Penerapan Adaptive Neuro Fuzzy Inference System pada Real Time Strategy Battle Arena Game

Authors

  • Andy Gunawan Program Studi Teknik Informatika
  • Rolly Intan Program Studi Teknik Informatika
  • Kristo Radion Purba Program Studi Teknik Informatika

Keywords:

Privacy-security, job productivity, convenience of life, e-tax system, service tax climate, user-satisfaction

Abstract

Nowadays, Real Time Strategy Battle Arena is one of the most popular game genre. However, most games with that genre are only interesting if played together with another human. That makes those games less flexible since they can’t be played without another human or internet connection.

Because of that, this thesis will create a game with Real Time Strategy Battle Arena genre with AI as the enemy where the enemy movements can be adjusted to approach human thinking ways. The enemy in this game will also be able to learn from each mistake. This thesis will use the method Adaptive Neuro Fuzzy Inference System.

Test results show that the enemy was able to choose the best move possible, which suits the way humans think using Fuzzy Inference System. Neural System also modified the Membership  Functions of some Fuzzy Inference System input variable everytime the enemy is considered to make mistake to minimize similar mistakes when the game is played again in the future.

References

[1] Buckland, M. 2005. Programming Game AI by Example. Plano: Wordware Publishing, Inc.

[2] Dernoncourt, F. 2013. Introduction to Fuzzy Logic. Cambridge: Massachusetts Institute of Technology.

[3] Gavrilova, V. 2013. Cognitive Load and Flow in Multiplayer Online Battle Arena Games. Limassol: Cyprus University of Technology.

[4] Jang, J.S.R. 1993. ANFIS: Adaptive-Network-Based Fuzzy Inference System. Berkeley: University of California.

[5] Lidianto, S.V., Budhi, G.S. & Intan, R. 2016. Perancangan dan Pembuatan Action Game dengan Artificial Intelligence dan Machine Learning. Surabaya: Universitas Kristen Petra.

[6] Shalev-Shwartz, S. & Ben-David, S. 2014. Understanding Machine Learning. Cambridge: Cambridge University Press.

[7] Suparta, W. & Alhasa K.M. 2016. Modeling of Tropospheric Delays Using ANFIS.

Downloads

Published

2019-01-15

Issue

Section

Articles