For the last couple of years, the development of many-objective optimization problems opened new avenues of research in the evolutionary multi-objective optimization domain. There are already a number of algorithms to solve such problems, now the next challenge is to interpret the results produced by those algorithms. In this paper, we propose an alternative way to visualize high-dimensional Pareto fronts where the goal is to present the Pareto front in terms of a decision maker's perspective. A decision maker is more interested in the different aspects of the end results instead of the convergence and spread of a Pareto front solutions. They are interested in Pareto-optimal solutions that offer the most trade-off. They are also interested to know the boundary solutions of a Pareto front. In this paper, we present a way to visualize the Pareto front in high dimension by keeping those criteria in mind.
[1]
Hans-Peter Kriegel,et al.
A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise
,
1996,
KDD.
[2]
Geoffrey E. Hinton,et al.
Stochastic Neighbor Embedding
,
2002,
NIPS.
[3]
Lily Rachmawati,et al.
Multiobjective Evolutionary Algorithm With Controllable Focus on the Knees of the Pareto Front
,
2009,
IEEE Transactions on Evolutionary Computation.
[4]
Qing Li,et al.
Multiobjective optimization for crash safety design of vehicles using stepwise regression model
,
2008
.
[5]
Alfred Inselberg,et al.
Parallel Coordinates: Visual Multidimensional Geometry and Its Applications
,
2003,
KDIR.