The learning of inter-day representation of electromyographic (EMG) signals across multiple days remains a challenging topic and not fully accommodated yet. This study aims to improve the inter-day hand motion classification accuracy via convolutional neural network (CNN)-based data feature fusion. An EMG database (ISRMyo-I) was recorded from six subjects on 10 days via a low density electrode setting. This study investigated CNNs’ capability of feature learning, and found that the output of the first fully connected layer (CNNFeats) was a decent supplement feature set to the most prevalent Hudgins’ time domain features in combination with fourth-order autoregressive coefficients (TDAR). Through adding the automatically learned CNNFeats to the handcrafted TDAR feature set, both linear discriminant analysis (LDA) and support vector machine (SVM) classifiers received >3% accuracy improvement. Similarly, taking TDAR as additional input to the CNN improved the accuracy by >1% in the comparison with the basic CNN. Our results also demonstrated that the CNN approach outperformed conventional approaches when multiple subjects’ data were available for training, while traditional approaches were more adept at presenting motion patterns for single subject. A preliminary conclusion is drawn that substantial “common knowledge/features” can be learned by CNNs from the raw EMG signals across multiple days and multiple subjects, and thus it is believed that a pre-trained CNN model would contribute to higher accuracy as well as the reduction of learning burden.

中文翻译：

---

通过基于卷积神经网络的特征融合改进日间手势识别

跨多天学习肌电图 (EMG) 信号的日间表示仍然是一个具有挑战性的主题，尚未完全适应。本研究旨在通过基于卷积神经网络 (CNN) 的数据特征融合来提高日间手部运动分类的准确性。通过低密度电极设置在 10 天内记录了六名受试者的 EMG 数据库 (ISRMyo-I)。这项研究调查了 CNN 的特征学习能力，发现第一个全连接层 (CNNFeats) 的输出是对最流行的 Hudgins 时域特征与四阶自回归系数 (TDAR) 相结合的一个不错的补充特征集. 通过将自动学习的 CNNFeats 添加到手工制作的 TDAR 特征集，>3% 的准确度提升。类似地，将 TDAR 作为 CNN 的附加输入提高了准确度>与基本 CNN 相比为 1%。我们的结果还表明，当多个受试者的数据可用于训练时，CNN 方法优于传统方法，而传统方法更擅长呈现单个受试者的运动模式。得出的初步结论是，CNN 可以从多天和多个受试者的原始 EMG 信号中学习大量的“共同知识/特征”，因此相信预训练的 CNN 模型将有助于提高准确性以及减轻学习负担。