Project FRG01A10-TK-1/2007

Project Code : FRG01A10-TK-1/2007
Project Title : Investigation on The Cynamic of Computation of Semi Autonomous Evolutionary Computation for Syntactic Optimization of a Set of Programming Codes

Project Fund : RM 70,000.00
Project Leader : Mohammad Sigit Arifianto
Project Researcher : Liawas Barukang

Description of Project :

Manual Selection of the most fit genes in an Evolutionary Computation (an Interactive Evolutionary Computation or IEC) is a relatively new approach in modeling the optimization computation of several problem such as website design, art, music, etc. Manual selection means there is no fitness function involved in the computation to find the most fit genes (user specify the next genes to be evolved). Searching for the most fit genes in an evolutionary Computation (EC) requires evaluation function to determine the set of genes to be evolved in the next generation. In both optimization methods, the correctness of the computation, confidence in using the variable set and the verification of the atomic computation of the EC is always assumed to be correct and reliable for any types of optimization computation. When correctness of the task (the semantic) is of utmost important, the intrinsic and extrinsic properties of the computation have to be evaluated.

Program codes can always be subjected to some optimization. Most optimized code is most likely to be found using EC. While EC can be relatively shows towards convergence, manual EC or the IEC can speed up the convergence. Thus, application of both methods may be able to produce an optimized code at relatively lesser time then using EC itself. We will investigate the intrinsic and extrinsic properties and characteristic of the computation and produce a model of confidence evaluation for the result of EC computation.