arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.03381eess.SPcs.AIcs.CVcs.LGeess.IV
收藏

S-ConvNet:一种用于基于瞬时高密度表面肌电图像的神经肌肉活动识别的浅层卷积神经网络架构

S-ConvNet: A Shallow Convolutional Neural Network Architecture for Neuromuscular Activity Recognition Using Instantaneous High-Density Surface EMG Images

Université du Québec à Trois-Rivières(魁北克大学三河分校);Concordia University(康考迪亚大学)

Md. Rabiul Islam, Daniel Massicotte, Francois Nougarou, Philippe Massicotte, Wei-Ping Zhu

AI总结:

针对HD-sEMG图像识别中深度网络计算成本高的问题,提出S-ConvNet和All-ConvNet模型从头学习特征,在无需预训练、数据集缩小约12倍且大幅减少参数的情况下,仍取得极具竞争力的准确率,尤其适用于资源受限场景。

摘要:

使用瞬时高密度表面肌电图(HD-sEMG)图像进行神经肌肉活动识别的概念,为开发更流畅和自然的肌肉计算机接口开辟了新途径。然而,现有方法在HD-sEMG图像识别中采用了非常大的深度卷积神经网络(ConvNet)架构和复杂的训练方案,这要求网络架构在非常大规模的带标签训练数据集上进行预训练,结果导致计算成本非常高。为了克服这一问题,我们提出了S-ConvNet和All-ConvNet模型,这是一个简单但高效的框架,可从头学习瞬时HD-sEMG图像以进行神经肌肉活动识别。在不使用任何预训练模型的情况下,我们提出的S-ConvNet和All-ConvNet在基于瞬时HD-sEMG图像的神经肌肉活动识别中,展示出与更复杂的最先进方法极具竞争力的识别准确率,同时使用了约12倍更小的数据集,并在很大程度上减少了学习参数。实验结果证明,S-ConvNet和All-ConvNet对于学习瞬时HD-sEMG图像识别的判别特征非常有效,特别是在数据和高端资源受限的场景中。

英文摘要:

The concept of neuromuscular activity recognition using instantaneous high-density surface electromyography (HD-sEMG) images opens up new avenues for the development of more fluid and natural muscle-computer interfaces. However, the existing approaches employed a very large deep convolutional neural network (ConvNet) architecture and complex training schemes for HD-sEMG image recognition, which requires the network architecture to be pre-trained on a very large-scale labeled training dataset, as a result, it makes computationally very expensive. To overcome this problem, we propose S-ConvNet and All-ConvNet models, a simple yet efficient framework for learning instantaneous HD-sEMG images from scratch for neuromuscular activity recognition. Without using any pre-trained models, our proposed S-ConvNet and All-ConvNet demonstrate very competitive recognition accuracy to the more complex state of the art for neuromuscular activity recognition based on instantaneous HD-sEMG images, while using a ~ 12 x smaller dataset and reducing learning parameters to a large extent. The experimental results proved that the S-ConvNet and All-ConvNet are highly effective for learning discriminative features for instantaneous HD-sEMG image recognition especially in the data and high-end resource constrained scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑