Steyrl David, Scherer Reinhold, Faller Josef, Müller-Putz Gernot R
Biomed Tech (Berl). 2016 Feb;61(1):77-86. doi: 10.1515/bmt-2014-0117.
There is general agreement in the brain-computer interface (BCI) community that although non-linear classifiers can provide better results in some cases, linear classifiers are preferable. Particularly, as non-linear classifiers often involve a number of parameters that must be carefully chosen. However, new non-linear classifiers were developed over the last decade. One of them is the random forest (RF) classifier. Although popular in other fields of science, RFs are not common in BCI research. In this work, we address three open questions regarding RFs in sensorimotor rhythm (SMR) BCIs: parametrization, online applicability, and performance compared to regularized linear discriminant analysis (LDA). We found that the performance of RF is constant over a large range of parameter values. We demonstrate - for the first time - that RFs are applicable online in SMR-BCIs. Further, we show in an offline BCI simulation that RFs statistically significantly outperform regularized LDA by about 3%. These results confirm that RFs are practical and convenient non-linear classifiers for SMR-BCIs. Taking into account further properties of RFs, such as independence from feature distributions, maximum margin behavior, multiclass and advanced data mining capabilities, we argue that RFs should be taken into consideration for future BCIs.
脑机接口（BCI）领域普遍认为，尽管非线性分类器在某些情况下能提供更好的结果，但线性分类器更可取。特别是，由于非线性分类器通常涉及许多必须仔细选择的参数。然而，在过去十年中开发了新的非线性分类器。其中之一是随机森林（RF）分类器。尽管RF在其他科学领域很受欢迎，但在BCI研究中并不常见。在这项工作中，我们解决了关于感觉运动节律（SMR）BCI中RF的三个开放性问题：参数化、在线适用性以及与正则化线性判别分析（LDA）相比的性能。我们发现RF的性能在很大范围的参数值上是恒定的。我们首次证明RF可在SMR-BCI中在线应用。此外，我们在离线BCI模拟中表明，RF在统计上显著优于正则化LDA约3%。这些结果证实RF是适用于SMR-BCI的实用且便捷的非线性分类器。考虑到RF的其他特性，如与特征分布无关、最大间隔行为、多类和先进的数据挖掘能力，我们认为未来的BCI应该考虑使用RF。
