Algorithm 2 Parallel Pattern Relation Table Algorithm

Input: Training data set D, test sequence $\sigma$ Output: Detect if $\sigma$ is normal or abnormal 1:Extract the event set E and the necessary event set $E_n$. 2:Extract the repeated event set $E_r$ by Subroutine 6. 3:Learn the loop pattern set $LP$ introduced in Section 4.2. 4:Process the sequence $d_i\in D$ in parallel introduced in Section 4.3. 5:Build multiple relation tables in parallel introduced in Section 4.4. 6:Detect if $\sigma$ is normal or not by Subroutine 7.