Research Article
AdaGUM: An Adaptive Graph Updating Model-Based Anomaly Detection Method for Edge Computing Environment
Algorithm 1
Anomaly detection on edge nodes.
| Input: -the threshold of similarity degree | | -the feature graph of anomalous patterns | | -the feature graph of normal patterns | | -the list of anomalous patterns in cache | | -the list of normal patterns in cache | | Output: -the collection of detected anomalies | -the collection of detected normal data | | -the collection of the data whose pattern are unknown | (1) | (2) | (3) | (4) | (5);//The queue of sensor data | (6)while () | (7){; | (8) while (!) | (9) {; | (10) for (each in ) | (11) if () | (12) {; } | (13 for (each in ) | (14) if () | (15) {; } | (16) for (each in ) | (17) if () | (18) {; } | (19) for (each in ) | (20) if () | (21) {; } | (22) if () | (23) {; } | (24) ; | (25) } | (26)} | (27)return; |
|