No abstract

:This paper presents an effective and efficient approach for translating fuzzy classification rules that use approximative sets to rules that use descriptive sets and linguistic hedges of predefined meaning. It works by first generating rules that use approximative sets from training data and then translating the resulting approximative rules into descriptive ones. Hedges that are useful for supporting such translations are provided. The translated rules are functionally equivalent to the original approximative ones, or a close equivalent given search time restrictions, while reflecting their underlying preconceived meaning. Thus, fuzzy descriptive classifiers can be obtained by taking advantage of any existing approach to approximative modeling which is generally efficient and accurate, whilst employing rules that are comprehensible to human users. Experimental results are provided and comparisons to alternative approaches given. The authors and the University of Edinburgh retain the right to reproduce and publish this paper for non-commercial purposes.Permission is granted for this report to be reproduced by others for non-commercial purposes as long as this copyright notice is reprinted in full in any reproduction. Applications to make other use of the material should be addressed in the first instance to Copyright Permissions, Division of Informatics, The University of Edinburgh, 80 South Bridge, Edinburgh EH1 1HN, Scotland.

AbsfracI-Combinatorial optimisation algorithm can be bothSlow and fragile. That is. the quality Of results produced can vary considerably with the problem and with the parameters chosen and the nser must hope or the best or search for problem-specific goodThe idea of is to fast, deterministic algorithm built from easilv-understood heuristics that shows eood nerformance across repeatedly find the nearest labelled point and apply its label until a complete solution had been built. In both varieties we into training and testing sets, in the performance evaluation. More details of hyper-heuristics itself, its high level algorithms, its connection with GAS. code and so on can be found on the around a thousand h a d bin-packing problems, for a I _ a range of problems. In this paper we show how the idea can be applied to class and exam timetabling problem and report results on non-trivial problem. Unlike many optimisation algorithms, the generated algorithm does not involve and solution-impmving search step, it is purely constructive.

No abstract

No abstract