DOLPHIN: An efficient algorithm for mining distance-based outliers in very large datasets.

Fabrizio Angiulli Fabio Fassetti

Published in: ACM Trans. Knowl. Discov. Data (2009)

Keyphrases

dynamic programming
computational complexity
computational cost
computationally efficient
detection algorithm
experimental evaluation
optimization algorithm
preprocessing

times faster
high accuracy
similarity measure
simulated annealing
significant improvement
experimental study
tree structure

single pass
matching algorithm
improved algorithm
highly efficient
data mining
input data
linear programming

np hard
cost function
k means
search space
optimal solution
clustering algorithm
learning algorithm