This operator uses the Local Outlier Factor (LOF) algorithm to find anomalies. You should use this operator with a window, because the operator saves all tuples in the current window and uses the normal LOF-algorithm on this set of tuples. If the number of tuples is too high, the algorithm may take a while to process the calculations.


The option "ignoreEqual" is useful, if the data stream has a lot of equal values. If thats the case, the distance between these values is zero. If there is one value, which is very close to these equal values and hence, the k nearest neighbors of this new value are all equal, the LOF will be infinity. That's because the average distance between the neighbors of this value if 0, there even the smallest distance greater than 0 will lead to an infinite LOF. If you set "ignoreEqual" to true, only one equal neighbor will be considered for the calculation of the LOF value.


/// Searches for anomalies in temperature data
temperatureWindow = ELEMENTWINDOW({
                        size = 100
                  lofvalue = 2.5,
                  neighbors = 5,
                  ignoreequal = 'true',
                  attribute = 'temp',
                  deliverFirstElements = 'true'