This paper proposes a novel explainable Dimensionality Reduction (XDR) framework to translate high-dimensional tacit knowledge learned by AI into human-understandable explicit knowledge. A case study on recognizing ethnic styles of village dwellings in Guangdong, China, using a Mask R-CNN model, reveals patio, size, length, direction, and asymmetric shape as key distinguishing features for Canton, Hakka, and Teochew styles. Results align with existing field studies and uncover evidence of Hakka migration, demonstrating XDR's potential for expanding domain knowledge.
Publisher
Humanities and Social Sciences Communications
Published On
Jan 26, 2023
Authors
Xun Li, Dongsheng Chen, Weipan Xu, Haohui Chen, Junjun Li, Fan Mo
Tags
Dimensionality Reduction
Explainable AI
Ethnic styles
Village dwellings
Canton
Hakka
Teochew
Related Publications
Explore these studies to deepen your understanding of the subject.
