A comparison of univariate, vector, bilinear autoregressive, and band power features for brain-computer interfaces
A comparison of univariate, vector, bilinear autoregressive, and band power features for brain-computer interfaces
复制标题
DOI：
10.1007/s11517-011-0828-x
复制
发表时间：
2011-11-01
影响因子：
3.2
通讯作者：
Neuper, Christa
中科院分区：
文献类型：
--
作者：
Brunner, Clemens;Billinger, Martin;Neuper, Christa
选择合适的特征类型对于获得良好的整体脑机接口性能至关重要。流行的特征类型包括对数频带功率（logBP）、自回归（AR）参数、时域参数和基于小波的方法。在这项研究中，我们专注于AR模型的不同变体，并将性能与logBP特征进行比较。特别是，我们分析了单变量，向量和双线性AR模型。我们使用了来自9名健康用户的两次会议的四类运动想象数据。我们使用第一个会话来优化参数，例如模型阶数和频带。然后，我们在看不见的第二次会议上评估了优化的特征提取方法。我们发现，频带功率产生显着更高的分类精度比AR方法。然而，在我们的分析程序中，我们没有更新第二阶段分类器的偏倚。当在新会话开始时更新偏倚时，我们发现所有方法之间不再存在显著差异。此外，我们的研究结果表明，特定主题的优化并不比全局优化的参数。AR方法内的比较表明，向量模型显著优于单变量和双线性变量。最后，将预测误差方差添加到特征空间显著改善了分类结果。
Selecting suitable feature types is crucial to obtain good overall brain-computer interface performance. Popular feature types include logarithmic band power (logBP), autoregressive (AR) parameters, time-domain parameters, and wavelet-based methods. In this study, we focused on different variants of AR models and compare performance with logBP features. In particular, we analyzed univariate, vector, and bilinear AR models. We used four-class motor imagery data from nine healthy users over two sessions. We used the first session to optimize parameters such as model order and frequency bands. We then evaluated optimized feature extraction methods on the unseen second session. We found that band power yields significantly higher classification accuracies than AR methods. However, we did not update the bias of the classifiers for the second session in our analysis procedure. When updating the bias at the beginning of a new session, we found no significant differences between all methods anymore. Furthermore, our results indicate that subject-specific optimization is not better than globally optimized parameters. The comparison within the AR methods showed that the vector model is significantly better than both univariate and bilinear variants. Finally, adding the prediction error variance to the feature space significantly improved classification results.