An Abnormal Detection and Early Warning System for Sugarcane Diseases Based on Unsupervised Learning

Considering the problem of scarce annotation data and diverse disease types in sugarcane disease detection, this paper proposes a detection and early warning system for sugarcane disease abnormalities based on unsupervised learning features. First, two unsupervised learning methods, clustering and self-encoder, are used for feature extraction, and then these features are fused to form a comprehensive feature vector. Then, the local anomaly factor (LOF) algorithm is used to detect the abnormal condition of sugarcane diseases. The experimental results show that compared with the traditional supervised learning method, the proposed method has a significant improvement in both accuracy and recall rate, which effectively solves the problem of insufficient annotation data in sugarcane disease detection. This method has high accuracy and stability in the abnormal detection and early warning of sugarcane diseases, and can provide strong support for the prevention and control of sugarcane diseases.