A Time Convolutional Network Based Outlier Detection for Multidimensional Time Series in Cyber-Physical-Social Systems

Xiu Mei Wei,Tao Wei,Chao Meng,Xue Song Jiang

doi:10.1109/access.2020.2988797

Xiu Mei Wei, Tao Wei + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2988797

Copy DOI

Abstract

With the development of the Cyber-Physical-Social Systems(CPSS), a large number of multidimensional time series have been generated in today's world, such as: sensor data for industrial equipment operation, vehicle driving data, and cloud server operation and maintenance data and so on. The key task of Cloud-Fog-Edge Computing in managing these systems is how to detect anomalous data in a specific time series to facilitate operator action to solve potential system problems. So multidimensional time series outlier detection become an important direction of CPSS data mining and Cloud-Fog-Edge Computing research, and it has a wide range of applications in industry, finance, medicine and other fields. This paper proposes a framework called Multidimensional time series Outlier detection based on a Time Convolutional Network AutoEncoder (MOTCN-AE), which can detect outliers in time series data, such as identifying equipment failures, dangerous driving behaviors of cars, etc. Specifically, this paper first uses a feature extraction method to transform the original time series into a feature-rich time series. Second, the proposed TCN-AE is used to reconstruct the feature-rich time series data, and the reconstruction error is used to calculate outlier scores. Finally, the MOTCN-AE framework is validated by multiple time series datasets to demonstrate its effectiveness in detecting time series outliers.

Highlights

Multidimensional time series outlier detection is one of the important research directions of time series data mining
MOTCN-automatic encoder (AE) FRAMEWORK This paper proposes a time series outlier detection framework based on a time convolutional network model (TCN)
WORK In this paper, a multidimensional time series outlier detection framework based on a TCN is proposed (MOTCN-AE), and this framework is the first attempt to combine a TCN with an AE and a rich time series

Summary

Introduction

Multidimensional time series outlier detection is one of the important research directions of time series data mining. It has been widely used in many fields such as industry [1], [2], finance [3] and medicine [4] and so on. Monitoring the behavior of these systems can generate a large amount of multidimensional time series data, such as sensor parameters in a power plant system (e.g., temperature and pressure), operating parameters of a vehicle driving system, or connection component parameters in the information system (such as CPU usage, disk I/O) and so on. The key task of Cloud–Fog–Edge Computing in managing these systems is how to detect anomalous data in a specific time series to.

Objectives

Results

Conclusion