Detection of Anomalies in Data Streams Using the LSTM-CNN Model

This paper presents a comparative analysis of selected deep learning methods applied to anomaly detection in data streams. The anomaly detection results obtained on the popular Yahoo! Webscope S5 dataset are used for the computational experiments. The two commonly used and recommended models in the...

Full description

Saved in:
Bibliographic Details
Main Authors: Agnieszka Duraj, Piotr S. Szczepaniak, Artur Sadok
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1610
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031516392882176
author Agnieszka Duraj
Piotr S. Szczepaniak
Artur Sadok
author_facet Agnieszka Duraj
Piotr S. Szczepaniak
Artur Sadok
author_sort Agnieszka Duraj
collection DOAJ
description This paper presents a comparative analysis of selected deep learning methods applied to anomaly detection in data streams. The anomaly detection results obtained on the popular Yahoo! Webscope S5 dataset are used for the computational experiments. The two commonly used and recommended models in the literature, which are the basis for this analysis, are the following: the LSTM and its more complicated variant, the LSTM autoencoder. Additionally, the usefulness of an innovative LSTM-CNN approach is evaluated. The results indicate that the LSTM-CNN approach can successfully be applied for anomaly detection in data streams as its performance compares favorably with that of the two mentioned standard models. For the performance evaluation, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mrow><mn>1</mn><mi>s</mi><mi>c</mi><mi>o</mi><mi>r</mi><mi>e</mi></mrow></msub></semantics></math></inline-formula> is used.
format Article
id doaj-art-104dbfbc8193412ea73af6e5cb7f0d9a
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-104dbfbc8193412ea73af6e5cb7f0d9a2025-08-20T02:58:57ZengMDPI AGSensors1424-82202025-03-01255161010.3390/s25051610Detection of Anomalies in Data Streams Using the LSTM-CNN ModelAgnieszka Duraj0Piotr S. Szczepaniak1Artur Sadok2Institute of Information Technology, Lodz University of Technology, al. Politechniki 8, 93-590 Łódź, PolandInstitute of Information Technology, Lodz University of Technology, al. Politechniki 8, 93-590 Łódź, PolandNESC Sp. z o.o., ul. Wojskowa 6/B1, 60-792 Poznań, PolandThis paper presents a comparative analysis of selected deep learning methods applied to anomaly detection in data streams. The anomaly detection results obtained on the popular Yahoo! Webscope S5 dataset are used for the computational experiments. The two commonly used and recommended models in the literature, which are the basis for this analysis, are the following: the LSTM and its more complicated variant, the LSTM autoencoder. Additionally, the usefulness of an innovative LSTM-CNN approach is evaluated. The results indicate that the LSTM-CNN approach can successfully be applied for anomaly detection in data streams as its performance compares favorably with that of the two mentioned standard models. For the performance evaluation, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mrow><mn>1</mn><mi>s</mi><mi>c</mi><mi>o</mi><mi>r</mi><mi>e</mi></mrow></msub></semantics></math></inline-formula> is used.https://www.mdpi.com/1424-8220/25/5/1610outliersanomaliesdeep learning methodsLSTM
spellingShingle Agnieszka Duraj
Piotr S. Szczepaniak
Artur Sadok
Detection of Anomalies in Data Streams Using the LSTM-CNN Model
Sensors
outliers
anomalies
deep learning methods
LSTM
title Detection of Anomalies in Data Streams Using the LSTM-CNN Model
title_full Detection of Anomalies in Data Streams Using the LSTM-CNN Model
title_fullStr Detection of Anomalies in Data Streams Using the LSTM-CNN Model
title_full_unstemmed Detection of Anomalies in Data Streams Using the LSTM-CNN Model
title_short Detection of Anomalies in Data Streams Using the LSTM-CNN Model
title_sort detection of anomalies in data streams using the lstm cnn model
topic outliers
anomalies
deep learning methods
LSTM
url https://www.mdpi.com/1424-8220/25/5/1610
work_keys_str_mv AT agnieszkaduraj detectionofanomaliesindatastreamsusingthelstmcnnmodel
AT piotrsszczepaniak detectionofanomaliesindatastreamsusingthelstmcnnmodel
AT artursadok detectionofanomaliesindatastreamsusingthelstmcnnmodel