Research Article

A New Evolutionary-Incremental Framework for Feature Selection

Algorithm 4

Evolutionary-incremental invasive weed optimization.
Input: : minimum production rate, : maximum production rate, : minimum number of seeds, : maximum
number of seeds, : addition probability, : deletion probability, : maximum length of solutions, : number of generations
that is constant during these generations
(i) Initialization: a finite number of seeds are being dispread over the search space randomly, the number of initial seeds have to
be fall in the range
(ii) Evaluation: calculation of fitness value of each seed
(iii)
(iv) If then and
(v) Reproduction: current seeds grow to flowering and produce new seeds. Rate of production of each flower is dependent to
the fitness of the corresponding seed. The production rate of seeds is linearly computed based on their fitness in the range
(vi) Addition: applying addition operator on each seed produced from the previous step with the probability of while
the length of solutions must be less than or equal to
(vii) Deletion: applying deletion operator on each seed produced from the previous step with the probability of while
the length of solutions must be greater than or equal to 1
(viii) Spatial Dispersal: the produced seeds are being randomly dispread over the search space and grow
(ix) Competitive Exclusion: if the maximum number of plants is greater than , now only plants with the highest fitness
values can survive and produce seeds. Other plants are eliminated
(x) Termination Condition: if termination condition(s) is satisfied, the algorithm is finished; otherwise go to step (iii).
When the algorithm is finished, the best solution with the highest fitness value is the output of the algorithm.