Special Session on "Advances in Single-Objective Continuous Parameter Optimization with Nature-inspired Algorithms"
Aims and ScopesSingle-objective continuous parameter optimization problems amount to find the minima (or maxima) of a scalar objective function which accepts a vector of real numbers as the argument. Such problems are ubiquitous in the diverse domains of science and technology. Most often in black-box optimization scenarios, the gradient information of the function is unavailable and the problem becomes even harder as the function possesses non-ideal characteristics such as non-convexity, ruggedness, ill-conditioning and so on. This makes the direct applicability of the mathematical programming methods infeasible very often. With the huge advancements made in computational resources over the past few decades, the field of nature-inspired algorithms for solving such problems has been growing at a spectacular rate now. Objective of this special session is to report the recent advances made in solving complex multimodal and multi-dimensional optimization problems (most often without any regular mathematical structure) with the application of swarm and evolutionary metaheuristics. Analytical studies on function features and landscape investigation are also welcome.
We encourage the prospective authors to test their proposed algorithms/algorithmic variants on the recently developed benchmarking suites for the IEEE CEC (Congress on Evolutionary Computation) competitions on real parameter optimization. The authors may also use a collection of real world continuous parameter optimization problems proposed for the CEC 2011 competition. Please see the following URL for further details: http://www.ntu.edu.sg/home/epnsugan/index_files/cec-benchmarking.htm. We also encourage the authors to validate their results through suitable (and preferably non-parametric) statistical tests.
Topics of Interest
Papers must present original work or review the state-of-the-art in the following non-exhaustive list of topics:
- Particle Swarm Optimization (PSO) and its advanced variants.
- Differential Evolution (DE) and its advanced variants.
- Covariance Matrix Adaptation Evolution Strategies (CMA-ESs).
- Artificial Bee Colony (ABC) and other honey bee inspired algorithms.
- Real coded Genetic Algorithms (GAs).
- Hybrid and memetic algorithms for continuous search spaces.
- Ensemble Strategies for Evolutionary Algorithms (see http://www.ntu.edu.sg/home/epnsugan/index_files/EEAs-EOAs.htm for some pioneering contributions).
- Parameter control and adaptation in evolutionary algorithms.
- Neighborhood-based search operators.
- Multi-population and distributed search techniques.
- Learning based techniques for continuous parameter optimization.
- Analysis of function features and fitness landscapes for continuous optimization problems.
- Swagatam Das, Indian Statistical Institute, India.
- P. N. Suganthan, Nanyang Technological University, Singapore.
- Janez Brest, University of Maribor, Slovenia.
- Roman Senkerik, Tomas Bata University in Zlin, Czech Republic.
- Rammohan Mallipeddi, Kyungpook National University, Republic of Korea.