A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves
This study presents a novel approach for the detection and severity assessment of pest-induced damage in maize plants, focusing on the <i>Zyginidia pullula</i> pest. A newly developed dataset is utilized, where maize plant images are initially classified into two primary categories: heal...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/10/5432 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711804400271360 |
|---|---|
| author | Havva Esra Bakbak Caner Balım Aydogan Savran |
| author_facet | Havva Esra Bakbak Caner Balım Aydogan Savran |
| author_sort | Havva Esra Bakbak |
| collection | DOAJ |
| description | This study presents a novel approach for the detection and severity assessment of pest-induced damage in maize plants, focusing on the <i>Zyginidia pullula</i> pest. A newly developed dataset is utilized, where maize plant images are initially classified into two primary categories: healthy and infected. Subsequently, infected samples are categorized into three distinct severity levels: low, medium, and high. Both traditional and deep learning-based feature extraction techniques are employed to achieve this. Specifically, hand-crafted feature extraction methods, including Gabor filters, Gray Level Co-occurrence Matrix, and Hue-Saturation-Value color space, are combined with CNN-based models such as ResNet-50, DenseNet-201, and EfficientNet-B2. The maize images undergo preprocessing and segmentation using Contrast Limited Adaptive Histogram Equalization and U2Net, respectively. Extracted features are then fused and subjected to Principal Component Analysis for dimensionality reduction. The classification task is performed using Support Vector Machines, Random Forest, and Artificial Neural Networks, ensuring robust and accurate detection. The experimental results demonstrate that the proposed hybrid approach outperforms individual feature extraction methods, achieving a classification accuracy of up to 92.55%. Furthermore, integrating multiple feature representations significantly enhances the model’s ability to differentiate between varying levels of pest damage. Unlike previous studies that primarily focus on plant disease detection, this research uniquely addresses the quantification of pest-induced damage, offering a valuable tool for precision agriculture. The findings of this study contribute to the development of automated, scalable, and efficient pest monitoring systems, which are crucial for minimizing yield losses and improving agricultural sustainability. |
| format | Article |
| id | doaj-art-9dccc8d63a384ea1a18b6d4f00dd018e |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-9dccc8d63a384ea1a18b6d4f00dd018e2025-08-20T03:14:32ZengMDPI AGApplied Sciences2076-34172025-05-011510543210.3390/app15105432A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize LeavesHavva Esra Bakbak0Caner Balım1Aydogan Savran2Department of Electrical and Electronic Engineering, Ege University, Izmir 35040, TurkeyDepartment of Software Engineering, Afyon Kocatepe University, Afyon 03204, TurkeyDepartment of Electrical and Electronic Engineering, Ege University, Izmir 35040, TurkeyThis study presents a novel approach for the detection and severity assessment of pest-induced damage in maize plants, focusing on the <i>Zyginidia pullula</i> pest. A newly developed dataset is utilized, where maize plant images are initially classified into two primary categories: healthy and infected. Subsequently, infected samples are categorized into three distinct severity levels: low, medium, and high. Both traditional and deep learning-based feature extraction techniques are employed to achieve this. Specifically, hand-crafted feature extraction methods, including Gabor filters, Gray Level Co-occurrence Matrix, and Hue-Saturation-Value color space, are combined with CNN-based models such as ResNet-50, DenseNet-201, and EfficientNet-B2. The maize images undergo preprocessing and segmentation using Contrast Limited Adaptive Histogram Equalization and U2Net, respectively. Extracted features are then fused and subjected to Principal Component Analysis for dimensionality reduction. The classification task is performed using Support Vector Machines, Random Forest, and Artificial Neural Networks, ensuring robust and accurate detection. The experimental results demonstrate that the proposed hybrid approach outperforms individual feature extraction methods, achieving a classification accuracy of up to 92.55%. Furthermore, integrating multiple feature representations significantly enhances the model’s ability to differentiate between varying levels of pest damage. Unlike previous studies that primarily focus on plant disease detection, this research uniquely addresses the quantification of pest-induced damage, offering a valuable tool for precision agriculture. The findings of this study contribute to the development of automated, scalable, and efficient pest monitoring systems, which are crucial for minimizing yield losses and improving agricultural sustainability.https://www.mdpi.com/2076-3417/15/10/5432machine learningdeep learningfeature extractionpest damage detectionimage segmentationhybrid classification |
| spellingShingle | Havva Esra Bakbak Caner Balım Aydogan Savran A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves Applied Sciences machine learning deep learning feature extraction pest damage detection image segmentation hybrid classification |
| title | A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves |
| title_full | A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves |
| title_fullStr | A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves |
| title_full_unstemmed | A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves |
| title_short | A Hybrid Machine Learning Approach for Detecting and Assessing <i>Zyginidia pullula</i> Damage in Maize Leaves |
| title_sort | hybrid machine learning approach for detecting and assessing i zyginidia pullula i damage in maize leaves |
| topic | machine learning deep learning feature extraction pest damage detection image segmentation hybrid classification |
| url | https://www.mdpi.com/2076-3417/15/10/5432 |
| work_keys_str_mv | AT havvaesrabakbak ahybridmachinelearningapproachfordetectingandassessingizyginidiapullulaidamageinmaizeleaves AT canerbalım ahybridmachinelearningapproachfordetectingandassessingizyginidiapullulaidamageinmaizeleaves AT aydogansavran ahybridmachinelearningapproachfordetectingandassessingizyginidiapullulaidamageinmaizeleaves AT havvaesrabakbak hybridmachinelearningapproachfordetectingandassessingizyginidiapullulaidamageinmaizeleaves AT canerbalım hybridmachinelearningapproachfordetectingandassessingizyginidiapullulaidamageinmaizeleaves AT aydogansavran hybridmachinelearningapproachfordetectingandassessingizyginidiapullulaidamageinmaizeleaves |