Title:
Designing Genetic Algorithms for Research in Intelligence and Entertainment Technology

Speaker:
ABU BAKAR, Nordin (UiTM)

Abstract:
In his 1975 book, Adaptation in Natural and Artificial Systems, Holland laid out a set of general principles for adaptation, including a proposal for genetic algorithms (GA). Since then GA has been used in research across various disciplines. Many versions of GA have proved to be successful in solving hard problems in science, engineering, art, architecture and music. In GA, the output is a solution to some problem or the close approximation of the solution. The input to GA has two parts: a population of candidate solution and a fitness function that takes these candidate solutions and assesses their fitness that measures how well the program works on the desired task.GA has been utilised as part of machine intelligence as a result of the intelligent system embedded into a particular application such as learning system, prediction protocol and robot navigation system. A concept learning program (DeJong) is presented with both a description of the feature space and a set of correctly classified examples of the concepts, and is expected to generate a reasonably accurate description of the unknown concepts. Nordin & Faridah (2015) devised GA to predict the strength of medium density fibreboard to skip some of the strength tests. Hagras et al. formulated Fuzzy-Genetic technique to adapt the learning behaviour of an autonomous mobile robot in unstructured and changing environments. An on-going research for designing a triage intelligent system is focused on producing a robust GA as part of its intelligent framework.GA has also been successfully used in entertainment technology as reported in Nagatsuka, K. et al (2014) when he used GA to break ties in chess, Nordin & Fadzil(2012) for using GA in designing Sudoku grids and an on-going research related to Game Refinement Theory (Iida, H.)The ultimate goal of these research works is to find and define a large network of components with no central control and simple rules of operation give rise to complex collective behaviour, sophisticated information processing and adaptation via learning or self-organising behaviours. GA and its variants give a natural foundation to achieve this goal and redefine intelligent system and entertainment technology.