Table 1.
Research on smart horticulture.
Fig 1.
DWC setup of the system.
Fig 2.
Block diagram of the system.
Fig 3.
Hardware architecture of the system.
Table 2.
List of entities.
Fig 4.
Software architecture of the system.
Fig 5.
Usecase diagram of the mobile application.
Fig 6.
A DL workflow for plant disease identification.
Fig 7.
Dataset sample for disease detection.
Fig 8.
DL pipeline for plant disease detection, from initial leaf image acquisition to the final classification of the leaf’s health status.
Fig 9.
Flowchart for image-based disease prediction process.
Fig 10.
Prototype of the system.
Table 3.
Cost estimation of current study.
Fig 11.
Sensor data stored in a database.
Fig 12.
Plant details features.
Fig 13.
Live sensor data.
Fig 14.
Notification for unwanted situation.
Fig 15.
Disease detection and solution providing.
Table 4.
Different model performance metrics comparison with HCNet.
Table 5.
HCNet model performance by disease type.
Table 6.
Expanded model comparison table: complexity, size, time, and efficiency.
Fig 16.
Graphs of model training with dynamics epochs.
Fig 17.
Classification outcomes for plant leaf diseases, actual conditions with predicted labels and associated confidence scores.
Fig 18.
Survey report representation.