Applying graph neural network to multivariate time series anomaly detection

The proliferation of data collection methods and technologies has underscored the importance and potential of data across various domains. Time series data, characterized by high dimensions and large volumes, serves as a valuable source for pattern discovery and information extraction in diverse fie...

Full description

Saved in:
Bibliographic Details
Main Author: Mao, Yiyun
Other Authors: Jagath C Rajapakse
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175247
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175247
record_format dspace
spelling sg-ntu-dr.10356-1752472024-04-26T15:42:02Z Applying graph neural network to multivariate time series anomaly detection Mao, Yiyun Jagath C Rajapakse School of Computer Science and Engineering ASJagath@ntu.edu.sg Computer and Information Science The proliferation of data collection methods and technologies has underscored the importance and potential of data across various domains. Time series data, characterized by high dimensions and large volumes, serves as a valuable source for pattern discovery and information extraction in diverse fields. Anomaly detection algorithms for time series data have garnered significant interest due to their potential to serve as real-time monitors, aiding in incident tracking, outlier identification, and forecasting improvement. Motivated by the need to explore advanced anomaly detection techniques, this study investigates the performance of graph neural network-based anomaly detection models on multivariate time series data. Through comprehensive analysis of experiment results, it is evident that joint optimization and feature vector embedded graph attention mechanisms yield improved experimental outcomes. Notably, the combination of the two demonstrates enhanced capacity and sensibility in outputting meaningful error scores for unseen data. Additionally, evaluation method comparisons reveal the superiority of the epsilon search method in achieving higher F1 scores and lower latencies compared to the POT method. In conclusion, this project underscores the potential of graph neural network-based anomaly detection models in addressing real-world challenges associated with time series data analysis. By leveraging advanced techniques such as joint optimization and feature vector embedding, these models offer promising avenues for enhancing anomaly detection capabilities and improving real-time monitoring systems. Bachelor's degree 2024-04-23T01:02:36Z 2024-04-23T01:02:36Z 2024 Final Year Project (FYP) Mao, Y. (2024). Applying graph neural network to multivariate time series anomaly detection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175247 https://hdl.handle.net/10356/175247 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
spellingShingle Computer and Information Science
Mao, Yiyun
Applying graph neural network to multivariate time series anomaly detection
description The proliferation of data collection methods and technologies has underscored the importance and potential of data across various domains. Time series data, characterized by high dimensions and large volumes, serves as a valuable source for pattern discovery and information extraction in diverse fields. Anomaly detection algorithms for time series data have garnered significant interest due to their potential to serve as real-time monitors, aiding in incident tracking, outlier identification, and forecasting improvement. Motivated by the need to explore advanced anomaly detection techniques, this study investigates the performance of graph neural network-based anomaly detection models on multivariate time series data. Through comprehensive analysis of experiment results, it is evident that joint optimization and feature vector embedded graph attention mechanisms yield improved experimental outcomes. Notably, the combination of the two demonstrates enhanced capacity and sensibility in outputting meaningful error scores for unseen data. Additionally, evaluation method comparisons reveal the superiority of the epsilon search method in achieving higher F1 scores and lower latencies compared to the POT method. In conclusion, this project underscores the potential of graph neural network-based anomaly detection models in addressing real-world challenges associated with time series data analysis. By leveraging advanced techniques such as joint optimization and feature vector embedding, these models offer promising avenues for enhancing anomaly detection capabilities and improving real-time monitoring systems.
author2 Jagath C Rajapakse
author_facet Jagath C Rajapakse
Mao, Yiyun
format Final Year Project
author Mao, Yiyun
author_sort Mao, Yiyun
title Applying graph neural network to multivariate time series anomaly detection
title_short Applying graph neural network to multivariate time series anomaly detection
title_full Applying graph neural network to multivariate time series anomaly detection
title_fullStr Applying graph neural network to multivariate time series anomaly detection
title_full_unstemmed Applying graph neural network to multivariate time series anomaly detection
title_sort applying graph neural network to multivariate time series anomaly detection
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/175247
_version_ 1800916224389939200