Person:
Goel, Ashok K.

Permanent Link
https://hdl.handle.net/1853/71296
Associated Organization(s)
ORCID
ArchiveSpace Name Record

Filters

2002 - 2009 4
4
3 1
4
Reset filters

Settings
Item Type: Publication × Start date: 2000 × End date: 2009 ×

Publication Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Playing Detective: Using AI for Sensemaking in Investigative Analysis
    (Georgia Institute of Technology, 2009) Goel, Ashok K. ; Adams, Summer ; Cutshaw, Neil ; Sugandh, Neha
    The sensemaking task in investigative analysis generates models that connect entities and events in an input stream of data. We describe two knowledge systems for aiding sensemaking in investigative analysis. The Spade system uses crime schemas to generate an explanatory hypothesis and past cases to validate the hypothesis. The STAB system represents crime schemas as hierarchical scripts with goals and states. It generates multiple explanatory hypotheses for an input data stream containing interleaved sequences of events, recognizes intent in a specific event sequence, and calculates confidence values for the generated hypotheses. We view STAB and Spade as automated cognitive assistants to human analysts: they may support sensemaking in investigative analysis by generating and managing multiple competing hypotheses.
  • Thumbnail Image
    Item
    Learning About and Through Biologically Inspired Design
    (Georgia Institute of Technology, 2008-06-22) Vattam, Swaroop ; Helms, Michael E. ; Goel, Ashok K. ; Yen, Jeannette ; Weissburg, Marc J.
    Biologically inspired design (BID) uses biological systems as analogues to develop solutions for design problems. Although designers have been looking to nature for inspiration for eons, only recently is BID gaining in importance as a wide-spread movement in design for environmentally-conscious sustainable development (e.g., Benyus 1997). But it is the tendency of the “products” of BID to be radically innovative (Forbes 2005; French 1998; Vogel 2000) that makes BID an interesting case for research in design creativity.
  • Thumbnail Image
    Item
    Biologically-Inspired Innovation in Engineering Design: a Cognitive Study
    (Georgia Institute of Technology, 2007) Vattam, Swaroop ; Helms, Michael E. ; Goel, Ashok K.
    Biologically-inspired design uses analogous biological phenomena to develop solutions for engineering problems. Understanding, learning and practicing this approach to design is challenging because biologists and engineers speak different languages, have different perspectives on design, with different constraints on design problems and different resources for realizing an abstract design. In Fall 2006, we attended ME/ISyE/MSE/PTFe/BIOL 4803: Biologically-Inspired Design, an interdisciplinary introductory course for juniors and seniors offered at Georgia Tech. We collected course materials, took class notes, observed teacher-student and student-student interactions in the classroom. We also observed some sessions of a few interdisciplinary teams of students engaged in their design projects outside the classroom. We then analyzed the observations in terms of existing cognitive theories of design, modeling, and analogy. The goals of this cognitive study were to (1) understand the cognitive basis of biologically-inspired innovation in engineering design, (2) identify opportunities for enabling more effective learning of biologically-inspired design, and (3) examine the implications for developing computational tools for facilitating effective biologically-inspired design. This report summarizes our main observations about learning biologically-inspired design, and presents our preliminary analysis of biologically-inspired design in a classroom setting.
  • Thumbnail Image
    Item
    Using Spatial Structure in the Associative Retrieval of 2-D Line Drawings
    (Georgia Institute of Technology, 2002) Yaner, Patrick W. ; Goel, Ashok K.
    We consider the problem of associative image retrieval, focusing on retrieval of 2-D line drawings by example. We represent 2-D line drawings as semantic networks of spatial elements and relations among them. We describe a process for retrieving the drawings based on a structural analogy between the query and the stored images. We then present several methods of retrieving the drawings: the first family methods uses logical unification and resolution to accomplish the matching; the second family of methods heuristically prunes the stored drawings and then does the resolution and unification on the remaining drawings; two more methods treat the retrieval problem as a constraint satisfaction problem and use common CSP techniques for solving it; and the last two methods combine the heuristic step of the second method with the CSP technique of the third and fourth. We report on experimental results that compare the performance of these methods on computer-based libraries of drawings. A surprising result of our work is that for the fastest of these methods two stage retrieval appeared to offer no benefit over one stage retrieval.