Idioma:

Performance Metric Ensemble for Multiobjective Evolutionary Algorithms

Yen, Gary G. ; Zhenan He

IEEE transactions on evolutionary computation, 2014-02, Vol.18 (1), p.131-144 [Periódico revisado por pares]

New York, NY: IEEE

Texto completo disponível

Citações Citado por

Enviar para

Título:
Performance Metric Ensemble for Multiobjective Evolutionary Algorithms
Autor: Yen, Gary G. ; Zhenan He
Assuntos: Algorithmics. Computability. Computer arithmetics ; Algorithms ; Applied sciences ; Approximation algorithms ; Approximation methods ; Benchmark testing ; Benchmarking ; Combinatorics ; Combinatorics. Ordered structures ; Computer science; control theory; systems ; Data processing. List processing. Character string processing ; Double elimination design ; ensemble method ; Evolutionary algorithms ; evolutionary algorithms (EAs) ; Exact sciences and technology ; Graph theory ; Heuristic ; Heuristic methods ; Information retrieval. Graph ; Mathematics ; Measurement uncertainty ; Memory organisation. Data processing ; Optimization ; Performance measurement ; performance metrics ; Ranking ; Sciences and techniques of general use ; Sociology ; Software ; Statistics ; Theoretical computing
É parte de: IEEE transactions on evolutionary computation, 2014-02, Vol.18 (1), p.131-144
Notas: ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
Descrição: Evolutionary algorithms have been successfully exploited to solve multiobjective optimization problems. In the literature, a heuristic approach is often taken. For a chosen benchmark problem with specific problem characteristics, the performance of multiobjective evolutionary algorithms (MOEAs) is evaluated via some heuristic chosen performance metrics. The conclusion is then drawn based on statistical findings given the preferable choices of performance metrics. The conclusion, if any, is often indecisive and reveals no insight pertaining to which specific problem characteristics the underlying MOEA could perform the best. In this paper, we introduce an ensemble method to compare MOEAs by combining a number of performance metrics using double elimination tournament selection. The double elimination design allows characteristically poor performance of a quality algorithm to still be able to win it all. Experimental results show that the proposed metric ensemble can provide a more comprehensive comparison among various MOEAs than what could be obtained from a single performance metric alone. The end result is a ranking order among all chosen MOEAs, but not quantifiable measures pertaining to the underlying MOEAs.
Editor: New York, NY: IEEE
Idioma: Inglês

Links

View record in Pascal Francis

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Performance Metric Ensemble for Multiobjective Evolutionary Algorithms

Yen, Gary G. ; Zhenan He

New York, NY: IEEE

Buscando em bases de dados remotas. Favor aguardar.