Geodesic
Application of OWL ontologies and LSTM networks in searching for anomalies of time series
Nečetkie sistemy i mâgkie vyčisleniâ, Tome 17 (2022) no. 2, pp. 28-40.

Voir la notice de l'article provenant de la source Math-Net.Ru

The paper describes the results of the development of an algorithm for detecting anomalies in time series, taking into account the specifics of the subject area. The algorithm involves finding a time series forecast using LSTM networks, detecting anomalies based on the obtained forecast, filtering the found anomalies in accordance with possible deviations of the time series values from the trend reflected in the ontology, and logically deriving search results using a set of SWRL rules. The effectiveness of the proposed approach has been confirmed by a number of experiments conducted on the benchmark of data on the operation of oil rigs.
Keywords: time series, neural network, ontology, anomaly detection. 
@article{FSSC_2022_17_2_a1,
     author = {D. S. Kurilo and A. A. Dyrnochkin and V. S. Moshkin and N. G. Yarushkina},
     title = {Application of {OWL} ontologies and {LSTM} networks in searching for anomalies of time series},
     journal = {Ne\v{c}etkie sistemy i m\^agkie vy\v{c}isleni\^a},
     pages = {28--40},
     publisher = {mathdoc},
     volume = {17},
     number = {2},
     year = {2022},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/FSSC_2022_17_2_a1/}
}
TY  - JOUR
AU  - D. S. Kurilo
AU  - A. A. Dyrnochkin
AU  - V. S. Moshkin
AU  - N. G. Yarushkina
TI  - Application of OWL ontologies and LSTM networks in searching for anomalies of time series
JO  - Nečetkie sistemy i mâgkie vyčisleniâ
PY  - 2022
SP  - 28
EP  - 40
VL  - 17
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/FSSC_2022_17_2_a1/
LA  - ru
ID  - FSSC_2022_17_2_a1
ER  - 
%0 Journal Article
%A D. S. Kurilo
%A A. A. Dyrnochkin
%A V. S. Moshkin
%A N. G. Yarushkina
%T Application of OWL ontologies and LSTM networks in searching for anomalies of time series
%J Nečetkie sistemy i mâgkie vyčisleniâ
%D 2022
%P 28-40
%V 17
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/FSSC_2022_17_2_a1/
%G ru
%F FSSC_2022_17_2_a1
D. S. Kurilo; A. A. Dyrnochkin; V. S. Moshkin; N. G. Yarushkina. Application of OWL ontologies and LSTM networks in searching for anomalies of time series. Nečetkie sistemy i mâgkie vyčisleniâ, Tome 17 (2022) no. 2, pp. 28-40. http://geodesic.mathdoc.fr/item/FSSC_2022_17_2_a1/

[1] Lindigrin A. N., “Analysis of specifics and problems of anomaly search processes in network data”, Izvestiya TulSU. Technical sciences, 2021, no. 5, 304–309

[2] Hasanov V. I., “Detection of anomalies in network traffic based on neural network modeling of dynamics of changes in IP packet volumes”, MMC, 2018, no. 2

[3] Busseti E., Osband I., Wong S., Deep Learning for Time Series Modeling, Stanford University, Stanford, California, 2012

[4] Chandola V., Banerjee A., Kumar V., Anomaly Detection: a Survey, University of Minnesota, Minneapolis, MN, 2007

[5] Ahmad S., Purdy S., Real-time Anomaly Detection for Streaming Analytics, Numenta, Redwood City, CA, 2016

[6] Das K., Detecting Patterns of Anomalies, Carnegie Mellon University, Pittsburg, PA, 2009 | MR

[7] Krizhevsky A., Convolutional Deep Belief Networks on CIFAR-10, University of Toronto, Toronto, ON, 2010

[8] Nikolov T., Recurrent neural network based language model, Brno University of Technology, Brno, Czech Republic, 2010

[9] Sak H., Senior A., Beaufays F., Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling, Google Inc., Mountain View, CA, 2014

[10] Liu X., Nielsen P. S., Regression-based Online Anomaly Detection for Smart Grid Data, Technical University of Denmark, Kgs. Lyngby, Denmark, 2016

[11] Zuev V. N., “Detection of network traffic anomalies by deep learning method”, Software products and systems, 2021, no. 1, 91–97 | DOI | MR

[12] Jean-Baptiste L., Ontologies with python, Apress, Berkeley, CA, 2021

[13] Wen T., Keyes R., Time series anomaly detection using convolutional neural networks and transfer learning, 2019, arXiv: 1905.13628

[14] Zhong C., Gursoy M.C., Velipasalar S., “Anomaly Detection and Sampling Cost Control via Hierarchical GANs”, 2020 IEEE Global Communications Conference, GLOBECOM, 2020, 1–6

[15] Malhotra P., Vig L., Shroff G. M., Agarwal P., “Long Short Term Memory Networks for Anomaly Detection in Time Series”, 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2015, Bruges, Belgium, 2015

[16] Yarushkina N., Andreev I., Moshkin V., Moshkina I., “Integration of Fuzzy OWL Ontologies and Fuzzy Time Series in the Determination of Faulty Technical Units”, Computational Science and Its Applications – ICCSA 2019, v. 11619, Lecture Notes in Computer Science, eds. Misra S. et al., Springer, Cham, 2019, 545–555 | DOI | MR

[17] Yarushkina N., Moshkin V., Klein V., Andreev I., Beksaeva E., “Hybridization of Fuzzy Inference and Self-learning Fuzzy Ontology-Based Semantic Data Analysis”, Proceedings of the First International Scientific Conference “Intelligent Information Technologies for Industry”, IITI'16, 2016, 277–285 | DOI

[18] Moshkin V., Yarushkina N., Moshkina I., “The Intelligent System for Interactive Analysis and Forecasting of Graph Data”, Intelligent and Fuzzy Systems. INFUS 2022, v. 504, Lecture Notes in Networks and Systems, eds. Kahraman C., Tolga A.C., Cevik Onar S., Cebi S., Oztaysi B., Sari I.U., Springer, Cham, 2022, 870–878 | DOI