Special Issue on Biologically Inspired Design
Ashok K. Goel, Daniel A. McAdams, Robert B. Stone
- Year
- 2014
- Citations
- 3
Abstract
In 2011 and 2012, we organized two workshops on computer-aided bio-inspired design sponsored by the United States National Science Foundation (NSF). These workshops brought together a few dozen leading researchers in computational methods and tools for biologically inspired design,1 and led to an edited volume [1]. The first chapter of the volume reports on the discussions at the two workshops. The success of the two workshops also led to this JMD special issue.The special issue consists of 13 significant articles. The first section contains two survey articles. In “‘Where Are We Now and Where Are We Going?’: The BioM Innovation Database,” Jacobs, Nichol, and Helms carefully and rigorously attempt to identify and archive the state of bio-inspired design practice as it exists in actual artifacts, products, and systems. Specifically, the authors address four questions. (1) Are products which are identified as being bio-inspired actually bio-inspired? (2) To what extent do bio-inspired designs mimic the forms, processes, and interactions of biological systems? (3) To what extent do bio-inspired designs exploit the scale and range of biological systems? (4) What patterns of design practice can we learn from successful bio-inspired design practitioners? Their process begins by collecting existing bio-inspired designs into a database that they can query for specific information about the design. Specific information is collected on 380 designs. The research team extensively interviewed bio-inspired design practitioners to create rich and detailed knowledge about the bio-inspired design. Although the processing and documentation of the state of bio-inspired design is ongoing, the research team did learn that more designs are solution based than challenge based, most designs claiming to be bio-inspired are, and most bio-inspired design teams are multidisciplinary and struggle with communication between the disciplines. Also, the research team discovered that bio-inspired design may be co-opted as a marketing element, thus decreasing the value and rigor of the bio-inspired design process.In “Bio-Inspired Design: An Overview Investigating Open Questions From the Broader Field of Design-by-Analogy,” Fu, Moreno, Yang, and Wood examine bio-inspired design practices in the broader context of design-by-analogy strategies. The seminal works in bio-inspired design are reviewed through a comparative qualitative research method and a quantitative analysis. Five major research thrusts emerge from the published methods and tools for supporting bio-inspired design and are categorized as methods, taxonomies, tools, and computational tools. The bio-inspired design research thrusts are assessed against known cognitive and implementation factors in the broader design-by-analogy field and opportunities for future improvement are identified. The study of bio-inspired design is concluded to be a fruitful route to innovation and with strong foundation laid for further investigation of diverse and rigorous approaches.Under Design Informatics, the paper by Glier, McAdams, and Linsey titled “Exploring Automated Text Classification to Improve Keyword Corpus Search Results for Bioinspired Design” examines the use of text mining techniques for accessing biology articles from a corpus relevant to a design problem specified by keywords. They compare three classification techniques for the task: a Naïve Bayes classifier, a k-Nearest Neighbor classifier, and a Support Vector Machine. Each of these techniques was first trained on data generated by human subjects. The three techniques were then tested on a corpus of single sentences selected from biology journals. Glier, McAdams, and Linsey found that the Naïve Bayes classifier performed best with a precision of 0.86, a recall of 0.52, and an F score of 0.65.Vandevenne, Verhaegen, and Duflou in “Mention and Focus Organism Detection and Their Applications for Scalable Systematic Bio-Ideation Tools” describe a technique
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991