In some cases, it becomes necessary to establish a correspondence between the declaredand actual value of a categorical variable on the basis of a set of object characteristics. In thiscase, there is a need for a classifier with an optimal sequence of the considered attributes with agiven value of the objective function. The target variable can be: yes, no, variety number, classnumber, etc. This paper solves the problem of constructing a classification model in the form of anoptimal sequence of the considered attributes and their values included in the route from the rootvertex to the terminal vertex with a given value of the target variable. If a classifier is requiredthat includes the possibility of alternative answers, then first, independently from each other, optimalroutes are built for each value of the target variable, and then these routes are combined("glued") into a single binary decision tree. In the algorithm for constructing a classifier based onthe method of crystallization of a placer of alternatives, each solution Qk is interpreted as an orientedroute Mk on a binary decision tree. Let us call the ordinal number of an element in the directedroute Mk the position siS={si|i=1,2,…,nA}. An element of the route Mk is the pair (xi, ui-),where xi corresponds to Ai. ui- in the route Mk is an edge outgoing from xi and corresponds to thevalue Ai chosen together with Ai. The second index of the element ui- is determined after the choiceof Ai, placed in the position sj+1 adjacent to sj. The work of the decision tree construction algorithmis based on the use of collective evolutionary memory, which is understood as informationreflecting the history of the search for a solution. The algorithm takes into account the tendency touse alternatives from the best solutions found. The peculiarities are the presence of an indirectexchange of information – stigmerges. The totality of data on alternatives and their assessmentsconstitutes a scattering of alternatives. The key points of the analysis of alternatives in the processof evolutionary collective adaptation are considered. Experimental studies have shown that thedeveloped algorithm finds solutions that are not inferior in quality, and sometimes surpass theircounterparts by an average of 3–4 %. The time complexity of the algorithm, obtained experimentally,lies within O(n2)-O(n3).
Read full abstract