Next Article in Journal
Combining the Strengths of LLMs and Persuasive Technology to Combat Cyberhate
Previous Article in Journal
A Framework for Domain-Specific Dataset Creation and Adaptation of Large Language Models
Previous Article in Special Issue
New Predictive Models for the Computation of Reinforced Concrete Columns Shear Strength
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

ViX-MangoEFormer: An Enhanced Vision Transformer–EfficientFormer and Stacking Ensemble Approach for Mango Leaf Disease Recognition with Explainable Artificial Intelligence

1
Department of Information Technology, Westcliff University, Irvine, CA 92614, USA
2
Department of Computer Science, Westcliff University, Irvine, CA 92614, USA
3
Department of Business Administration, International American University, 3440 Wilshire Blvd STE 1000, Los Angeles, CA 90010, USA
4
Department of Engineering Management, Westcliff University, Irvine, CA 92614, USA
5
Department of Computer Science and Engineering, East West University, Dhaka 1212, Bangladesh
6
School of Computing and Information Systems, Athabasca University, Athabasca, AB T9S 3A3, Canada
*
Authors to whom correspondence should be addressed.
Computers 2025, 14(5), 171; https://doi.org/10.3390/computers14050171
Submission received: 29 March 2025 / Revised: 22 April 2025 / Accepted: 28 April 2025 / Published: 2 May 2025
(This article belongs to the Special Issue Deep Learning and Explainable Artificial Intelligence)

Abstract

Mango productivity suffers greatly from leaf diseases, leading to economic and food security issues. Current visual inspection methods are slow and subjective. Previous Deep-Learning (DL) solutions have shown promise but suffer from imbalanced datasets, modest generalization, and limited interpretability. To address these challenges, this study introduces the ViX‑MangoEFormer, which combines convolutional kernels and self-attention to effectively diagnose multiple mango leaf conditions in both balanced and imbalanced image sets. To benchmark against ViX‑MangoEFormer, we developed a stacking ensemble model (MangoNet-Stack) that utilizes five transfer learning networks as base learners. All models were trained with Grad‑CAM produced pixel‑level explanations. In a combined dataset of 25,530 images, ViX-MangoEFormer achieved an F1 score of 99.78% and a Matthews Correlation Coefficient (MCC) of 99.34%. This performance consistently outperformed individual pre-trained models and MangoNet-Stack. Additionally, data augmentation has improved the performance of every architecture compared to its non-augmented version. Cross‑domain tests on morphologically similar crop leaves confirmed strong generalization. Our findings validate the effectiveness of transformer attention and XAI in mango leaf disease detection. ViX‑MangoEFormer is deployed as a web application that delivers real‑time predictions, probability scores, and visual rationales. The system enables growers to respond quickly and enhances large-scale smart crop health monitoring.
Keywords: Vision Transformer (ViT); explainable AI (XAI); ensemble learning; precision agriculture; mango leaf classification Vision Transformer (ViT); explainable AI (XAI); ensemble learning; precision agriculture; mango leaf classification

Share and Cite

MDPI and ACS Style

Noman, A.A.; Hossain, A.; Sakib, A.; Debnath, J.; Fardin, H.; Sakib, A.A.; Haque, R.; Ahmed, M.R.; Reza, A.W.; Dewan, M.A.A. ViX-MangoEFormer: An Enhanced Vision Transformer–EfficientFormer and Stacking Ensemble Approach for Mango Leaf Disease Recognition with Explainable Artificial Intelligence. Computers 2025, 14, 171. https://doi.org/10.3390/computers14050171

AMA Style

Noman AA, Hossain A, Sakib A, Debnath J, Fardin H, Sakib AA, Haque R, Ahmed MR, Reza AW, Dewan MAA. ViX-MangoEFormer: An Enhanced Vision Transformer–EfficientFormer and Stacking Ensemble Approach for Mango Leaf Disease Recognition with Explainable Artificial Intelligence. Computers. 2025; 14(5):171. https://doi.org/10.3390/computers14050171

Chicago/Turabian Style

Noman, Abdullah Al, Amira Hossain, Anamul Sakib, Jesika Debnath, Hasib Fardin, Abdullah Al Sakib, Rezaul Haque, Md. Redwan Ahmed, Ahmed Wasif Reza, and M. Ali Akber Dewan. 2025. "ViX-MangoEFormer: An Enhanced Vision Transformer–EfficientFormer and Stacking Ensemble Approach for Mango Leaf Disease Recognition with Explainable Artificial Intelligence" Computers 14, no. 5: 171. https://doi.org/10.3390/computers14050171

APA Style

Noman, A. A., Hossain, A., Sakib, A., Debnath, J., Fardin, H., Sakib, A. A., Haque, R., Ahmed, M. R., Reza, A. W., & Dewan, M. A. A. (2025). ViX-MangoEFormer: An Enhanced Vision Transformer–EfficientFormer and Stacking Ensemble Approach for Mango Leaf Disease Recognition with Explainable Artificial Intelligence. Computers, 14(5), 171. https://doi.org/10.3390/computers14050171

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop