Static and dynamic difficulty level design for edutainment game using artificial neural networks

Authors:
Kok Wai Wong;Chun Che Fung;Arnold Depickere;Shri Rai
Affiliations:
School of Information Technology, Murdoch University, Murdoch, Western Australia;School of Information Technology, Murdoch University, Murdoch, Western Australia;Division of Arts, Murdoch University, Murdoch, Western Australia;School of Information Technology, Murdoch University, Murdoch, Western Australia
Venue:
Edutainment'06 Proceedings of the First international conference on Technologies for E-Learning and Digital Entertainment
Year:
2006

Citing 2
Cited 2

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Game Level Design (Game Development Series)

Game Level Design (Game Development Series)

Adaptive Computer Game System Using Artificial Neural Networks

Neural Information Processing
Effects of different scenarios of game difficulty on player immersion

Interacting with Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

When designing a game, one of the major tasks is to design a game of exciting and challenging difficulty levels to maintain the interest level of a player throughout the game. This is especially important when designing an educational game. This paper proposes the use of Artificial Neural Networks (ANNs), specifically the Backpropagation Neural Networks (BPNNs) for handling the gaming experience. The BPNNs can provide targeted learning experience for the user or the student. This will achieve personalized learning that is an important issue for student relationship management. The proposed frameworks will provide motivation for the student as the difficulty level progresses and adjusts to suit individual users.