School of Computer Science and Technology, Huazhong University of Science and Technology, China.
Neural Netw. 2021 Apr;136:126-140. doi: 10.1016/j.neunet.2021.01.001. Epub 2021 Jan 6.
With the rapid increase of data availability, time series classification (TSC) has arisen in a wide range of fields and drawn great attention of researchers. Recently, hundreds of TSC approaches have been developed, which can be classified into two categories: traditional and deep learning based TSC methods. However, it remains challenging to improve accuracy and model generalization ability. Therefore, we investigate a novel end-to-end model based on deep learning named as Multi-scale Attention Convolutional Neural Network (MACNN) to solve the TSC problem. We first apply the multi-scale convolution to capture different scales of information along the time axis by generating different scales of feature maps. Then an attention mechanism is proposed to enhance useful feature maps and suppress less useful ones by learning the importance of each feature map automatically. MACNN addresses the limitation of single-scale convolution and equal weight feature maps. We conduct a comprehensive evaluation of 85 UCR standard datasets and the experimental results show that our proposed approach achieves the best performance and outperforms the other traditional and deep learning based methods by a large margin.
随着数据可用性的快速增加，时间序列分类（TSC）已经在广泛的领域中出现，并引起了研究人员的极大关注。最近，已经开发了数百种 TSC 方法，可以将其分为两类：基于传统和深度学习的 TSC 方法。然而，提高准确性和模型泛化能力仍然具有挑战性。因此，我们研究了一种基于深度学习的新型端到端模型，称为多尺度注意力卷积神经网络（MACNN），以解决 TSC 问题。我们首先应用多尺度卷积通过生成不同尺度的特征图来沿时间轴捕获不同尺度的信息。然后，提出了一种注意力机制，通过自动学习每个特征图的重要性来增强有用的特征图并抑制不太有用的特征图。MACNN 解决了单尺度卷积和等权特征图的局限性。我们对 85 个 UCR 标准数据集进行了全面评估，实验结果表明，我们提出的方法表现最佳，大大优于其他传统和基于深度学习的方法。
