Anomaly Detection using LSTM AutoEncoder

Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is...

Full description

Bibliographic Details
Main Authors: Mahmoud Moallem, Ali Akbar Pouyan
Format: Article
Language:fas
Published: Semnan University 2019-04-01
Series:مجله مدل سازی در مهندسی
Subjects:
Online Access:https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf
_version_ 1827342449058512896
author Mahmoud Moallem
Ali Akbar Pouyan
author_facet Mahmoud Moallem
Ali Akbar Pouyan
author_sort Mahmoud Moallem
collection DOAJ
description Anomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM).
first_indexed 2024-03-07T22:06:41Z
format Article
id doaj.art-f1798676e15041fb988ec5113cef8a26
institution Directory Open Access Journal
issn 2008-4854
2783-2538
language fas
last_indexed 2024-03-07T22:06:41Z
publishDate 2019-04-01
publisher Semnan University
record_format Article
series مجله مدل سازی در مهندسی
spelling doaj.art-f1798676e15041fb988ec5113cef8a262024-02-23T19:06:03ZfasSemnan Universityمجله مدل سازی در مهندسی2008-48542783-25382019-04-01175619121110.22075/jme.2018.12979.12703812Anomaly Detection using LSTM AutoEncoderMahmoud Moallem0Ali Akbar Pouyan1Faculty of Computer & IT Engineering, Shahrood University of Technology, Shahrood, Iran,Faculty of Computer & IT Engineering, Shahrood University of Technology, Shahrood, IranAnomaly detection means detecting samples that are different from the normal samples in the dataset. One of the great challenges in this area is finding labeled data, especially for the abnormal categories. In this paper, we propose a method that uses normal data to detect anomalies. This method is based on established neural networks which are called automated encoder and are considered in deep learning studies. An automated encoder reproduces its input as output and reconstruction deviation to rate anomalies. We have used LSTM blocks to construct encoder instead of using ordinary neurons. In fact, these blocks are a category of recurring neural networks that are specialized in discovering and fetching time and proximity dependencies. The result of employing an automated encoder using LSTM blocks to detect point anomalies shows that this approach has been promising and successful in extracting the normal data’s internal model and also detecting anomalous data. The AUC factor of the model, in almost all cases, is better than the AUC of an ordinary automated encoder and One Class Support Vector Machine (OC-SVM).https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdfanomaly detectionautoencoderlstmdeep learning
spellingShingle Mahmoud Moallem
Ali Akbar Pouyan
Anomaly Detection using LSTM AutoEncoder
مجله مدل سازی در مهندسی
anomaly detection
autoencoder
lstm
deep learning
title Anomaly Detection using LSTM AutoEncoder
title_full Anomaly Detection using LSTM AutoEncoder
title_fullStr Anomaly Detection using LSTM AutoEncoder
title_full_unstemmed Anomaly Detection using LSTM AutoEncoder
title_short Anomaly Detection using LSTM AutoEncoder
title_sort anomaly detection using lstm autoencoder
topic anomaly detection
autoencoder
lstm
deep learning
url https://modelling.semnan.ac.ir/article_3812_176825df33b04a7466d5f4fc41dc0ccb.pdf
work_keys_str_mv AT mahmoudmoallem anomalydetectionusinglstmautoencoder
AT aliakbarpouyan anomalydetectionusinglstmautoencoder