Research Article
TS-PADM: Anomaly Detection Model of Wireless Sensors Based on Spatial-Temporal Feature Points
Algorithm 1
Anomaly detection algorithm based on spatial-temporal features.
Input: a feature set of detection points | Output: the probability of detection points in various regions | 1. Map the primitive features of detection points to the latent feature space,, | 2. Use a clustering algorithm to initialize the target distribution | 3. WHILE NOT converged: | 4. Fix the target distributionand update the parameter | 5. Calculate the possibility of the detection points in the regionand update | 6. Fix the parameters and calculateto update target distribution | 7. END WHILE | 8. RETURN |
|