Academic Journal
Artificial Intelligence Driven Smart Farming for Accurate Detection of Potato Diseases: A Systematic Review
| العنوان: | Artificial Intelligence Driven Smart Farming for Accurate Detection of Potato Diseases: A Systematic Review |
|---|---|
| المؤلفون: | Kaur, Avneet, Randhawa, Gurjit S., Abbas, Farhat, Ali, Mumtaz, Esau, Travis J., Farooque, Aitazaz A., Singh, Rajandeep |
| بيانات النشر: | IEEE (Institute of Electrical and Electronics Engineers) |
| سنة النشر: | 2024 |
| المجموعة: | University of Southern Queensland: USQ ePrints |
| مصطلحات موضوعية: | Artificial intelligence, deep learning, food security, machine learning, potato disease forecasting |
| الوصف: | Agriculture can ensure food security and enhance monetary benefits if practiced with modern technologies and supported with artificial intelligence (AI). Modern advancements in farming practices have revolutionized the production of food vegetation. However, crop cultivation faces several threats including insect and pest attacks and disease infections on plant leaves. For example, one of the most consumed foods vegetables universally—potatoes, are vulnerable to diseases like Late Blight (LB), Early Blight (EB), and others. These infections must be controlled to enhance food quality and yield. Conventional disease detection techniques are slow and depend on human involvement, which may be laborious and erroneous. However, AI tools, for instance, Machine Learning (ML) and Deep Learning (DL), offer precise and well-timed solutions for disease detection, classification, and eradication. A comprehensive review of literature has been conducted by examining over 400 articles to focus on 72 studies including 14 reviews publications on ML and DL models about potato disease forecasting using different techniques. It highlights the need for proficient disease control by integrating image and climate data. It further aids in addressing challenges like data availability and geographical variations. It has been learned that image-processing techniques overwhelm the existing research and have the potential to integrate meteorological data. The most widely used algorithms incorporate Support Vector Machine (SVM), Random Forest (RF), Convolutional Neural Network (CNN), and MobileNet with accuracy rates between 64.3 and 100%. The importance of accurate disease detection and eradication has been reported for food security, financial stability, and sustainable farming practices. Progressions in disease forecasts aid farmers in making informed decisions, minimizing crop losses, and reducing pesticide use through targeted application of agrochemicals with the use of AI-driven variable rate sprayers. This leads to healthier crops, ... |
| نوع الوثيقة: | article in journal/newspaper |
| وصف الملف: | application/pdf |
| اللغة: | unknown |
| Relation: | https://research.usq.edu.au/download/409ed35f92cb1356dcc8a96dc21c06b205ccf64cad20e61b655474b4b3e3a185/3756166/Artificial_Intelligence_Driven_Smart_Farming_for_Accurate_Detection_of_Potato_Diseases_A_Systematic_Review.pdf; https://doi.org/10.1109/ACCESS.2024.3510456; Kaur, Avneet, Randhawa, Gurjit S., Abbas, Farhat, Ali, Mumtaz, Esau, Travis J., Farooque, Aitazaz A. and Singh, Rajandeep. 2024. "Artificial Intelligence Driven Smart Farming for Accurate Detection of Potato Diseases: A Systematic Review." IEEE Access. 12, pp. 193902-193922. https://doi.org/10.1109/ACCESS.2024.3510456 |
| DOI: | 10.1109/ACCESS.2024.3510456 |
| الاتاحة: | https://research.usq.edu.au/item/zqy60/artificial-intelligence-driven-smart-farming-for-accurate-detection-of-potato-diseases-a-systematic-review https://research.usq.edu.au/download/409ed35f92cb1356dcc8a96dc21c06b205ccf64cad20e61b655474b4b3e3a185/3756166/Artificial_Intelligence_Driven_Smart_Farming_for_Accurate_Detection_of_Potato_Diseases_A_Systematic_Review.pdf https://doi.org/10.1109/ACCESS.2024.3510456 |
| Rights: | CC BY 4.0 |
| رقم الانضمام: | edsbas.87977EA2 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1109/ACCESS.2024.3510456 |
|---|