YOLO-E3CA: An Ensemble YOLOv8 Framework with Coordinate Attention for Automated Detection of Karanda (Carissa carandas) Leaf Diseases

DOI

10.2991/978-94-6239-664-7_59How to use a DOI?

Keywords

Deep learning; Precision agriculture; Object detection; YOLOv8n; Coordinate attention

Abstract

Karanda (Carissa carandas), a significant tropical fruit crop of South Asia, faces remarkable yield and quality losses due to foliar fungal and bacterial diseases. Traditional methods of disease detection are slow, subjective, and inaccurate, resulting in late interventions and significant agricultural losses. This study presents an early curated and annotated Karanda Leaf Disease Datasets to advance research in automated disease detection. We present YOLO-E3CA (YOLOv8 Ensemble of 3 with Coordinate Attention), a novel network structure that consists of three different YOLOv8 version models with various hyperparameters, combined by a Coordinate Attention mechanism for enhancing spatial and channel feature representation. The model employs an advanced augmentation pipeline simulating diverse weather conditions and a custom training strategy to ensure robust generalization under noisy and fuzzy environments. With 98.5% mean average precision (mAP@50), YOLO-E3CA provides an accurate early diagnosis with a real-time web interface for practical accessibility. This study is the first to propose detecting Karanda leaf disease using ensemble learning and an attention mechanism in order to manage crops sustainably. In the future, we expect to diversify the deployment of our dataset and develop a mobile application for on-site inspection, providing affordable solutions for precision agriculture in extreme environmental conditions.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Amit Kumar Ghosh
AU  - Md Majidul Kabir
AU  - Shahriar Marjan
AU  - Deepu Bhowmik
AU  - Rejowan Arifin Nayeem
AU  - Md Assaduzzaman
PY  - 2026
DA  - 2026/06/08
TI  - YOLO-E3CA: An Ensemble YOLOv8 Framework with Coordinate Attention for Automated Detection of Karanda (Carissa carandas) Leaf Diseases
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 857
EP  - 871
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_59
DO  - 10.2991/978-94-6239-664-7_59
ID  - Ghosh2026
ER  -