Anomaly detection with Attention-based deep autoencoder

Anomaly detection has become one of the most trending topics in the Information Technology domain. There are many existing approaches that deeply investigate the application of anomaly detection in several domains, such as video surveillance, financial technology, telecommunication, and healthcare....

Full description

Bibliographic Details
Main Author: Yong, Hong Long
Format: Final Year Project / Dissertation / Thesis
Published: 2022
Subjects:
Online Access:http://eprints.utar.edu.my/4697/
http://eprints.utar.edu.my/4697/1/fyp_CS_2022_YHL.pdf
_version_ 1848886218679386112
author Yong, Hong Long
author_facet Yong, Hong Long
author_sort Yong, Hong Long
building UTAR Institutional Repository
collection Online Access
description Anomaly detection has become one of the most trending topics in the Information Technology domain. There are many existing approaches that deeply investigate the application of anomaly detection in several domains, such as video surveillance, financial technology, telecommunication, and healthcare. However, to the best of our knowledge, there is currently no absolute best solution that is reliable to be deployed on real-world applications. We investigate the key observation from the real-world application and tend to improve the existing anomaly detection model to a certain that we may find it is practical and reliable for real-world applications. We have found several key observations that might help to improve the existing work of MemAE from [4]. Firstly, anomaly detection on surveillance cameras will always process frames from the same scene. Secondly, it is not practical for an anomaly detection model to be trained with a huge amount of data in actual deployment. Thirdly, the anomalies that happen in a single video frame often occupy only a small portion of the video frame instead of the whole frame. In this project, a Conv2D autoencoder was built from scratch that mimics the Conv3D autoencoder to process images. Two attention mechanisms were applied to the baseline Conv2D autoencoder separately and thus forms two different attention-based deep autoencoders. The two attention mechanisms are Convolutional Block Attention Module (CBAM) [10], and an attention-based approach proposed by [11]. Throughout the experiments, improvement can be seen by implementing the attention mechanisms onto the baseline autoencoder and so the accuracy of anomaly detection
first_indexed 2025-11-15T19:35:00Z
format Final Year Project / Dissertation / Thesis
id utar-4697
institution Universiti Tunku Abdul Rahman
institution_category Local University
last_indexed 2025-11-15T19:35:00Z
publishDate 2022
recordtype eprints
repository_type Digital Repository
spelling utar-46972023-01-15T13:51:43Z Anomaly detection with Attention-based deep autoencoder Yong, Hong Long T Technology (General) Anomaly detection has become one of the most trending topics in the Information Technology domain. There are many existing approaches that deeply investigate the application of anomaly detection in several domains, such as video surveillance, financial technology, telecommunication, and healthcare. However, to the best of our knowledge, there is currently no absolute best solution that is reliable to be deployed on real-world applications. We investigate the key observation from the real-world application and tend to improve the existing anomaly detection model to a certain that we may find it is practical and reliable for real-world applications. We have found several key observations that might help to improve the existing work of MemAE from [4]. Firstly, anomaly detection on surveillance cameras will always process frames from the same scene. Secondly, it is not practical for an anomaly detection model to be trained with a huge amount of data in actual deployment. Thirdly, the anomalies that happen in a single video frame often occupy only a small portion of the video frame instead of the whole frame. In this project, a Conv2D autoencoder was built from scratch that mimics the Conv3D autoencoder to process images. Two attention mechanisms were applied to the baseline Conv2D autoencoder separately and thus forms two different attention-based deep autoencoders. The two attention mechanisms are Convolutional Block Attention Module (CBAM) [10], and an attention-based approach proposed by [11]. Throughout the experiments, improvement can be seen by implementing the attention mechanisms onto the baseline autoencoder and so the accuracy of anomaly detection 2022-09-09 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/4697/1/fyp_CS_2022_YHL.pdf Yong, Hong Long (2022) Anomaly detection with Attention-based deep autoencoder. Final Year Project, UTAR. http://eprints.utar.edu.my/4697/
spellingShingle T Technology (General)
Yong, Hong Long
Anomaly detection with Attention-based deep autoencoder
title Anomaly detection with Attention-based deep autoencoder
title_full Anomaly detection with Attention-based deep autoencoder
title_fullStr Anomaly detection with Attention-based deep autoencoder
title_full_unstemmed Anomaly detection with Attention-based deep autoencoder
title_short Anomaly detection with Attention-based deep autoencoder
title_sort anomaly detection with attention-based deep autoencoder
topic T Technology (General)
url http://eprints.utar.edu.my/4697/
http://eprints.utar.edu.my/4697/1/fyp_CS_2022_YHL.pdf