A Proposal of Boosting Algorithm for Brain-Computer Interface Using Probabilistic Data Interpolation
A Proposal of Boosting Algorithm for Brain-Computer Interface Using Probabilistic Data Interpolation
复制标题
基于概率数据插值的脑机接口Boosting算法的提出
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Tsuruse Shinji
中科院分区：
文献类型：
--
作者：
Hayashi Isao;Tsuruse Shinji
脑-机接口（BCI）和脑-机接口（BMI）是近年来研究的热点。利用近红外光谱（NIRS）或脑电图（EEG）检测到的脑活动和识别出的边界，控制外部计算机和机器。然而，在一般情况下，大量的活动数据是必要的，以确定在传统的判别模型的判别边界。在本文中，我们提出了一种新的提升算法的BCI使用概率数据插值。在我们的模型中，插值数据产生的概率分布和周围的错误，而不是在传统的Adaboost的权重。通过插值数据，识别边界，有效地控制外部机器。将该方法应用于近红外光谱的算术测试中，并讨论了该方法的有效性。
Brain-computer interface(BCI) and brain-machine interface(BMI) have been come into the research limelight. The outer computer and machine are controlled by brain activity and the discriminated boundary, which are detected with near-infrared spectroscopy(NIRS) or electroencephalograph(EEG). However, in general, a large amount of activity data are necessary to determine the discriminated boundary in the conventional discriminant models. In this paper, we propose a new boosting algorithm for BCI using probabilistic data interpolation. In our model, interpolated data are generated by probabilistic distribution and assorted around errors instead of weights in the conventional Adaboost. By the interpolated data, the discriminated boundary is identified to control the outer machine effectively. We apply our method to arithmetic test with NIRS, and discuss the usefulness of our method.