can decompose the recorded EEG into its underlying independent components and in BCI involving motor imagery, the aim is to isolate rhythmic activity over the sensorimotor cortex. We demonstrate that, through the technique of spectrally constrained ICA, we can learn a spatial filter suited to each individual EEG recording. This can effectively extract discriminatory information from two types of single-trial EEG data. Through the use of the ICA algorithm, the classification accuracy is improved by about 25%, on average, compared to the performance on the unpreprocessed data. This implies that this ICA technique can be reliably used to identify and extract BCI-related rhythmic activity underlying the recordings where a particular filter is learned for each subject. The high classification rate and low computational cost make it a promising algorithm for application to an online BCI system.
我们提出了一种基于约束独立成分分析（ICA）的技术，应用于从脑机接口（BCI）系统记录的节律性脑电图（EEG）数据。ICA 是一种可以将记录的 EEG 分解为其基本独立成分的技术，在涉及运动想象的 BCI 中，目的是隔离感觉运动皮层上的节律活动。我们证明，通过谱约束 ICA 的技术，我们可以为每个个体 EEG 记录学习适合的空间滤波器。这可以有效地从两种类型的单次 EEG 数据中提取鉴别信息。通过使用 ICA 算法，与未经预处理的数据相比，分类准确率平均提高了约 25%。这意味着，该 ICA 技术可以可靠地用于识别和提取记录中与 BCI 相关的节律活动，其中为每个受试者学习了特定的滤波器。高分类率和低计算成本使其成为应用于在线 BCI 系统的有前途的算法。
