Assessing Machine Learnability of Image and Graph Representations for Drone Performance Prediction. (May 2022)

• Record Type: Journal Article
• Authors: Song, B.; McComb, C.; Ahmed, F.
• Is Part Of: Proceedings of the Design Society. Volume 2(2022)
• Page Start: 1777
• Page End: 1786
• Publication Date: 2022-05
• Subjects: engineering design -- artificial intelligence (AI) -- design evaluation -- design representation -- graph convolutional networks; Industrial design -- Congresses; Engineering design -- Congresses; 620.0042
• DOI: 10.1017/pds.2022.180
• Languages: English
• ISSNs: 2633-7762

Abstract

Abstract: Deep learning (DL) from various representations have succeeded in many fields. However, we know little about the machine learnability of distinct design representations when using DL to predict design performance. This paper proposes a graph representation for designs and compares it to the common image representation. We employ graph neural networks (GNNs) and convolutional neural networks (CNNs) respectively to learn them to predict drone performance. GCNs outperform CNNs by 2.6-8.1% in predictive validity. We argue that graph learning is a powerful and generalizable method for such tasks.