Accurate Analysis of Blast Disease Prediction in Rice Crop Using Artificial Neural Network Algorithm Compared with Random Forest Algorithm

The proposed work is to find the blast disease in rice crops using artificial neural network compared with random forest algorithm. To predict the rice blast illness, an artificial neural network and random forest are used with different training and testing splits. In this instance, each of the two groups’ 169 samples was used in an analysis that required a total of 10 iterations. The ClinCalc program is used as a tool to calculate the setup’s correctness for supervised learning. With Gpower setting parameters of 0.05 and 0.80, the test’s average Gpower is roughly 80%. Identifying blast disease detection in rice crops can be used to classify the presence or absence of the disease based on input features such as crop characteristics, environmental factors, and symptoms. With an independent sample T-test value of p = 0.001, artificial neural network (ANN) (91.8100%) outperforms random forest (RF) (78.1000%) in terms of both accuracy and loss, which is considered to be statistically significant. In comparison with the random forest (78.10%), artificial neural networks (91.81%) are more accurate for the selected dataset.