Table 4 Performance comparison.
Model | Accuracy (%) | Yield distribution | Computational outcome |
|---|---|---|---|
Proposed Random Forest Classifier | 90.1 | 100,000 | Edge based devices support |
AI enabled IoT soft sensor and deep learning architecture | 89 | 54,000 | Computationally expensive |
LoRa | 87.2 | 56,000 | Computationally expensive |
Adaptive AI with self-learning method | 88 | 77,863 | No device support |
XGBoost | 88 | 66,289 | Prone to overfitting |
ANN | 89.27 | 79,823 | Computationally expensive |
SVM | 87.29 | 50,624 | More energy use |
