Rethinking 1D-CNN for Time Series Classification: A Stronger Baseline
Rethinking 1D-CNN for Time Series Classification: A Stronger Baseline
复制标题
DOI：
--
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Wensi Tang;Guodong Long;Lu Liu;Tianyi Zhou;Jing Jiang;M. Blumenstein
中科院分区：
文献类型：
--
作者：
Wensi Tang;Guodong Long;Lu Liu;Tianyi Zhou;Jing Jiang;M. Blumenstein
对于使用1D-CNN的时间序列分类任务，核大小的选择至关重要，以确保模型能够从长时间序列中捕捉到正确的尺度显著信号。现有的1D-CNN研究大多将核大小作为超参数，通过网格搜索来寻找合适的核大小，这既耗时又低效。本文从理论上分析了核大小对1D-CNN性能的影响。考虑到核大小的重要性，我们提出了一种新的全尺度1D-CNN(OS-CNN)结构来在模型学习期间捕获合适的核大小。开发了一种针对内核大小配置的特定设计，它使我们能够组合极少的内核大小选项来表示更易接受的领域。使用85个数据集的UCR档案对所提出的OS-CNN方法进行了评估。实验结果表明，我们的方法在关键差异图、胜数和平均准确率等多个性能指标上具有更强的基线。我们还在GitHub上发布了实验源代码(这是一个HTTPS URL)。
For time series classification task using 1D-CNN, the selection of kernel size is critically important to ensure the model can capture the right scale salient signal from a long time-series. Most of the existing work on 1D-CNN treats the kernel size as a hyper-parameter and tries to find the proper kernel size through a grid search which is time-consuming and is inefficient. This paper theoretically analyses how kernel size impacts the performance of 1D-CNN. Considering the importance of kernel size, we propose a novel Omni-Scale 1D-CNN (OS-CNN) architecture to capture the proper kernel size during the model learning period. A specific design for kernel size configuration is developed which enables us to assemble very few kernel-size options to represent more receptive fields. The proposed OS-CNN method is evaluated using the UCR archive with 85 datasets. The experiment results demonstrate that our method is a stronger baseline in multiple performance indicators, including the critical difference diagram, counts of wins, and average accuracy. We also published the experimental source codes at GitHub (this https URL).