Algorithm 1 Multi-objective cuckoo search.

From: A hybrid model based on learning automata and cuckoo search for optimizing test item selection in computerized adaptive testing

1. Define fitting objectives as \(\:{f}_{1}\left(x\right),\dots\:,{f}_{K}\left(x\right)\:x=\left({x}_{1},\:\dots\:,\:{x}_{d}\right).\:\)

2. Generate an initial population consisting of n cuckoos, each containing K eggs.

3. Repeat the following steps until (t < T) or one of the termination conditions is met:

3.1. Select a random cuckoo, i, using the Lévy flight algorithm.

3.2. Evaluate the fitness of the selected cuckoo in the light intensity.

3.3. Choose a random cuckoo, j, from the n population.

3.4. If the solutions present in j dominate those in i, replace i with the solutions in j.

3.5. Abandon a fraction \(\:{P}_{a}\:\)of the worst cuckoos and replace them with new cuckoos.

3.6. Preserve the best solutions.

3.7. Sort the population and determine the optimal solutions in the current iteration based on the light intensity.

3.8. Increment the value of t by one unit.

4. End.

Back to article page