Procedural Video Game Scene Generation by Genetic and Neutrosophic WASPAS Algorithms

Petrovas, Aurimas; Baušys, Romualdas

doi:10.3390/app12020772

Cited by 14 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The base used for the algorithm was taken from the original WASPAS procedural scene generator (Petrovas & Bausys, 2022). The CPU used for the calculations has 8-core processor with 2.4 GHz speed.…”

Section: Resultsmentioning

confidence: 99%

Generation of Creative Game Scene Patterns by the Neutrosophic Genetic CoCoSo Method

PETROVAS¹,

BAUSYS²,

Zavadskas³

et al. 2022

SIC

View full text Add to dashboard Cite

Creative procedural generation requires, by its nature, a nondeterministic result. Each set of outputs has to satisfy the required criteria and, at the same time, has to show unique results to be considered creative. One of the keys to increasing nondeterminism is to use fuzzy neutrosophic sets. A combination of a CoCoSo multi-criteria decision algorithm with a genetic algorithm to generate game scenes was proposed. The algorithm satisfies the required game rules and improves the aesthetics value of the visual game scene. The proposed approach seeks to produce a creative solution which satisfies the replayability principle, when the solution is not optimal in the optimization procedure sense. In this paper, improvements of the CoCoSo method were proposed in order to work with iterative genetic algorithm.

show abstract

Section: Resultsmentioning

confidence: 99%

Generation of Creative Game Scene Patterns by the Neutrosophic Genetic CoCoSo Method

PETROVAS¹,

BAUSYS²,

Zavadskas³

et al. 2022

SIC

View full text Add to dashboard Cite

show abstract

“…Then, the Maximum Likelihood Estimation (MLE) is applied to estimate 𝜃 based on the observed or inputted dataset 𝑋. Detailed formulation is as shown in Equation (3).…”

Section: Autoencoding Variational Autoencoder (Vae) and Decoding Proc...mentioning

confidence: 99%

“…In the 21 st century, enormous mathematical and data analytic techniques and algorithms have been adopted in designing new video games and frames, for the purposes of enhancing teaching and learning processes within virtual environment, pushing the innovation and specialty of gameplay mechanics to its furthest extent, and visualizing game scenes in a human-crafted, realistic and dynamic manner [1][2][3]. The concerned subjects include the investigation of 3-dimensional geometric properties of characters within a particular frame [4], the capturing of geometric transformations and motion in real-time basis [5], the use of simulation games for analyzing and building up complex systems that could better reflect real world conditions [6].…”

Section: Introductionmentioning

confidence: 99%

“…The concerned subjects include the investigation of 3-dimensional geometric properties of characters within a particular frame [4], the capturing of geometric transformations and motion in real-time basis [5], the use of simulation games for analyzing and building up complex systems that could better reflect real world conditions [6]. Today, credited with the increment of computing power and resources, the enhancement of capability in terms of data storage, and the massive data volume for simultaneous processing [3], advances in machine learning (ML) and artificial intelligence (AI) approaches are taking place and being widely adopted in different practical disciplines, especially those related to image processing and computer vision, as well as the emergence of generative models. Such new Disclaimer/Publisher's Note: The statements, opinions, and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Mak¹,

Han²,

Yin³

2023

Preprint

View full text Add to dashboard Cite

In recent decades, the Variational AutoEncoder (VAE) model has shown good potential and capabilities in image generation and dimensionality reduction. The combination of VAE and various machine learning frameworks has also worked effectively in different daily life applications, however its possibility and effectiveness in modern game design has seldom been explored nor assessed. The use of its feature extractor for data clustering was minimally discussed in literature neither. This paper first attempts to explore different mathematical properties of the VAE model, in particular, the theoretical framework of the encoding and decoding processes, the possible achievable lower bound and loss functions of different applications; then applies the established VAE model into generating new game levels within two well-known game settings; as well as validating the effectiveness of its data clustering mechanism with the aid of the Modified National Institute of Standards and Technology (MNIST) database. Respective statistical metrics and assessments were also utilized for evaluating the performance of the proposed VAE model in aforementioned case studies. Based on the statistical and spatial results, several potential drawbacks and future enhancement of the established model were outlined, with the aim of maximizing the strengths and advantages of VAE for future game design tasks and relevant industrial missions.

show abstract

“…In the 21st century, enormous mathematical and data analytic techniques and algorithms have been adopted in designing new video games and frames, for the purposes of enhancing teaching and learning processes in a virtual environment, pushing the innovation and specialty of gameplay mechanics to its furthest extent, and visualizing game scenes in a human-crafted, realistic and dynamic manner [ 1 , 2 , 3 ]. The concerned subjects include the investigation of 3-dimensional geometric properties of characters within a particular frame [ 4 ], the capturing of geometric transformations and motion on a real-time basis [ 5 ], and the use of simulation games for analyzing and building up complex systems that could better reflect real world conditions [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Mak

Han

Yin

2023

Sensors

View full text Add to dashboard Cite

In recent decades, the Variational AutoEncoder (VAE) model has shown good potential and capability in image generation and dimensionality reduction. The combination of VAE and various machine learning frameworks has also worked effectively in different daily life applications, however its possible use and effectiveness in modern game design has seldom been explored nor assessed. The use of its feature extractor for data clustering has also been minimally discussed in the literature neither. This study first attempts to explore different mathematical properties of the VAE model, in particular, the theoretical framework of the encoding and decoding processes, the possible achievable lower bound and loss functions of different applications; then applies the established VAE model to generate new game levels based on two well-known game settings; and to validate the effectiveness of its data clustering mechanism with the aid of the Modified National Institute of Standards and Technology (MNIST) database. Respective statistical metrics and assessments are also utilized to evaluate the performance of the proposed VAE model in aforementioned case studies. Based on the statistical and graphical results, several potential deficiencies, for example, difficulties in handling high-dimensional and vast datasets, as well as insufficient clarity of outputs are discussed; then measures of future enhancement, such as tokenization and the combination of VAE and GAN models, are also outlined. Hopefully, this can ultimately maximize the strengths and advantages of VAE for future game design tasks and relevant industrial missions.

show abstract

Procedural Video Game Scene Generation by Genetic and Neutrosophic WASPAS Algorithms

Cited by 14 publications

References 27 publications

Generation of Creative Game Scene Patterns by the Neutrosophic Genetic CoCoSo Method

Generation of Creative Game Scene Patterns by the Neutrosophic Genetic CoCoSo Method

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Application of Variational AutoEncoder (VAE) Model and Image Processing Approaches in Game Design

Contact Info

Product

Resources

About