Results and Discussion
The prototype is reviewed through model assessment, module testing and functional examination of the web interface.
Irrigation Results
The irrigation model produced higher watering recommendations when soil moisture was low and temperature was high. Mean Absolute Error, Mean Squared Error and Root Mean Squared Error can be used to compare predicted and expected values.
Disease Detection Results
The image model distinguishes healthy leaves from visible disease categories. Accuracy, precision, recall and F1-score provide a balanced view of performance.
Testing Process
- Unit testing of individual modules
- Integration testing across data collection, processing and display
- Functional testing of navigation and outputs
- Review of clarity, responsiveness and usability
Discussion
The findings suggest that intelligent monitoring can improve gardening decisions. Sensor-based irrigation supports water conservation by responding to actual conditions, while image analysis can provide an earlier warning of visible plant problems. Limitations remain where images are unclear, symptoms overlap or the model encounters a plant species that was not represented in training.
Traditional and Intelligent Approaches
| Area | Traditional Method | Proposed System |
|---|---|---|
| Monitoring | Periodic manual checks | Frequent sensor readings |
| Irrigation | Experience-based schedule | Environmental-data prediction |
| Disease recognition | Visual inspection | Image-supported classification |
| Records | Manual and inconsistent | Structured digital presentation |