Background:

Analysis and classication of extensive medical data (e.g. electroencephalography (EEG) signals) is a signicant challenge to develop effective brain-computer interface (BCI) system. Therefore, it is necessary to build automated classification framework to decode different brain signals.

Methods:

In the present study, two-step filtering approach is utilize to achieve resilience towards cognitive and external noises. Then, empirical wavelet transform (EWT) and four data reduction techniques; principal component analysis (PCA), independent component analysis (ICA), linear discriminant analysis (LDA) and neighborhood component analysis (NCA) are rst time integrated together to explore dynamic nature and pattern mining of motor imagery (MI) EEG signals. Specically, EWT helped to explore the hidden patterns of MI tasks by decomposing EEG data into dierent modes where every mode was consider as a feature vector in this study and each data reduction technique have been applied to all these modes to reduce the dimension of huge feature matrix. Moreover, an automated correlation-based components/coefficients selection criteria and parameter tuning were implemented for PCA, ICA, LDA, and NCA respectively. For the comparison purposes, all the experiments were performed on two publicly available datasets (BCI competition III dataset IVa and IVb). The performance of the experiments was veried by decoding three dierent channel combination strategies along with several neural networks. The regularizationparameter tuning of NCA guaranteed to improve classification performancewith significantfeaturesfor each subject.

Results:

The experimental results revealed that NCA provides an average sensitivity, specificity, accuracy, precision, F1 score and kappa-coefficient of 100% for subject dependent case whereas 93%, 93%, 92.9%, 93%, 96.4% and 90% for subject independent case respectively. All the results were obtained with artificial neural networks, cascade-forward neural networks and multilayer perceptron neural networks (MLP) for subject dependent case while with MLP for subject independent case by utilizing 7 channels out of total 118. Such an increase in results can alleviate users to explain more clearly their MI activities. For instance, physically impaired person will be able to manage their wheelchair quite effectively, and rehabilitated persons may be able to improve their activities.

中文翻译：

---

利用降维和神经网络技术开发专家脑机接口

背景：

分析和分类大量医学数据（例如脑电图（EEG）信号）是开发有效的脑机接口（BCI）系统的重大挑战。因此，有必要建立自动分类框架来解码不同的大脑信号。

方法：

在本研究中，采用两步滤波方法来实现对认知和外部噪声的适应能力。然后，经验小波变换（EWT）和四种数据约简技术；主成分分析（PCA），独立成分分析（ICA），线性判别分析（LDA）和邻域成分分析（NCA）首次集成在一起，以探索运动图像（MI）脑电信号的动态性质和模式挖掘。具体而言，EWT通过将EEG数据分解为不同的模式来帮助探索MI任务的隐藏模式，在该模式中，每种模式均被视为特征向量，并且每种数据缩减技术均已应用于所有这些模式以减小巨大特征的维数矩阵。此外，分别为PCA，ICA，LDA和NCA实施了基于自动相关性的成分/系数选择标准和参数调整。为了进行比较，所有实验均在两个公开可用的数据集（BCI竞赛III数据集IVa和IVb）上进行。通过解码三种不同的渠道组合策略以及几个神经网络来检验实验的性能。NCA的正则化参数调整可确保提高分类性能，并具有针对每个主题的显着功能。通过解码三种不同的渠道组合策略以及几个神经网络来检验实验的性能。NCA的正则化参数调整可确保提高分类性能，并具有针对每个主题的显着功能。通过解码三种不同的渠道组合策略以及几个神经网络来检验实验的性能。NCA的正则化参数调整可确保提高分类性能，并具有针对每个主题的显着功能。

结果：

实验结果表明，NCA对受检者依赖性病例的平均敏感性，特异性，准确性，准确性，F1得分和κ系数为100％，而受检者为93％，93％，92.9％，93％，96.4％和90％分别独立案例。所有结果都是通过人工神经网络，级联前向神经网络和多层感知器神经网络（MLP）针对受试者相关病例而获得的，而对于MLP对于受试者无关病例，则利用了总共118个通道中的7个通道。这样的结果增加可以缓解用户可以更清楚地说明他们的MI活动。例如，身体残障的人将能够相当有效地管理其轮椅，而康复者则可能能够改善其活动。