|
AUTHOR(S): V. Raji, E. Rajendran
|
TITLE Detecting the Growth Rate of Mealybugs Attacking Plants Using DCNN |
 PDF |
ABSTRACT Currently, many farmers, due to financial constraints, rely on natural methods to cultivate crops. However, during the crop growth stage, mealybugs a specific type of pest attack these plants, causing significant damage. Since these farmers use organic or natural pest control methods, their ability to completely prevent the spread of these pests is limited. As a result, severe infestations lead to economic losses and even the death of plants. To address this issue, we propose using DCNN (Deep Convolutional Neural Networks) and Anomaly Detection with Regression Analysis to detect the growth rate of mealybugs and provide timely solutions for controlling them. By analyzing the infestation speed and severity, this method can help farmers take preventive measures more effectively. Furthermore, by comparing our proposed approach with previous research studies “Detection of Mealybugs Disease Using Artificial Intelligence Methods”, we demonstrate that our method outperforms earlier solutions in accurately detecting and managing mealybug infestations. |
KEYWORDS DCNN (Deep Convolutional Neural Networks), Regression Analysis, Mealybug Management, Anomaly Detection, Organic Pest Control |
|
Cite this paper V. Raji, E. Rajendran. (2025) Detecting the Growth Rate of Mealybugs Attacking Plants Using DCNN. International Journal of Computers, 10, 124-132 |
|
