IMPROVING ALGORITHMS FOR DIAGNOSING SYSTEM STATUS AND DETECTING ANOMALIES BASED ON INTELLIGENT ANALYSIS OF DIGITAL IMAGES AND SIGNALS

Main Article Content

I.J. Perdebayeva S.B. Abdullaev

Abstract

This article examines issues of early detection of malfunctions occurring during the operation of complex technical systems and equipment, as well as improving the process of system state diagnostics. The limitations of traditional threshold methods are analyzed, and new approaches based on multimodal intelligent analysis of digital signals and visual images are proposed. Ways to increase the efficiency of anomaly detection using Deep Learning and auto-coding architectures are substantiated.


 

Article Details

Section
Articles

References

Pang G., Cao C., Cheng L., van den Hengel A. Deep Learning for Anomaly Detection: A Review // ACM Computing Surveys. - 2021. Vol. 54, No. 2. – P. 1–38.

Chandola V., Banerjee A., Kumar V. Anomaly detection: A survey // ACM Computing Surveys (CSUR). – 2009. Vol. 41, No. 3. – P. 1–58.

Goodfellow I., Bengio Y., Courville A. Deep Learning. – Cambridge: MIT Press. - 800 p.

Charu C. Aggarwal. Outlier Analysis. - 2nd ed. - Springer, 2017. - 474 p.

Karimov S.A., Yakubov J.Kh. Fundamentals of digital signal and image processing. - Tashkent: "Fan va texnologiya," 2022. - 260 p.

Malhotra P., Vig L., Shroff G., Agarwal P. Long Short Term Memory Networks for Anomaly Detection in Time Series // European Symposium on Artificial Neural Networks (ESANN). – 2015. – P. 89–94.

Bermudez-Cameo J., et al. Intelligent anomaly detection in industrial systems using multimodal sensor data // Computers in Industry. - 2023. Vol. 145. – P. 103812.