Abnormal Event Detection in Wireless Sensor Networks Based on Multiattribute Correlation

Algorithm 1

Abnormal event detection algorithm based on multiattribute correlation.

Input. WSN data set

Output. Abnormal event Information Info

(1) standardize into values between 0 and 1

(2) divide into subsets, choose the first set to learn Bayesian network

(3) choose the network with highest score as attribute

  dependency model

(4) for to epoch//epoch is incremental tick

(5)   if %period = 0//period is parameter update period

(6)   flag = true; //flag represents update parameter or not

(7)  end

(8)  for to is the id of WSN, is the number of sensors

(9)    learn parameter for each sensor node

(10)   if dataPointer < group_length

    //prevent the exceed the length of group

(11)     if groupData_time

     //prevent a break caused by data loss

(12)     compute α from M

(13)     end

(14)   end

(15)  compute

(16)  if < ε  &&  

(17)   compute ;

(18)   if

(19)     report Info to sink node;

(20)   else

(21)    filter as noise;

(22)   end

(23)   end

(24)   end

(25)  flag = false;

(26) end