arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.02577cs.LGcs.AI
收藏

一种可学习的动态时态池时间序列分类算法

Learnable Dynamic Temporal Pooling for Time Series Classification

POSTECH(浦项科技大学)

Dongha Lee, Seonghyeon Lee, Hwanjo Yu

摘要:

随着可用时间序列数据的增加,预测其类别标签已成为众多学科中最重要的挑战之一。最近的时间序列分类研究表明,卷积神经网络(CNN)实现了最先进的性能作为一个单一的分类器。在这项工作中,指出,通常采用现有的CNN分类器的全局池层丢弃的高级别功能的时间信息,我们提出了一个动态的时间池(DTP)技术,通过聚集在段级别的功能,减少隐藏表示的时间大小。为了将整个系列划分为多个片段,我们利用动态时间规整(DTW)将每个时间点按时间顺序与片段的原型特征对齐,这些特征可以与CNN分类器的网络参数同时优化。与全连接层相结合的DTP层有助于提取进一步的判别特征,考虑到它们在输入时间序列中的时间位置。在单变量和多变量时间序列数据集上的大量实验表明,我们提出的池化方法显着提高了分类性能。

英文摘要:

With the increase of available time series data, predicting their class labels has been one of the most important challenges in a wide range of disciplines. Recent studies on time series classification show that convolutional neural networks (CNN) achieved the state-of-the-art performance as a single classifier. In this work, pointing out that the global pooling layer that is usually adopted by existing CNN classifiers discards the temporal information of high-level features, we present a dynamic temporal pooling (DTP) technique that reduces the temporal size of hidden representations by aggregating the features at the segment-level. For the partition of a whole series into multiple segments, we utilize dynamic time warping (DTW) to align each time point in a temporal order with the prototypical features of the segments, which can be optimized simultaneously with the network parameters of CNN classifiers. The DTP layer combined with a fully-connected layer helps to extract further discriminative features considering their temporal position within an input time series. Extensive experiments on both univariate and multivariate time series datasets show that our proposed pooling significantly improves the classification performance.

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。

↑