Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification

Abstract Early detection of plant diseases is crucial in smart agriculture to prevent significant crop losses and reduce reliance on chemical pesticides. While many existing methods leverage customized neural network architectures or transfer learning, they often suffer from limited accuracy, model...

Full description

Saved in:
Bibliographic Details
Main Authors: Silpa Padmanabhuni, Pradeepini Gera
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Sustainability
Subjects:
Online Access:https://doi.org/10.1007/s43621-025-01648-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344505471303680
author Silpa Padmanabhuni
Pradeepini Gera
author_facet Silpa Padmanabhuni
Pradeepini Gera
author_sort Silpa Padmanabhuni
collection DOAJ
description Abstract Early detection of plant diseases is crucial in smart agriculture to prevent significant crop losses and reduce reliance on chemical pesticides. While many existing methods leverage customized neural network architectures or transfer learning, they often suffer from limited accuracy, model interpretability, and dataset imbalance. This study proposes a novel hybrid model that integrates a pre-trained Inception v3 architecture for feature extraction with a Bayesian-optimized activation strategy and a fine-tuned Random Forest classifier for final decision-making. The architecture involves freezing specific layers within Inception v3 to retain essential low-level features while adapting high-level features for the target domain. Bayesian optimization is used to identify and combine optimal activation functions, enhancing the network's capacity to learn complex disease patterns from tomato leaf images. The extracted features are then classified using a Random Forest model that is tuned for performance on imbalanced data using class weights and key hyperparameters. The proposed approach was evaluated on a multi-class dataset comprising 10 categories, including 9 diseased and 1 healthy class of tomato leaves from the PlantVillage dataset. Results show that the model achieves a classification accuracy of 99.6%, representing a + 5.4% improvement over standard transfer learning techniques. The integration of Bayesian-optimized activations and a tuned Random Forest enhances both precision and robustness across classes, including minority ones. This design not only improves accuracy but also supports a more balanced and interpretable classification process. The model demonstrates significant potential for real-world agricultural applications, particularly where early and accurate disease detection is essential for timely intervention and improved crop management.
format Article
id doaj-art-ac47f4fd1f0941bdbc95c392fe67ad9e
institution Kabale University
issn 2662-9984
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Sustainability
spelling doaj-art-ac47f4fd1f0941bdbc95c392fe67ad9e2025-08-20T03:42:39ZengSpringerDiscover Sustainability2662-99842025-07-016113110.1007/s43621-025-01648-1Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identificationSilpa Padmanabhuni0Pradeepini Gera1Department of Computer Science and Engineering, Koneru Lakshmaiah Education FoundationDepartment of Computer Science and Engineering, Koneru Lakshmaiah Education FoundationAbstract Early detection of plant diseases is crucial in smart agriculture to prevent significant crop losses and reduce reliance on chemical pesticides. While many existing methods leverage customized neural network architectures or transfer learning, they often suffer from limited accuracy, model interpretability, and dataset imbalance. This study proposes a novel hybrid model that integrates a pre-trained Inception v3 architecture for feature extraction with a Bayesian-optimized activation strategy and a fine-tuned Random Forest classifier for final decision-making. The architecture involves freezing specific layers within Inception v3 to retain essential low-level features while adapting high-level features for the target domain. Bayesian optimization is used to identify and combine optimal activation functions, enhancing the network's capacity to learn complex disease patterns from tomato leaf images. The extracted features are then classified using a Random Forest model that is tuned for performance on imbalanced data using class weights and key hyperparameters. The proposed approach was evaluated on a multi-class dataset comprising 10 categories, including 9 diseased and 1 healthy class of tomato leaves from the PlantVillage dataset. Results show that the model achieves a classification accuracy of 99.6%, representing a + 5.4% improvement over standard transfer learning techniques. The integration of Bayesian-optimized activations and a tuned Random Forest enhances both precision and robustness across classes, including minority ones. This design not only improves accuracy but also supports a more balanced and interpretable classification process. The model demonstrates significant potential for real-world agricultural applications, particularly where early and accurate disease detection is essential for timely intervention and improved crop management.https://doi.org/10.1007/s43621-025-01648-1Merge operationTransfer learningInceptionBayesian optimizationActivatorsRandom forest
spellingShingle Silpa Padmanabhuni
Pradeepini Gera
Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
Discover Sustainability
Merge operation
Transfer learning
Inception
Bayesian optimization
Activators
Random forest
title Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
title_full Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
title_fullStr Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
title_full_unstemmed Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
title_short Bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
title_sort bayesian optimized deep learning and ensemble classification approach for multiclass plant disease identification
topic Merge operation
Transfer learning
Inception
Bayesian optimization
Activators
Random forest
url https://doi.org/10.1007/s43621-025-01648-1
work_keys_str_mv AT silpapadmanabhuni bayesianoptimizeddeeplearningandensembleclassificationapproachformulticlassplantdiseaseidentification
AT pradeepinigera bayesianoptimizeddeeplearningandensembleclassificationapproachformulticlassplantdiseaseidentification