Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification
Utilizing modern deep learning techniques for image processing and data classification holds immense promise for yielding significant outcomes. Consequently, deep learning-based approaches have demonstrated successful applications in agricultural contexts, particularly in tasks such as image classif...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gazi University
2025-06-01
|
| Series: | Gazi Üniversitesi Fen Bilimleri Dergisi |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/tr/pub/gujsc/issue/77315/1632938 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849221875310264320 |
|---|---|
| author | Engin Eşme Muhammed Arif Şen Halil Çimen |
| author_facet | Engin Eşme Muhammed Arif Şen Halil Çimen |
| author_sort | Engin Eşme |
| collection | DOAJ |
| description | Utilizing modern deep learning techniques for image processing and data classification holds immense promise for yielding significant outcomes. Consequently, deep learning-based approaches have demonstrated successful applications in agricultural contexts, particularly in tasks such as image classification and data analysis. This study focuses on classifying agricultural crop images, which often bear close resemblance, employing 17 distinct deep learning models and dynamic voting. Initially, the paper provides a concise overview of the dataset and the deep learning methodologies employed. Subsequently, the training and testing phases are carried out effectively. The dataset comprises a total of 804 images depicting five different types of crops: jute, maize, rice, sugarcane, and wheat. To ensure robustness, 10-fold cross-validation is employed, and experiments are conducted consistently across all models using the same sample sets. The results obtained report which models can more accurately detect and classify agricultural crop images. Further, the proposed ensemble approach improves accuracy and ensures greater robustness and stability. According to the experimental findings, Shufflenet achieved the highest individual accuracy of 98.63% on the test set, but the ensemble approach increased this value to 99.75%. |
| format | Article |
| id | doaj-art-184b15dcbc2b412b8e68fe69610c0aa6 |
| institution | Kabale University |
| issn | 2147-9526 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Gazi University |
| record_format | Article |
| series | Gazi Üniversitesi Fen Bilimleri Dergisi |
| spelling | doaj-art-184b15dcbc2b412b8e68fe69610c0aa62025-08-26T11:31:00ZengGazi UniversityGazi Üniversitesi Fen Bilimleri Dergisi2147-95262025-06-0113265366410.29109/gujsc.1632938 Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop ClassificationEngin Eşme 0https://orcid.org/0000-0001-9012-6587Muhammed Arif Şen1https://orcid.org/0000-0002-6081-2102Halil Çimen2https://orcid.org/0000-0003-0104-3005KONYA TECHNICAL UNIVERSITYKONYA TECHNICAL UNIVERSITYKONYA TECHNICAL UNIVERSITYUtilizing modern deep learning techniques for image processing and data classification holds immense promise for yielding significant outcomes. Consequently, deep learning-based approaches have demonstrated successful applications in agricultural contexts, particularly in tasks such as image classification and data analysis. This study focuses on classifying agricultural crop images, which often bear close resemblance, employing 17 distinct deep learning models and dynamic voting. Initially, the paper provides a concise overview of the dataset and the deep learning methodologies employed. Subsequently, the training and testing phases are carried out effectively. The dataset comprises a total of 804 images depicting five different types of crops: jute, maize, rice, sugarcane, and wheat. To ensure robustness, 10-fold cross-validation is employed, and experiments are conducted consistently across all models using the same sample sets. The results obtained report which models can more accurately detect and classify agricultural crop images. Further, the proposed ensemble approach improves accuracy and ensures greater robustness and stability. According to the experimental findings, Shufflenet achieved the highest individual accuracy of 98.63% on the test set, but the ensemble approach increased this value to 99.75%.https://dergipark.org.tr/tr/pub/gujsc/issue/77315/1632938deep learningdynamic votingcrop classification |
| spellingShingle | Engin Eşme Muhammed Arif Şen Halil Çimen Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification Gazi Üniversitesi Fen Bilimleri Dergisi deep learning dynamic voting crop classification |
| title | Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification |
| title_full | Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification |
| title_fullStr | Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification |
| title_full_unstemmed | Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification |
| title_short | Dynamic Voting-Based Ensemble Deep Learning for Closely Resembling Crop Classification |
| title_sort | dynamic voting based ensemble deep learning for closely resembling crop classification |
| topic | deep learning dynamic voting crop classification |
| url | https://dergipark.org.tr/tr/pub/gujsc/issue/77315/1632938 |
| work_keys_str_mv | AT enginesme dynamicvotingbasedensembledeeplearningforcloselyresemblingcropclassification AT muhammedarifsen dynamicvotingbasedensembledeeplearningforcloselyresemblingcropclassification AT halilcimen dynamicvotingbasedensembledeeplearningforcloselyresemblingcropclassification |