EEG-based trial-by-trial texture classification during active touch.

EEG-based trial-by-trial texture classification during active touch.
复制标题

主动触摸期间基于EEG的逐试纹理分类。

DOI:
10.1038/s41598-020-77439-7
复制
发表时间:
2020-11-27
期刊:
影响因子:
4.6
通讯作者:
Akcakaya M
Akcakaya M
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Eldeeb S;Weber D;Ting J;Demir A;Erdogmus D;Akcakaya M

文献摘要

参考文献

被引文献

相似文献

试验的纹理分类分析和识别显着的纹理相关的EEG功能,在主动触摸的运动类型和频率条件的影响最小是这项工作的主要贡献。共招募了12名健康受试者。每个受试者被指示使用他们的优势手的食指的指尖摩擦或敲击三个纹理表面(光滑平坦,中等粗糙和粗糙)与三个水平的运动频率(约2,1和0.5 Hz)。在每个触摸条件下同步收集EEG和力数据。一个系统的特征选择过程中,选择时间和频谱EEG功能,有助于纹理分类,但对运动类型和频率分类的贡献低。一个十倍交叉验证被用来训练两个3类(每个纹理和运动频率分类)和2类(运动类型)支持向量机分类器。我们的研究结果表明,在mu(8-15 Hz)和beta(16-30 Hz)频段的总功率在区分具有不同粗糙度水平的纹理(平均准确度> 84%)方面表现出较高的准确度,但对运动类型(平均准确度< 65%)和频率(平均准确度< 58%)分类的贡献较低。
Trial-by-trial texture classification analysis and identifying salient texture related EEG features during active touch that are minimally influenced by movement type and frequency conditions are the main contributions of this work. A total of twelve healthy subjects were recruited. Each subject was instructed to use the fingertip of their dominant hand’s index finger to rub or tap three textured surfaces (smooth flat, medium rough, and rough) with three levels of movement frequency (approximately 2, 1 and 0.5 Hz). EEG and force data were collected synchronously during each touch condition. A systematic feature selection process was performed to select temporal and spectral EEG features that contribute to texture classification but have low contribution towards movement type and frequency classification. A tenfold cross validation was used to train two 3-class (each for texture and movement frequency classification) and a 2-class (movement type) Support Vector Machine classifiers. Our results showed that the total power in the mu (8–15 Hz) and beta (16–30 Hz) frequency bands showed high accuracy in discriminating among textures with different levels of roughness (average accuracy > 84%) but lower contribution towards movement type (average accuracy < 65%) and frequency (average accuracy < 58%) classification.
DOI: 10.3389/fphys.2019.01452
发表时间: 2019-12-03
影响因子: 4
作者:
Bogdan, Paul
通讯作者: Bogdan, Paul
DOI: 10.1177/0278364915603135
发表时间: 2015-12-01
影响因子: 9.2
作者:
Pacchierotti, C.;Meli, L.;Prattichizzo, D.
通讯作者: Prattichizzo, D.
DOI: 10.1016/j.neuropsychologia.2015.07.007
发表时间: 2015-12
期刊: Neuropsychologia
影响因子: 2.6
作者:
Borich MR;Brodie SM;Gray WA;Ionta S;Boyd LA
通讯作者: Boyd LA
DOI: 10.3758/bf03206916
发表时间: 2000-05-01
期刊: PERCEPTION & PSYCHOPHYSICS
影响因子: --
作者:
Hollins, M;Risner, SR
通讯作者: Risner, SR
DOI: 10.1016/s0167-8760(00)00145-8
发表时间: 2001-01-01
影响因子: 3
作者:
Basar, E;Basar-Eroglu, C;Schürmann, M
通讯作者: Schürmann, M