arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.09293cs.LGcs.PF
收藏

LSTM与TCN模型在时间序列数据异常检测中的比较研究

A Comparative Study of Detecting Anomalies in Time Series Data Using LSTM and TCN Models

Texas Tech University(德克萨斯理工大学);Rutgers University(罗格斯大学)

Saroj Gopali, Faranak Abri, Sima Siami-Namini, Akbar Siami Namin

摘要:

存在几种数据驱动的方法,使我们能够对时间序列数据进行建模,包括传统的基于回归的建模方法(即,ARIMA)。最近,深度学习技术已经在时间序列分析和预测的背景下被引入和探索。要问的一个主要研究问题是深度学习技术的这些变体在预测时间序列数据时的性能。本文比较了两种主要的深度学习建模技术。比较了基于递归神经网络(RNN)的长短期记忆(LSTM)和基于卷积神经网络(CNN)的时间卷积网络(TCN),并报告了它们的性能和训练时间。根据我们的实验结果,这两种建模技术的性能都优于基于TCN的模型,略优于LSTM。此外,基于CNN的TCN模型比基于RNN的LSTM模型更快地建立稳定的模型。

英文摘要:

There exist several data-driven approaches that enable us model time series data including traditional regression-based modeling approaches (i.e., ARIMA). Recently, deep learning techniques have been introduced and explored in the context of time series analysis and prediction. A major research question to ask is the performance of these many variations of deep learning techniques in predicting time series data. This paper compares two prominent deep learning modeling techniques. The Recurrent Neural Network (RNN)-based Long Short-Term Memory (LSTM) and the convolutional Neural Network (CNN)-based Temporal Convolutional Networks (TCN) are compared and their performance and training time are reported. According to our experimental results, both modeling techniques perform comparably having TCN-based models outperform LSTM slightly. Moreover, the CNN-based TCN model builds a stable model faster than the RNN-based LSTM models.

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。

↑