Professional Documents
Culture Documents
OPTIMIZATION
1
ANT ALGORITHM
2
ANT ALGORITHM
3
ANT ALGORITHM
4
ANT ALGORITHM
5
ANT ALGORITHM
How do ants find the shortest path between their nest and
food source, without any visible, central, active coordination
mechanism?
Studies have shown that the search for food is random in the
beginning
6
ANT ALGORITHM
How do ants find the shortest path between their nest and
food source, without any visible, central, active coordination
mechanism?
Studies have shown that the search for food is random in the
beginning
7
ANT ALGORITHM
8
ANT ALGORITHM
Ant Algorithm
Ant Algorithm
10
ANT ALGORITHM
Ant Algorithm
Ant Algorithm
12
ANT ALGORITHM
13
ANT ALGORITHM
The probability that the ant chooses j as the next city after it
has arrived at city i where j is in the set S of cities that have
not been visited is
14
ANT ALGORITHM
15
ANT ALGORITHM
The solution may have been even better, if the city had been
replaced by another city
16
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Classification
Algorithms
Training
Data
• General description
• Heuristic function
• Rule pruning
• Pheromone updating
• Use of discovered rules for classifying new cases
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
• General description
• Heuristic function
• Rule pruning
• Pheromone updating
• Use of discovered rules for classifying new cases
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Search Space
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Algorithm
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Algorithm
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Algorithm
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Where:
Heuristic Function
Where
• w is the class attribute
• k is the number of classes in the domain of class attribute
• Ai is the i-th attribute
• Vij is the jth value of the domain of the attribute Ai
• P(w | Ai = Vij) is the empirical probability of observing class w
conditional on having observe Ai = Vij
29
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Heuristic Function
Where:
• a is the total number of attributes
• xi is set to 1 if the attribute Ai was not yet used by the current ant
• bi is the number of values in the domain of ith attribute
30
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Rule Pruning
Rule Pruning
• This process is repeated until the rule has just one term
or until there is no term whose removal will improve the
quality of the rule
DATA MINING WITH AN ANT COLONY
OPTIMIZATION ALGORITHM
Pheromone Updating
Pheromone Updating
Pheromone Updating
Rule Quality
• The quality of a rule is computed according to: