Automatic discovery of design task structure using deep belief nets

Lan, Lijun, Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940 and Lu, Wen Feng 2017. Automatic discovery of design task structure using deep belief nets. Journal of Computing and Information Science in Engineering 17 (4) , 041001. 10.1115/1.4036198 Item availability restricted.

PDF - Published Version Restricted to Repository staff only Available under License Creative Commons Attribution. Download (1MB)

Abstract

With the arrival of cyber physical world and an extensive support of advanced IT infrastructure, nowadays it is possible to obtain the footprints of design activities through emails, design journals, change logs, and different forms of social data. In order to manage a more effective design process, it is essential to learn from the past by utilizing these valuable sources and understand, for example, what design tasks are actually carried out, their interactions and how they impact each other. In this paper, a computational approach based on deep belief nets (DBN) is proposed to automatically uncover design tasks and quantify their interactions from design document archives. Firstly, a DBN topic model with real-valued units is developed to learn a set of intrinsic topic features from a simple word-frequency based input representation. The trained DBN model is then utilized to discover design tasks by unfolding hidden units by sets of strongly connected words, followed by estimating their interactions by their co-occurrence frequency in a hidden representation space. Finally, the proposed approach is demonstrated through a real-life case study using a design email archive spanning for more than two years.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Subjects:	T Technology > TJ Mechanical engineering and machinery
Publisher:	American Society of Mechanical Engineers
ISSN:	1530-9827
Date of First Compliant Deposit:	18 April 2016
Date of Acceptance:	15 April 2016
Last Modified:	06 May 2023 09:07
URI:	https://orca.cardiff.ac.uk/id/eprint/89368

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item