Semi-supervised online anomaly detection method for wireless sensor network

The invention discloses a semi-supervised online anomaly detection method for a wireless sensor network, and belongs to the technical field of wireless sensor network data reliability. According to the method, a wireless sensor network semi-supervised online anomaly detection method integrating space-time correlation and a double-inspection mechanism is adopted; the problems that a supervised learning anomaly detection algorithm needs a complete labeled data set, an unsupervised learning anomaly detection algorithm is only suitable for detecting statistical anomalies, and a semi-supervised learning anomaly detection algorithm is poor in data classification effect on uneven distribution are solved. According to the method, a small amount of labeled data is utilized to train the model, the anomaly detection accuracy in the online detection stage is high, and the Kmeans model updating algorithm provided by the invention can effectively improve the detection accuracy of the existing anomaly detection model. 本发明公开