Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/49377
Title: CONCEPT GENERATION SUPPORT BY CONCEPTUAL BLENDING: MULTI-AREA INSPIRATION SEARCH
Authors: DO THANH MAI
Keywords: Google statistics,support system, MAI Search, multi area inspiration search, conceptual blending, concept generation
Issue Date: 22-Aug-2013
Source: DO THANH MAI (2013-08-22). CONCEPT GENERATION SUPPORT BY CONCEPTUAL BLENDING: MULTI-AREA INSPIRATION SEARCH. ScholarBank@NUS Repository.
Abstract: This work describes a concept generation system to provide an ideation support in a very early phase of creativity. We focus on cross-domain innovation in a new search scheme called Multi-area Inspiration Search. The Search is an application of Conceptual Blending, which provides inspiration search results in different areas of knowledge from that of a query. We first formalize Conceptual Blending framework based on Conceptual Graph to establish a theoretical foundation. We then apply the Search to Biomimicry, a research branch mimicking nature design in engineering solutions. An empirical study in Biomimicry with up to 7000 concepts provides promising results and justifies the use of statistical measure, Google Normalize Retrieval Distance in cross-domain search. We produced reasonable and intuitive relatedness measure in all experiment cases. The Search is able to classify and rank results to expected inspiration group for complex source and query.
URI: http://scholarbank.nus.edu.sg/handle/10635/49377
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Concept Generation Support by Conceptual Blending MAIS - Experiment Data.xlsm25.11 MBUnknown

OPEN

NoneView/Download
DoTM.pdf2.32 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

124
checked on Dec 11, 2017

Download(s)

80
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.