arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11829cs.LG
收藏

RTFN:一种用于时间序列分类的鲁棒时间特征网络

RTFN: A Robust Temporal Feature Network for Time Series Classification

Southwest Jiaotong University(西南交通大学);China University of Mining and Technology(中国矿业大学)

Zhiwen Xiao, Xin Xu, Huanlai Xing, Shouxi Luo, Penglin Dai, Dawei Zhan

摘要:

时间序列数据通常包含局部和全局模式。现有的特征网络大多关注局部特征,而忽略了特征之间的关系。然而,后者也很重要,但更难探索。通过特征网络获得足够的表示仍然是一个挑战。为此,我们提出了一种新的鲁棒时间特征网络(RTFN)的特征提取在时间序列分类,包含一个时间特征网络(TFN)和一个基于LSTM的注意力网络(LSTMaN)。TFN是具有多个卷积层的残差结构。它作为一个局部特征提取网络从数据中挖掘足够的局部特征。LSTMaN由两个相同的层组成,其中注意力和长短期记忆(LSTM)网络混合。该网络作为一个关系抽取网络,用于发现序列数据中不同位置的抽取特征之间的内在关系。在实验中,我们将RTFN嵌入到监督结构中作为特征提取器,嵌入到无监督结构中作为编码器。结果表明,基于RTF的结构在大量UCR2018和UEA2018数据集上实现了出色的监督和无监督性能。

英文摘要:

Time series data usually contains local and global patterns. Most of the existing feature networks pay more attention to local features rather than the relationships among them. The latter is, however, also important yet more difficult to explore. To obtain sufficient representations by a feature network is still challenging. To this end, we propose a novel robust temporal feature network (RTFN) for feature extraction in time series classification, containing a temporal feature network (TFN) and an LSTM-based attention network (LSTMaN). TFN is a residual structure with multiple convolutional layers. It functions as a local-feature extraction network to mine sufficient local features from data. LSTMaN is composed of two identical layers, where attention and long short-term memory (LSTM) networks are hybridized. This network acts as a relation extraction network to discover the intrinsic relationships among the extracted features at different positions in sequential data. In experiments, we embed RTFN into a supervised structure as a feature extractor and into an unsupervised structure as an encoder, respectively. The results show that the RTFN-based structures achieve excellent supervised and unsupervised performance on a large number of UCR2018 and UEA2018 datasets.

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。

↑