Article: A furniture design assistance method based on spatiotemporal graph neural networks and multi-objective optimisation Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.40 pp.34 - 54 Abstract: This paper suggests a furniture design assistance method (FD-STGMO) based on spatial-temporal graph neural network (ST-GNN) and multi-objective optimisation to help with the problem of balancing the structural complexity and multi-objective optimisation needs in the furniture design process. The technique first employs ST-GNN to find structural change features. Then, it uses multi-objective optimisation algorithms to come up with design solutions. Finally, it builds a collaborative end-to-end design support system. The performance comparison tests done on the simulation dataset all show that the new FD-STGMO method is better than the old one in four areas: structural stability (0.84), material utilisation (0.88), functional adaptability (0.80), and aesthetics score (0.85). The findings of the modular contribution analysis experiments show that FD-STGMO has good potential for use in engineering and business. Inderscience Publishers - linking academia, business and industry through research

Title: A furniture design assistance method based on spatiotemporal graph neural networks and multi-objective optimisation

Authors: Tiande Wei

Addresses: Zhongge Art College, Guangdong Ocean University, Zhanjiang, 524088, China

Abstract: This paper suggests a furniture design assistance method (FD-STGMO) based on spatial-temporal graph neural network (ST-GNN) and multi-objective optimisation to help with the problem of balancing the structural complexity and multi-objective optimisation needs in the furniture design process. The technique first employs ST-GNN to find structural change features. Then, it uses multi-objective optimisation algorithms to come up with design solutions. Finally, it builds a collaborative end-to-end design support system. The performance comparison tests done on the simulation dataset all show that the new FD-STGMO method is better than the old one in four areas: structural stability (0.84), material utilisation (0.88), functional adaptability (0.80), and aesthetics score (0.85). The findings of the modular contribution analysis experiments show that FD-STGMO has good potential for use in engineering and business.

Keywords: furniture design; spatial-temporal graph neural network; ST-GNN; multi-objective optimisation; intelligent aided design.

DOI: 10.1504/IJICT.2025.149813

International Journal of Information and Communication Technology, 2025 Vol.26 No.40, pp.34 - 54

Received: 28 Jul 2025
Accepted: 15 Sep 2025
Published online: 13 Nov 2025 *

Title: A furniture design assistance method based on spatiotemporal graph neural networks and multi-objective optimisation

Keep up-to-date