Hyunmin Cheong

  • Citations Per Year
Learn More
This paper reports insights gained from observing groups of novice designers apply biological analogies to solve design problems. We recorded the discourse of fourth-year mechanical engineering students during biomimetic design sessions. We observed that the availability of associations from superficial or functional characteristics of biological knowledge(More)
While biology is well recognized as a good source of analogies for engineering design, the steps of 1) retrieving relevant analogies and 2) applying these analogies are not trivial. Our recent work translated the functional terms of the Functional Basis into biologically meaningful keywords that can help engineers search for and retrieve relevant biological(More)
Identifying relevant analogies from biology is a significant challenge in biomimetic design. Our naturallanguage approach addresses this challenge by developing techniques to search biological information in naturallanguage format, such as books or papers. This paper presents the application of natural-language processing techniques, such as part-of-speech(More)
The natural-language approach to identifying biological analogies exploits the existing format of much biological knowledge, beyond databases created for biomimetic design. However, designers may need to select analogies from search results, during which biases may exist towards: specific words in descriptions of biological phenomena, familiar organisms and(More)
We show how four-bar linkages can be designed using non-convex optimization techniques. Our generative design software takes as input a curve that needs to be reproduced by a four-bar linkage and outputs the best assembly that approximates this curve. We model the problem using quadratic constraints and show how redundant constraints help to solve the(More)
Biology has long been recognized as an excellent source of analogies and stimuli for engineering design. Previous work focused on the systematic identification of relevant biological analogies by searching for instances of functional keywords in biological information in natural language format. This past work revealed that engineering keywords couldn’t(More)
This paper presents a method to automatically extract function knowledge from natural language text. Our method uses syntactic rules to extract subject-verb-object triplets from parsed text. We then leverage the Functional Basis taxonomy, WordNet, and word2vec to classify the triplets as artifactfunction-energy flow knowledge. For evaluation, we compare the(More)