Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 10, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

U-AttentionFlow: A Multi-Scale Invertible Attention Network for OLTC Anomaly Detection Using Acoustic Signals.

Donghyun Kim1, Hoseong Hwang1, Hochul Kim1

  • 1Department of Medical Artificial Intelligent, Eul-Ji University, Seongnam-si 13135, Gyeonggi-do, Republic of Korea.

Sensors (Basel, Switzerland)
|October 16, 2025
PubMed
Summary

Related Concept Videos

Classification of Signals01:30

Classification of Signals

1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MoEKAN: Multi-Scale Transformer-Based Gating KAN Experts Network for Time Series Forecasting.

Sensors (Basel, Switzerland)·2025
Same author

Resolving the initial contour problem of GVF snake in the sequential images.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2007
See all related articles

Early detection of On-Load Tap Changer (OLTC) faults is crucial for power grid stability. A novel deep learning model, U-AttentionFlow, effectively identifies OLTC anomalies using acoustic signals with 99.15% accuracy.

Area of Science:

  • Electrical Engineering
  • Artificial Intelligence
  • Signal Processing

Background:

  • On-Load Tap Changers (OLTCs) are vital for voltage regulation in power transformers.
  • OLTC faults can compromise power grid stability, necessitating early detection methods.

Purpose of the Study:

  • To develop a robust anomaly detection model for OLTCs using acoustic signals.
  • To enhance fault detection accuracy through advanced deep learning techniques.

Main Methods:

  • Proposed a one-class deep learning model, U-AttentionFlow, trained on normal OLTC acoustic data.
  • Integrated Squeeze-and-Excitation (SE) blocks and Convolutional Block Attention Module (CBAM) for feature enhancement.
  • Employed multihead self-attention (MHSA) and a U-Flow-style invertible structure for temporal and multi-scale feature learning.
Keywords:
OLTCU-Netanomaly detectionattention mechanismflow-based modelsmulti-scale feature fusionone-class classification

Related Experiment Videos

Last Updated: Jul 10, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Main Results:

  • Achieved an anomaly detection accuracy of 99.15% on real-world OLTC acoustic data.
  • Demonstrated the model's effectiveness in identifying deviations from normal operating patterns.
  • Validated performance under realistic voltage and load conditions.

Conclusions:

  • The U-AttentionFlow model shows outstanding performance and practical applicability for OLTC anomaly detection.
  • Acoustic signal analysis combined with deep learning offers a promising approach for predictive maintenance of power equipment.