Evaluating a Human Computation Approach to Biologically Inspired Design

Computationally finding good inspiration for a design problem solution is a present research challenge that involves data processing, design knowledge management, and human creativity. Latent Semantic Indexing (LSI) has been used to find design analogies from functional models and patent documents, but requires that these source documents be lengthy enough to differentiate unique features. Humans are much better at finding related concepts from limited data, but lack comparable raw processing power. This work assesses a game that, as a side effect of playing, produces a network of generally valid assertions about biological phenomena. One goal of that game is to produce an automatically-populated database of biological phenomena that has better accuracy and resolution than purely computational approaches to finding design analogies. The goal of this paper is to assess the quality of the human-generated network generated from this game by benchmarking it against the overall document similarity predicted by LSI. The results suggest that the conceptual network created through human computation creates externally valid connections between related concepts, ultimately supporting the validity of this approach to facilitating biologically inspired design.

[1]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[2]  G. W. Stewart,et al.  On the Early History of the Singular Value Decomposition , 1993, SIAM Rev..

[3]  Erik T. Mueller,et al.  Open Mind Common Sense: Knowledge Acquisition from the General Public , 2002, OTM.

[4]  Ryan Arlitt,et al.  Using Human Computation to Assist Biologically Inspired Design: Evaluating a Game-With-a-Purpose , 2014 .

[5]  Gabriela Goldschmidt,et al.  Expertise and the use of visual analogy: implications for design education , 1999 .

[6]  Luis von Ahn.  Games with a Purpose , 2006, Computer.

[7]  Jonathan Cagan,et al.  The Meaning of “Near” and “Far”: The Impact of Structuring Design Databases and the Effect of Distance of Analogy on Design Output , 2012 .

[8]  Ashok K. Goel,et al.  Learning Generic Mechanisms for Innovative Strategies in Adaptive Design , 1997 .

[9]  Santosh S. Vempala,et al.  Latent semantic indexing: a probabilistic analysis , 1998, PODS '98.

[10]  Arthur B. Markman,et al.  INCREASING INNOVATION: PRESENTATION AND EVALUATION OF THE WORDTREE DESIGN- BY-ANALOGY METHOD , 2008 .

[11]  L. H. Shu,et al.  Automatic Extraction of Causally Related Functions From Natural-Language Text for Biomimetic Design , 2012 .

[12]  Kerry R. Poppa.  Theory and Application of Vector Space Similarity Measures in Computer Assisted Conceptual Design , 2011 .

[13]  J. Kolodner.  Educational implications of analogy. A view from case-based reasoning. , 1997, The American psychologist.

[14]  Susan T. Dumais,et al.  Improving the retrieval of information from external sources , 1991 .

[15]  Aric Hagberg,et al.  Exploring Network Structure, Dynamics, and Function using NetworkX , 2008, Proceedings of the Python in Science Conference.

[16]  Ashok K. Goel,et al.  DANE: Fostering Creativity in and through Biologically Inspired Design , 2011 .

[17]  Henry Lieberman,et al.  AnalogySpace: Reducing the Dimensionality of Common Sense Knowledge , 2008, AAAI.

[18]  Sriram Subramanian,et al.  Talking about tactile experiences , 2013, CHI.

[19]  L. H. Shu,et al.  A natural-language approach to biomimetic design , 2010, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[20]  Amaresh Chakrabarti,et al.  A functional representation for aiding biomimetic and artificial inspiration of new ideas , 2005, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[21]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[22]  Luis von Ahn.  Human Computation , 2008, ICDE.

[23]  Hugo Liu,et al.  ConceptNet — A Practical Commonsense Reasoning Tool-Kit , 2004 .

[24]  Manuel Blum,et al.  Verbosity: a game for collecting common-sense facts , 2006, CHI.

[25]  Kristin L. Wood,et al.  A Quantitative Similarity Metric for Design-by-Analogy , 2002 .

[26]  Ashok K. Goel,et al.  Learning Functional Models of Biological Systems for Biologically Inspired Design , 2011, 2011 IEEE 11th International Conference on Advanced Learning Technologies.

[27]  L. De Veylder,et al.  Transcriptional control of the cell cycle. , 2009, Current opinion in plant biology.

[28]  K. Holyoak,et al.  Analogical problem solving , 1980, Cognitive Psychology.

[29]  Claudia Eckert,et al.  REFERENCES TO PAST DESIGNS , 2005 .

[30]  P. Doerner,et al.  Cell cycle controls: genome-wide analysis in Arabidopsis. , 2001, Current opinion in plant biology.

[31]  Bo T. Christensen,et al.  The relationship of analogical distance to analogical function and preinventive structure: the case of engineering design , 2007, Memory & cognition.

[32]  Linden J. Ball,et al.  Spontaneous analogising in engineering design: a comparative analysis of experts and novices , 2004 .

[33]  D. Gentner.  Structure‐Mapping: A Theoretical Framework for Analogy* , 1983 .

[34]  Ann Heylighen,et al.  5.8 Analogies per Hour , 2002, AID.

[35]  Elizabeth R. Jessup,et al.  Matrices, Vector Spaces, and Information Retrieval , 1999, SIAM Rev..