**weka.attributeSelection**

Tabu Search :

=20Performs a search through the space of attribute subsets. Evading local = maximums by accepting bad and diverse solutions and make further search in = the best soluions. Stops when there's not more improvement in n iterations.= For more information see:

=20Abdel-Rahman Hedar, Jue Wangy, Masao Fukushima (2006). Tabu Search for A= ttribute Reduction in Rough Set Theory.

=20The table below describes the options available for TabuSearch.

=20
=20
=20
=20
=20
=20
=20
=20
=
=20
=20
=20
=20
=20
=20
=20
=20
=20
=20
=20
=20
=20
=20

Option | Description |
---|---|

diversificationProb | Set the probability of diversification. This= is the probability of change of search subspace in an abrupt way |

initialSize | Set the number of attributes that are going = to be in the initial Solution |

numNeighborhood | Set the number of current solution's neighbo= rhood to generate for looking for a better solution |

seed | Set the random seed. |