Evolution strategies –A comprehensive introduction
Natural Computing: an international journal
Evolutionary Algorithms for Solving Multi-Objective Problems (Genetic and Evolutionary Computation)
Evolutionary Algorithms for Solving Multi-Objective Problems (Genetic and Evolutionary Computation)
Multiobjective optimization problems with complicated Pareto sets, MOEA/D and NSGA-II
IEEE Transactions on Evolutionary Computation
A review of multiobjective test problems and a scalable test problem toolkit
IEEE Transactions on Evolutionary Computation
Classification of adaptive memetic algorithms: a comparative study
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
This paper presents a novel method for visualizing large experimental datasets called a Biaxial Box Plot which provides both an easily read general impression of the results that highlights performance trends whilst also allowing for careful comparison of individual results. The Biaxial Box Plot is compared against heatmaps and traditional box plots where it is argued that the new method provides a suitable combination of the two existing methods. In addition, a novel ranking method is presented called the Ordered Trial Rank (OTR) that is designed for use with results that contain a large number of related sets of samples - e.g. a group of algorithm performance results on the same problem. The OTR is compared against simple median and standard deviation scores and shown to provide a better statistical distinction between the sets of results. Both methods are presented in the context of EA experimental research but can be applied more generally to data with two orthogonal group that can be combined to create a matrix of numeric data sets.