Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ South Ural State Uni...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Нейросетевой метод обнаружения аномалий в многомерных потоковых временных ряда

Authors: Kraeva, Ya.A.;

Нейросетевой метод обнаружения аномалий в многомерных потоковых временных ряда

Abstract

Краева Яна Александровна, к.ф.-м.н., старший преподаватель, кафедра системного программирования, Южно-Уральский государственный университет (национальный исследовательский университет) (Челябинск, Российская Федерация) Kraeva Yana Aleksandrovna, PhD in Physics and Mathematics, Senior Lecturer, Department of System Programming, South Ural State University (National Research University) (Chelyabinsk, Russian Federation) В статье рассмотрена задача детекции аномальных подпоследовательностей многомерного потокового временного ряда, элементы которого поступают в режиме реального времени, возникающая в настоящее время в широком спектре предметных областей: промышленный Интернет вещей, персональное здравоохранение и др. Предложен новый метод решения указанной задачи, получивший название mDiSSiD (Discord, Snippet, and Siamese Neural Network-based Detector of multivariate anomalies). Предложенный метод использует концепцию диссонанса временного ряда (подпоследовательность, имеющая наиболее не похожего на нее ближайшего соседа), обобщенную на многомерный случай. Под многомерным диссонансом понимается N -мерная подпоследовательность d-мерного временного ряда (где 1 ≤ N ≤ d), которая наиболее не похожа на все остальные подпоследовательности N -мерных временных рядов, полученных путем составления всевозможных сочетаний из d рядов по N . Детекция аномалий реализуется с помощью нейросетевой модели на основе сиамских нейросетей. Вычислительные эксперименты на реальных временных рядах из различных предметных областей показали, что метод mDiSSiD в среднем опережает по точности обнаружения аномалий передовые аналоги, использующие иные нейросетевые подходы (сверточные и рекуррентные нейронные сети, автоэнкодеры, генеративно-состязательные сети).The article touches upon the problem of detecting anomalous subsequences of multivariate streaming time series, where the elements arrive in real time, which currently arises in a wide range of subject domains: industrial Internet of Things, personal healthcare, etc. In the article, we introduce a novel method to solve such a problem, called mDiSSiD (Discord, Snippet, and Siamese Neural Network-based Detector of multivariate anomalies). The mDiSSiD method employs the time series discord concept (a subsequence with the most dissimilar nearest neighbor), which is generalized to the multivariate case. Multivariate discord refers to the N-dimensional subsequence of a d-dimensional time series (where 1 ≤ N ≤ d), which is the most dissimilar to all other subsequences of N -dimensional time series obtained by composing all the possible combinations of d series of N . Anomaly detection is implemented through a deep learning model based on the Siamese neural network architecture. Experimental evaluation of mDiSSiD over real time series from various subject domains showed that the proposed method is on average ahead of state-of-the-art analogs based on other deep learning approaches (convolutional and recurrent neural networks, autoencoders, and generative-adversarial networks) in terms of anomaly detection accuracy. Работа выполнена при финансовой поддержке Российского научного фонда (грант № 23-21-00465). The work was carried out with the financial support of the Russian Science Foundation (grant No. 23-21-00465).

Keywords

УДК 004.272.25, поиск аномалий, сниппет, discord, multivariate time series, Siamese neural network, snippet, УДК 004.032.24, диссонанс, сиамская нейронная сеть, УДК 004.421, anomaly detection, многомерный временной ряд

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green