<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The development of the Internet era acts on every change brought by spatial design so that the application of virtual reality technology in spatial design solutions begins to emerge. In this paper, firstly, combining the general process of visualization and the characteristics of visual variables, seven visual variables are selected for preliminary 3D visual representation, and their applicability under virtual reality space is analyzed. The HSV color space is also used for visual coding. According to the intuitive nature of visual perception of spatial design, a multiple visual variables mapping model based on VR is proposed. Considering the sequential characteristics of spatial design, PCA-LSTM spatial design classification model is proposed, and virtual space is applied in spatial design by local changes of the top surface, ground surface, and vertical interface. The simulation experiments are conducted by selecting SVM, BP neural network, and LSTM network as the comparison algorithms, and the results show that the accuracy of both the training set and the test set is found to be improved based on the PCA-LSTM classification model for spatial design classification, which is 4.9% and 9.49% higher than the traditional LSTM algorithm, respectively, verifying the PCA-LSTM for spatial design The effectiveness of PCA-LSTM for spatial design classification is verified. This study cleverly uses the design technique of virtual space to better apply virtual space in spatial design.</p>
</abstract>

The development of the Internet era acts on every change brought by spatial design so that the application of virtual reality technology in spatial design solutions begins to emerge. In this paper, firstly, combining the general process of visualization and the characteristics of visual variables, seven visual variables are selected for preliminary 3D visual representation, and their applicability under virtual reality space is analyzed. The HSV color space is also used for visual coding. According to the intuitive nature of visual perception of spatial design, a multiple visual variables mapping model based on VR is proposed. Considering the sequential characteristics of spatial design, PCA-LSTM spatial design classification model is proposed, and virtual space is applied in spatial design by local changes of the top surface, ground surface, and vertical interface. The simulation experiments are conducted by selecting SVM, BP neural network, and LSTM network as the comparison algorithms, and the results show that the accuracy of both the training set and the test set is found to be improved based on the PCA-LSTM classification model for spatial design classification, which is 4.9% and 9.49% higher than the traditional LSTM algorithm, respectively, verifying the PCA-LSTM for spatial design The effectiveness of PCA-LSTM for spatial design classification is verified. This study cleverly uses the design technique of virtual space to better apply virtual space in spatial design.

Exploring the application of virtual space in spatial design in the era of artificial intelligence

Design school, Anhui Polytechnic University

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The development of the Internet era acts on every change brought by spatial design so that the application of virtual reality technology in spatial design...

Exploring the application of virtual space in spatial design in the era of artificial intelligence

Pubblicato online: 02 ott 2023

Pagine: -

Ricevuto: 30 nov 2022

Accettato: 12 apr 2023

DOI: https://doi.org/10.2478/amns.2023.2.00441

Parole chiave
Virtual reality technology, Spatial design, PCA-LSTM, HSV color space, Multiple visual variables, Mapping model

© 2023 Pei Ding et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Exploring the application of virtual space in spatial design in the era of artificial intelligence

Pubblicato online: 02 ott 2023

Pagine: -

Ricevuto: 30 nov 2022

Accettato: 12 apr 2023

DOI: https://doi.org/10.2478/amns.2023.2.00441

Parole chiaveVirtual reality technology, Spatial design, PCA-LSTM, HSV color space, Multiple visual variables, Mapping model

© 2023 Pei Ding et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Virtual reality technology, Spatial design, PCA-LSTM, HSV color space, Multiple visual variables, Mapping model