arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.16477cs.LGstat.ML
收藏

用于时间序列生成的条件GAN

Conditional GAN for timeseries generation

Florida Institute of Technology(佛罗里达理工学院)

Kaleb E Smith, Anthony O Smith

摘要:

很明显,时间相关数据是世界上重要的信息来源。对于机器学习中的应用来说,挑战在于获得算法开发和分析所需的大量高质量数据。使用生成对抗网络(GAN)对合成数据进行建模一直是提供可行解决方案的核心。我们的工作集中在一维时间序列,并探讨了Few Shot方法,这是一个算法的能力,执行有限的数据。这项工作试图通过提出一种新的架构,时间序列GAN(TSGAN),以模拟现实的时间序列数据,以减轻挫折感。我们评估TSGAN从基准时间序列数据库的70个数据集。我们的研究结果表明,TSGAN表现优于竞争对手,无论是定量使用弗雷歇初始得分(FID)度量,定性分类时,作为评估标准。

英文摘要:

It is abundantly clear that time dependent data is a vital source of information in the world. The challenge has been for applications in machine learning to gain access to a considerable amount of quality data needed for algorithm development and analysis. Modeling synthetic data using a Generative Adversarial Network (GAN) has been at the heart of providing a viable solution. Our work focuses on one dimensional times series and explores the few shot approach, which is the ability of an algorithm to perform well with limited data. This work attempts to ease the frustration by proposing a new architecture, Time Series GAN (TSGAN), to model realistic time series data. We evaluate TSGAN on 70 data sets from a benchmark time series database. Our results demonstrate that TSGAN performs better than the competition both quantitatively using the Frechet Inception Score (FID) metric, and qualitatively when classification is used as the evaluation criteria.

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。

↑