论文标题
与歧视老师的时间段有关神经网络的时间序列数据扩展
Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
论文作者
论文摘要
神经网络已成为模式识别的强大工具，其成功的一部分是由于使用大型数据集而概括。但是，与其他域不同，时间序列分类数据集通常很小。为了解决这个问题，我们提出了一个新颖的时间序列数据扩展，称为“指导翘曲”。尽管许多数据增强方法基于随机转换，但引导翘曲利用动态时间扭曲（DTW）和ShapeTW的元素比对属性（一种基于形状描述符的高级DTW方法）来确定性扭曲样品模式。这样，时间序列是通过扭曲样本模式的特征来匹配参考模式的时间步骤的混合。此外，我们介绍了一位歧视性老师，以作为指导扭曲的定向参考。我们在2015年UCR时间序列档案中的所有85个数据集上评估了该方法，该档案库具有深度卷积神经网络（CNN）和复发性神经网络（RNN）。可以在https://github.com/uchidalab/time_series_augmentation上找到具有易于使用的代码。
Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to address this problem, we propose a novel time series data augmentation called guided warping. While many data augmentation methods are based on random transformations, guided warping exploits the element alignment properties of Dynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shape descriptors, to deterministically warp sample patterns. In this way, the time series are mixed by warping the features of a sample pattern to match the time steps of a reference pattern. Furthermore, we introduce a discriminative teacher in order to serve as a directed reference for the guided warping. We evaluate the method on all 85 datasets in the 2015 UCR Time Series Archive with a deep convolutional neural network (CNN) and a recurrent neural network (RNN). The code with an easy to use implementation can be found at https://github.com/uchidalab/time_series_augmentation .
