Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI
Sunflower is a crop that has many economic values and ornamental usages. However, its production can be hampered due to various diseases such as downy mildew, gray mold, and leaf scars, and it is challenging for farmers to identify disease-prone conditions with traditional approaches. Thus, a comput...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/10/2241 |
| _version_ | 1797599198400479232 |
|---|---|
| author | Promila Ghosh Amit Kumar Mondal Sajib Chatterjee Mehedi Masud Hossam Meshref Anupam Kumar Bairagi |
| author_facet | Promila Ghosh Amit Kumar Mondal Sajib Chatterjee Mehedi Masud Hossam Meshref Anupam Kumar Bairagi |
| author_sort | Promila Ghosh |
| collection | DOAJ |
| description | Sunflower is a crop that has many economic values and ornamental usages. However, its production can be hampered due to various diseases such as downy mildew, gray mold, and leaf scars, and it is challenging for farmers to identify disease-prone conditions with traditional approaches. Thus, a computerized model composed of vision, artificial intelligence, and machine learning is the demand of the age to detect diseases in plants efficiently. In this paper, we develop a hybrid model with transfer learning (TL) and a simple CNN using a small dataset for detecting sunflower diseases. Out of the eight models tested on the dataset of four different classes (downy mildew, gray mold, leaf scars, and fresh leaf), the VGG19 + CNN hybrid model achieves the best results in terms of precision, recall, F1-score, accuracy, Hamming loss, Matthews coefficient, Jaccard score, and Cohen’s kappa metrics. The experimental outcomes show that the proposed model provides better precision, recall, and accuracy than other approaches on the benchmark dataset. |
| first_indexed | 2024-03-11T03:32:22Z |
| format | Article |
| id | doaj.art-74ce59a547f94dada42a1cf1f4fbc43c |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T03:32:22Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-74ce59a547f94dada42a1cf1f4fbc43c2023-11-18T02:18:04ZengMDPI AGMathematics2227-73902023-05-011110224110.3390/math11102241Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AIPromila Ghosh0Amit Kumar Mondal1Sajib Chatterjee2Mehedi Masud3Hossam Meshref4Anupam Kumar Bairagi5Computer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshComputer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshComputer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshDepartment of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi ArabiaDepartment of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi ArabiaComputer Science and Engineering Discipline, Khulna University, Khulna 9208, BangladeshSunflower is a crop that has many economic values and ornamental usages. However, its production can be hampered due to various diseases such as downy mildew, gray mold, and leaf scars, and it is challenging for farmers to identify disease-prone conditions with traditional approaches. Thus, a computerized model composed of vision, artificial intelligence, and machine learning is the demand of the age to detect diseases in plants efficiently. In this paper, we develop a hybrid model with transfer learning (TL) and a simple CNN using a small dataset for detecting sunflower diseases. Out of the eight models tested on the dataset of four different classes (downy mildew, gray mold, leaf scars, and fresh leaf), the VGG19 + CNN hybrid model achieves the best results in terms of precision, recall, F1-score, accuracy, Hamming loss, Matthews coefficient, Jaccard score, and Cohen’s kappa metrics. The experimental outcomes show that the proposed model provides better precision, recall, and accuracy than other approaches on the benchmark dataset.https://www.mdpi.com/2227-7390/11/10/2241sunflower diseasestransfer learningdeep learninghybrid modelexplainable AILIME |
| spellingShingle | Promila Ghosh Amit Kumar Mondal Sajib Chatterjee Mehedi Masud Hossam Meshref Anupam Kumar Bairagi Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI Mathematics sunflower diseases transfer learning deep learning hybrid model explainable AI LIME |
| title | Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI |
| title_full | Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI |
| title_fullStr | Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI |
| title_full_unstemmed | Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI |
| title_short | Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI |
| title_sort | recognition of sunflower diseases using hybrid deep learning and its explainability with ai |
| topic | sunflower diseases transfer learning deep learning hybrid model explainable AI LIME |
| url | https://www.mdpi.com/2227-7390/11/10/2241 |
| work_keys_str_mv | AT promilaghosh recognitionofsunflowerdiseasesusinghybriddeeplearninganditsexplainabilitywithai AT amitkumarmondal recognitionofsunflowerdiseasesusinghybriddeeplearninganditsexplainabilitywithai AT sajibchatterjee recognitionofsunflowerdiseasesusinghybriddeeplearninganditsexplainabilitywithai AT mehedimasud recognitionofsunflowerdiseasesusinghybriddeeplearninganditsexplainabilitywithai AT hossammeshref recognitionofsunflowerdiseasesusinghybriddeeplearninganditsexplainabilitywithai AT anupamkumarbairagi recognitionofsunflowerdiseasesusinghybriddeeplearninganditsexplainabilitywithai |