Work

Identification of Anomalies in the Work Intelligent Metering Devices Based on Modeling of Reference Functioning

Year: 2026

Type: article

Abstract: The article considers event-oriented data flows and their features. It is shown that such data are characterized by high dimension and complex time structure. An approach based on the use of a recurrent autoencoder is proposed to simulate normal behavior and identify deviations from the reconstruction error. The method makes it possible to effectively detect abnormal conditions, including potential cases of unauthorized exposure. The results are confirmed on samples of real data.

Source: Applied Mathematics and Fundamental Informatics

DOI: 10.25206/2311-4908-2026-13-2-18-24

Authors: E. A. VALIKOVA, M. I. GUNENKOV

Institution: Omsk State Technical University

Language: English

Topic: Anomaly Detection Techniques and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W7167689656

FWCI:

Cites:

Cited by:

Related to: 10