A case-aware feature modulation framework for defect classification in power lines

Nyan Farooq Ezzulddin, Zainab Mohammed Abdulkareem, Saif Mohamed Baraa Alsabti, Raid Gaib, Ali M Elhenidy · 2026

Read A case-aware feature modulation framework for defect classification in power lines by Nyan Farooq Ezzulddin, Zainab Mohammed Abdulkareem, Saif Mohamed Baraa Alsabti, Raid Gaib, Ali M Elhenidy (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13216314.txt.

Description

Nyan Farooq Ezzulddin and co-authors present a 2026 engineering study on spotting defects in high-voltage power line insulators from photographs. Dirty or damaged insulators can trigger outages, and foot patrols are slow, so automated image checks are attractive.

Their model, built on a convolutional network backbone, handles several power line component tasks at once. Tricks include features adjusted to each case, a penalty that keeps task-specific features distinct, and self-supervised pretraining on unlabelled images. Across five defect datasets the model scored strongly on precision, recall, and accuracy, and heat maps showed it looking at physically sensible regions. The authors note weak spots with rare or subtle faults and fixed camera images, and they propose adding video and other data types.

Catalog record

CREATORNyan Farooq Ezzulddin, Zainab Mohammed Abdulkareem, Saif Mohamed Baraa Alsabti, Raid Gaib, Ali M Elhenidy
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE43 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13216314

Browse the full library · About the Tower of Babel