The Genetic Algorightm (GA) is based on a mathematical theory derived from the principles of natural evelotion. Borrowing from the concepts of random selection, survival of the fittest, and adaption. GA offers a unique, innovative approach to finding solutions to the generalized optimization problem. How to apply performance metrics to decisions in a way that allows iterative improvement toward the best one in a way in a timely fashion. GA offers an alternative to classical techniques, particularly in cases where their use may not be feasible due to violations of necessary theoretical assumptions, problem size, or complexity. The GA is applicable to a broad range of decisions-based problems, including those found in genetics, game theory, artificial intelligence, economics, control and psychology. Potential applications would encompass prediction, modeling, automatic control, optimal routing, neural network training and design, and automatic programming and robotics. Genetics is related to the broader discipline of evolutionary programming or simulated evolution. Phase I demonstrated the value of GA using a missile-target assignment problem. The objective of Phase II is to expand and further refine the methodology investigated during Phase I to establish the viability of GA for large, complex problems. A major goal is the derivation of generic software that could be applied to a myriad of decision-based problems.
Keywords: Operational Planning Targeting Genetic Algorithm Evolutionary Programming Parallel Processing Neural
