محفوظ في:
| المؤلفون الرئيسيون: | , |
|---|---|
| التنسيق: | Recurso digital |
| اللغة: | الإنجليزية |
| منشور في: |
Zenodo
2025
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://doi.org/10.5281/zenodo.17762603 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
جدول المحتويات:
- <h3><span lang="EN-US">Abstract</span></h3> <p><span lang="EN-US">Leaf diseases pose a severe and multifaceted threat to the productivity of key cash crops in the Tirupattur district, notably <span>Tomato</span> (<em>Solanum lycopersicum</em>), <span>Brinjal</span> (<em>Solanum melongena</em>), <span>Chilli</span> (<em>Capsicum annuum</em>), and <span>Lady's Finger</span> (<em>Abelmoschus esculentus</em>). Traditional detection methods fail to scale effectively across this crop diversity. This paper proposes a novel <span>Stacked Generalization Ensemble Deep Learning (DL) model</span> to establish a single, robust diagnostic architecture for simultaneously classifying multiple diseases across all four species. The architecture utilizes <span>Transfer Learning</span> on three distinct Convolutional Neural Network (CNN) feature extractors: <span>EfficientNetB3</span>, <span>ResNet101</span>, and <span>DenseNet169</span>. Their unique, high-dimensional feature vectors are concatenated and input to a non-linear <span>Support Vector Machine (SVM)</span>, which acts as the discriminative Meta-Learner. Tested on a comprehensive, locally augmented dataset of 18,000 images, the ensemble model achieved an outstanding <span>99.25% overall classification accuracy</span> and an <span>F1-Score of 99.23%</span>. This performance significantly surpassed the best individual baseline model, DenseNet169, by <span>0.87%</span>. Detailed feature visualization using t-SNE confirms the ensemble's ability to resolve inter-species symptom ambiguities, validating the method’s efficiency and superior generalization for complex agricultural environments.</span></p> <p><strong><span lang="EN-US">Keywords:</span></strong><span lang="EN-US"> </span><span lang="EN-US">Deep Learning, Ensemble Learning, Stacking Generalization, Multi-Crop, Solanaceae, Malvaceae, Support Vector Machine, Transfer Learning.</span></p>