Advances in Computational Intelligence Systems
Advances in Computational Intelligence Systems
复制标题
计算智能系统的进展
DOI：
10.1007/978-3-319-46562-3_19
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Adair J
中科院分区：
文献类型：
--
作者：
Adair J
脑机接口是假肢进步的关键技术，但目前的信号采集方法受到许多因素的阻碍，尤其是噪声。在这种背景下，需要特征选择来选择重要的信号特征，提高分类器的准确性。进化算法已被证明优于特征选择的过滤方法（在准确性方面）。本文采用了一种单点启发式搜索方法，迭代局部搜索（ILS），并将其与遗传算法（GA）和模因算法（MA）进行了比较。然后，它进一步尝试利用特征之间的链接来指导搜索操作员使用所述算法。发现GA优于ILS。与直觉相反的是，链接引导算法比非引导算法导致更高的分类错误率。对此，本文进行了探讨。
Brain Computer Interfaces are an essential technology for the advancement of prosthetic limbs, but current signal acquisition methods are hindered by a number of factors, not least, noise. In this context, Feature Selection is required to choose the important signal features and improve classifier accuracy. Evolutionary algorithms have proven to outperform filtering methods (in terms of accuracy) for Feature Selection. This paper applies a single-point heuristic search method, Iterated Local Search (ILS), and compares it to a genetic algorithm (GA) and a memetic algorithm (MA). It then further attempts to utilise Linkage between features to guide search operators in the algorithms stated. The GA was found to outperform ILS. Counter-intuitively, linkage-guided algorithms resulted in higher classification error rates than their unguided alternatives. Explanations for this are explored.