Channel Attention for Fusarium Head Blight Detection in Hyperspectral Images

Lily Akpanke, Dustin van der Haar, Hima Vadapalli

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This research enhances Fusarium Head Blight (FHB) detection in hyperspectral images using a Deep Convolutional Neural Network (DCNN) with Principal Component Analysis (PCA) and a Spectral Attention Module (SAM). By reducing spectral dimensionality with PCA and applying channel attention, the model improves feature representation. Tested on the AI for Agriculture 2024 dataset, it achieved 97.06% accuracy, outperforming the baseline’s 81.76%. Ablation studies confirmed PCA’s key role, while SAM had limited impact. These results highlight the benefits of spectral feature selection for more precise and scalable agricultural disease monitoring.

Original languageEnglish
Title of host publicationArtificial Intelligence and Soft Computing - 24th International Conference, ICAISC 2025, Proceedings
EditorsLeszek Rutkowski, Rafal Scherer, Marcin Korytkowski, Witold Pedrycz, Ryszard Tadeusiewicz, Jacek M. Zurada
PublisherSpringer Science and Business Media Deutschland GmbH
Pages281-294
Number of pages14
ISBN (Print)9783032037077
DOIs
Publication statusPublished - 2026
Event24th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2025 - Zakopane, Poland
Duration: 22 Jun 202526 Jun 2025

Publication series

NameLecture Notes in Computer Science
Volume15949 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference24th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2025
Country/TerritoryPoland
CityZakopane
Period22/06/2526/06/25

Keywords

  • Attention
  • Deep Learning
  • Fusarium Head Blight
  • Hyperspectral

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Channel Attention for Fusarium Head Blight Detection in Hyperspectral Images'. Together they form a unique fingerprint.

Cite this