This paper proposes a novel feature selection method utilizing Rényi min-entropy-based algorithm for achieving a highly efficient brain–computer interface (BCI). Usually, wavelet packet transformation (WPT) is extensively used for feature extraction from electro-encephalogram (EEG) signals. For the case of multiple-class problem, classification accuracy solely depends on the effective feature selection from the WPT features. In conventional approaches, Shannon entropy and mutual information methods are often used to select the features. In this work, we have shown that our proposed Rényi min-entropy-based approach outperforms the conventional methods for multiple EEG signal classification. The dataset of BCI competition-IV (contains 4-class motor imagery EEG signal) is used for this experiment. The data are preprocessed and separated as the classes and used for the feature extraction using WPT. Then, for feature selection Shannon entropy, mutual information, and Rényi min-entropy methods are applied. With the selected features, four-class motor imagery EEG signals are classified using several machine learning algorithms. The results suggest that the proposed method is better than the conventional approaches for multiple-class BCI.

中文翻译：

---

利用小波包变换中基于Rényi最小熵的特征选择进行多类EEG信号分类。

本文提出了一种新颖的特征选择方法，该方法利用基于Rényi最小熵的算法来实现高效的脑机接口（BCI）。通常，小波包变换（WPT）被广泛用于从脑电图（EEG）信号中提取特征。对于多类别问题，分类准确性仅取决于从WPT功能中选择的有效功能。在常规方法中，通常使用香农熵和互信息方法来选择特征。在这项工作中，我们已经表明，我们提出的基于Rényi最小熵的方法优于传统的用于多个EEG信号分类的方法。本实验使用BCI竞赛IV的数据集（包含4类运动图像EEG信号）。数据经过预处理并作为类分离，并用于使用WPT进行特征提取。然后，为进行特征选择，应用香农熵，互信息和Rényi最小熵方法。通过选择的功能，可以使用几种机器学习算法对四类运动图像脑电信号进行分类。结果表明，所提出的方法优于传统方法的多类BCI。