当前位置: X-MOL 学术Signal Image Video Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A new approach for multiclass motor imagery recognition using pattern image features generated from common spatial patterns
Signal, Image and Video Processing ( IF 2.3 ) Pub Date : 2020-01-11 , DOI: 10.1007/s11760-019-01623-0
Mario I. Chacon-Murguia , Brenda E. Olivas-Padilla , Juan Ramirez-Quintana

This paper presents a new method that can classify multiple motor imageries and can be implemented in a realistic application because of its low computation time. The method proposes the use of pattern images, generated with the common spatial pattern (CSP) technique. The paper also suggests a new algorithm to determine the best frequency bands for optimal discrimination among the diverse motor imageries to classify. The pattern images and the state images, which represent the mental state of the user in a specific segment of time, are used to compute cross-correlation coefficients. Feature vectors, including characteristics obtained with CSP, and the mean and variance of the correlation coefficients were employed to design binary classifiers with support vector machines. In addition, the work includes a real-time simulation involving a sliding window technique. The proposed method was evaluated in four datasets: IVa, IVb and V from BCI Competition III and another provided by the software BCILAB, which compared with other state-of-the-art methods. The results that overcome surpassed the methods in these competitions and other state-of-the-art methods mentioned in this paper. The method also presents short computation time, robustness between subjects and capability to classify between multiple mental states.

中文翻译:

一种使用从常见空间模式生成的模式图像特征的多类运动图像识别新方法

本文提出了一种新方法,可以对多个运动图像进行分类,并且由于其计算时间短,因此可以在实际应用中实现。该方法建议使用通过共同空间模式 (CSP) 技术生成的模式图像。该论文还提出了一种新算法来确定最佳频带,以便在要分类的不同运动图像之间进行最佳区分。模式图像和状态图像代表用户在特定时间段内的心理状态,用于计算互相关系数。特征向量,包括用 CSP 获得的特征,以及相关系数的均值和方差,被用来设计带有支持向量机的二元分类器。此外,这项工作包括一个涉及滑动窗口技术的实时模拟。所提出的方法在四个数据集上进行了评估:来自 BCI 竞赛 III 的 IVa、IVb 和 V 以及由 BCILAB 软件提供的另一个数据集,与其他最先进的方法进行了比较。克服的结果超过了这些比赛中的方法和本文提到的其他最先进的方法。该方法还具有较短的计算时间、主体之间的鲁棒性以及在多种心理状态之间进行分类的能力。克服的结果超过了这些比赛中的方法和本文提到的其他最先进的方法。该方法还具有较短的计算时间、主体之间的鲁棒性以及在多种心理状态之间进行分类的能力。克服的结果超过了这些比赛中的方法和本文提到的其他最先进的方法。该方法还具有较短的计算时间、主体之间的鲁棒性以及在多种心理状态之间进行分类的能力。
更新日期:2020-01-11
down
wechat
bug