Creating Knowledge with Data Science for Design in Systems

Time: Fri 2019-10-11 09.30

Location: T2, Hälsovägen 11, 141 57, Huddinge (English)

Subject area: Technology and Health

Doctoral student: Vinutha Magal Shreenath , Skolan för kemi, bioteknologi och hälsa (CBH), Biomedical Engineering and Health Systems

Opponent: Professor John Gero, University of North Carolina at Charlotte

Supervisor: Professor Sebastiaan Meijer, Hälsoinformatik och logistik; Universitetslektor Jannicke Baalsrud Hauge, Skolan för industriell teknik och management (ITM)

Abstract

Designing in large-scale engineering systems is a difficult cognitive task undertakenby experts. Knowledge of experts continually changes as they are confrontedwith similar by different problems in designing in such systems. However, it is alsoimportant that designers are presented information that is representative of the system,and that they are cognizant of activities on a system scale so they can create diversechoices for designs in early phase of design process.Data Science has been proven to be effective at informing people for decisions atimmediate horizons. But the use of data science to drive long terms designs whereexperts have to make the right series of decisions i.e. designs is yet unknown. The useof data science is to inform decision makers of activities at system scale.In this thesis, I have looked at how data science can be used to create knowledge indesigners for designing in large scale systems. I have also investigated further questionsregarding imitation of expertise using AI, and in generating similar knowledge bycreating diverse options in design.The results point out that data science can indeed inform designers, change theirdesigns and hence create knowledge. They also point out that design cognition inexperts can be partly imitated in data science itself, through careful modeling of theill-defined problem in design. This therefore points to a promising future directionwhere data can be used as an interface between human thinking and machine learning,by translation of conceptual forms such as differential diagnoses and cognitive artefactsusing data.

urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259566

Page responsible:Sabina Fabrizi
Belongs to: CBH
Last changed: Oct 03, 2019