URL: http://www.adaptivebox.net/doi/SCO

(Current Version: V1.0.000)

Basic Description | What's New | Problem to be solved | Setting Parameters | Output Information | References | Contact |
---|

Social Cognitive Optimization (SCO) is a simple agent-based model based on the observational learning mechanism in human social cognition.

**License information**: SCO is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License 3.0.

**Problem to be solved**: (constrained) numerical optimization problem (NOP), or called the nonlinear programming problem.
**System Requirements**: SCO is a platform-independent software developed by JAVA version 1.4 or above.

**Command line** (examples): $ java SCO Problem=<Problem_Name> [NAME=VALUE] ...

What's New |
---|

It implements the original SCO algorithm [1] & [2].

Problem to be solved |
---|

The problem to be solved is (constrained) numerical optimization problem (NOP), or called the nonlinear programming problem.

**Tips**: 1) all the variable bounds must be specified, since optimal solution(s) might situate at anywhere; and 2) problem.ProblemEncoder andproblem.UnconstrainedProblemEncoder are the parental classes of all constrained (e.g., problem.constrained.Michalewicz_G1) and unconstrained (e.g., problem.unconstrained.GoldsteinPrice) problems, respectively.

**Implemented problem instances**: please download from the up-to-date list of source files, which will be situated in the directories: 1) problem/constrained, and 2) problem/unconstrained.

Setting parameters [NAME=VALUE] |
---|

NAME VALUE_type Range Default_Value Description Problem String * <Problem_Name> The problem to be solved //For example: problem.constrained.Michalewicz_G2 is the default value ------------------------------------------------------------------------------------------------------ N integer >5 70 General: The number of agents T integer >1 2000 General: The maximum learning cycles NL integer >1 3*N For the library: The number of Points //The total number of evaluation times is N*T+NL //The program outputs runtime information of the best solution every "Tout" cycles.

Output Information |
---|

[**Parsing information**]: provide the parsing information for all input parameters.

[**Setting information**]: show the information of all setting parameters for the algorithm.

[**Runtime information**]: The program outputs runtime information, i.e., the evaluation values <Vcon, Vopt> of the best solution, at every "Tout" cycles.

//**Vopt**: the value of objective function; **Vcon**: the weighted constraint violation value (≥0): it is not outputted if Vcon≡0 since there is no violation

[**Summary information**]: At the end, it outputs the input variables, response values, and evaluation values <Vcon, Vopt> of the best solution.

References |
---|

[1] Xiao-Feng Xie, Wen-Jun Zhang, Zhi-Lian Yang. Social cognitive optimization for nonlinear programming problems. *International Conference on Machine Learning and Cybernetics* (ICMLC). Beijing, China, 2002: 779-783. [DOI]

[2] Xiao-Feng Xie, Wen-Jun Zhang. Solving engineering design problems by social cognitive optimization. *Genetic and Evolutionary Computation Conference* (GECCO), LNCS 3102, Seattle, WA, USA, 2004: 261-262. [DOI]

Maintained by AdaptiveBox StUdIo, under a Creative Commons Attribution 3.0 License.