Detecting Anomalies for corn crop disease using Isolation forest

Today, the most challenging issue for researchers is to continue their research for crop disease using deep learning and image processing. One of the crucial detection methods used in one-class classification to find the outliers in the dataset is anomaly detection. The isolation forest approach is used in this work to discover anomalies using the corn dataset from Kaggleas a benchmark dataset. To find abnormalities in the provided dataset, this algorithm mimics a binary decision tree technique. This algorithm’s classification accuracy is 89 percent. For the corn dataset, the experimental findings of the isolation forest show improved outcomes. Other anomaly identification methods will eventually combine anomaly scores and new datasets on leaf disease.