Designing machine learning frameworks for intelligence and gamification research / Nordin Abu Bakar

In the era of big data analytic, describing structural pattern in data has been the fore front of many research themes. By defining the data, machines (or computers) will be able to create information and later on transform it into knowledge. The knowledge will be stored, used, referred, postulated and reasoned with. Those activities define learning in its own specific domain and context. The more important thing, however, is how beneficial these activities are to humans. The end product of learning that could establish the relationships between knowledge and intelligence. Better knowledge produces good performance which will gradually enable a system to make intelligent decisions. The central part of this subject is described in terms of frameworks or algorithms that explains how to achieve better performance. These are the main issues being explored and discussed in this research. As artificial intelligence (AI) is a very wide subject, two specific areas are chosen to illustrate the practical usage of machine learning frame-works. For the first part, intelligence embedded system has been utilised to improve performance and .secondly, tackling the issues in games and gamification technology. Machine learning frameworks have been utilised to facilitate intelligence as operational mechanism in intelligence embedded system 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 genetic framework 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.