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;