"Integrating Taylor-SPBO and Deep Learning in IoT for Plant Disease Detection"

What is it about?

The Internet of Things (IoT) has grown more importance in agriculture production, as it helps to observe and store up information in a large environment. The plant leaf disease condenses the quantity and quality of agricultural products. Hence, the farmer needs to find and discover the plant disease at the beginning stage. The plant disease can be present in any part, like leaves, fruits and stems. Therefore, it is an important research area to detect plant disease automatically to reduce economic or production loss. Without appropriate classification of the disease and the disease-causing mediator, the disease control process can be a waste of time and money and can lead to additional plant losses. This research developed a method named Taylor Student Psychology Based Optimization integrated Deep Q network (TSPBO-based DQN) to detect plant disease in IoT simulated system atmosphere. The nodes are randomly dispersed in the system area to collect plant images. The captured images are routed to the sink node to complete the proposed method's disease recognition scheme. The proposed method is highly efficient in classifying the plant diseases and has shown outstanding performance by acquiring high accuracy, sensitivity, specificity and remaining energy.

Featured Image

Why is it important?

Early identification of diseases in plant parts such as leaves, fruits, and stems is crucial for preventing the spread of disease and minimizing damage. This method facilitates early detection, directly impacting the quantity and quality of agricultural output. The automation of disease detection processes reduces the need for manual monitoring, making the management of plant health more efficient and less labor-intensive.

Perspectives