Cutting-Edge AI for Helianthus Disease Detection: A CNN-KNN Hybrid Model

Sunflowers, which belong to the genus Helianthus, play a significant part in agriculture around the world since they supply essential food products and contribute to the preservation of biodiversity. The cultivation of these plants, however, is complicated by a number of diseases, such as rust, wilts, rot, and stem canker, any of which can have a substantial adverse effect on crop output and quality. This research paper provides a hybrid deep learning (DL) model for the accurate and automated identification of Helianthus disease that combines the convolutional neural networks (CNN) and the k-nearest neighbors (k-NN) method. Both of these algorithms are DL techniques. We construct a complete system that is capable of diagnosing diseases over a wide range of environmental variables as well as disease severities. This system makes use of a dataset that contains 50,000 high-resolution photos. The diagnostic accuracy of the model is demonstrated by its overall accuracy of 93.44%, which shows how good it is in discriminating between diseases. In order to get a better understanding of the model's performance, we also provide a layer-by-layer analysis of the resulting number of parameters, as well as a confusion matrix and an inter-class graphical comparison. In addition, the findings of the hybrid model are shown to be competitive when compared to methods that are considered to be state-of-the-art. The success of the model that was proposed demonstrates its potential to revolutionize precision agriculture by making it possible to make timely interventions and manage crops in a sustainable manner.