Hu Chaochen, Sun Zihan, Li Chao, Zhang Yong, Xing Chunxiao
Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China.
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China.
Sensors (Basel). 2023 Aug 5;23(15):6976. doi: 10.3390/s23156976.
Nowadays, with the rapid growth of the internet of things (IoT), massive amounts of time series data are being generated. Time series data play an important role in scientific and technological research for conducting experiments and studies to obtain solid and convincing results. However, due to privacy restrictions, limited access to time series data is always an obstacle. Moreover, the limited available open source data are often not suitable because of a small quantity and insufficient dimensionality and complexity. Therefore, time series data generation has become an imperative and promising solution. In this paper, we provide an overview of classical and state-of-the-art time series data generation methods in IoT. We classify the time series data generation methods into four major categories: rule-based methods, simulation-model-based methods, traditional machine-learning-based methods, and deep-learning-based methods. For each category, we first illustrate its characteristics and then describe the principles and mechanisms of the methods. Finally, we summarize the challenges and future directions of time series data generation in IoT. The systematic classification and evaluation will be a valuable reference for researchers in the time series data generation field.
如今，随着物联网（IoT）的迅速发展，大量的时间序列数据正在生成。时间序列数据在科学技术研究中起着重要作用，通过进行实验和研究以获得可靠且有说服力的结果。然而，由于隐私限制，对时间序列数据的有限访问始终是一个障碍。此外，有限的可用开源数据往往不合适，因为数量少、维度不足且复杂性不够。因此，时间序列数据生成已成为一种势在必行且前景广阔的解决方案。在本文中，我们概述了物联网中经典的和最新的时间序列数据生成方法。我们将时间序列数据生成方法分为四大类：基于规则的方法、基于仿真模型的方法、基于传统机器学习的方法和基于深度学习的方法。对于每一类，我们首先阐述其特点，然后描述方法的原理和机制。最后，我们总结了物联网中时间序列数据生成的挑战和未来方向。这种系统的分类和评估将为时间序列数据生成领域的研究人员提供有价值的参考。
