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 2404.08601cs.LG
收藏

面向信息物理系统的合成时间序列数据生成

Generating Synthetic Time Series Data for Cyber-Physical Systems

Mississippi State University(密西西比州立大学);Eng. Research and Dev. Center Department of Defence(国防部工程研究与开发中心)

Alexander Sommers, Somayeh Bakhtiari Ramezani, Logan Cummins, Sudip Mittal, Shahram Rahimi, Maria Seale, Joseph Jaboure

AI总结:

针对Transformer在时间序列数据增强领域研究不足的问题,本文提出融合多项先验的架构并经时域相似性度量测试,揭示了领域挑战与未来研究方向。

摘要:

数据增强是深度学习在时间序列领域落地应用的重要支撑。现有文献存在一处空白:作为主流序列模型的Transformer,在时间序列数据增强方向的探索十分匮乏。本文提出一种融合多项成熟先验知识的架构,并采用一种性能优异的时域相似性度量开展测试。结果表明该领域具有挑战性,同时指明了未来研究的若干有价值方向。

英文摘要:

Data augmentation is an important facilitator of deep learning applications in the time series domain. A gap is identified in the literature, demonstrating sparse exploration of the transformer, the dominant sequence model, for data augmentation in time series. A architecture hybridizing several successful priors is put forth and tested using a powerful time domain similarity metric. Results suggest the challenge of this domain, and several valuable directions for future work.

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。

↑