Player profiling and quality assessment of dynamic car racing tracks using entertainment quantifier technique

Abstract

AbstractInteractive games have been an interesting area of research and have many challenges. With the advancement in technology, games have been revolutionizing at each step per the emerging and variant interests of players. Recently, machine learning techniques are used for the generation of game content based on player's experience. The dynamic content generation in computer games based on player's experience and feedback is still a challenging task. This requires measurement of entertainment factor achieved by a player during a game. In order to measure entertainment factor, we need to incorporate human‐computer interaction by evolution of game content with respect to player's response. Optimization techniques can be used for the measurement of entertainment factor and for the generation of dynamic game content. The use of computational intelligence techniques in game development can lead to a new domain called “computational intelligence in games.” This research is focused on car racing game genre, and the paradigm selected for dynamicity is track generation of car racing game. It requires player profiling and classification of players. The optimization of track generation has been performed by using single and multiobjective genetic algorithm and particle swarm optimization. Initially, classification of player's rank based on data and theory‐driven approaches has been performed. Moreover, 3 different techniques of defining ranges or boundaries of race parameters for player's rank classification are studied. The techniques are based on crisp values, neural network, and fuzzy inference process. Then, an entertainment quantifier technique is proposed for a player after playing a certain number of games based on dynamic content generation using multiobjective genetic algorithm using standard Pareto optimal front and an epsilon (ϵ) front. In conclusion, the method proposed for quantifying entertainment can be used to analyze and classify the trend in interests of a player according to which the game itself can dynamically generate. This will keep the interest of player intact and provides maximum entertainment experience per the interest of an individual. The proposed solution can easily be used in generation of any game content and can effectively be used in accurate measurement of entertaining factor of any game.