ERA Research Laboratory Demonstrations
Image Provenance to Learn
(IP2Learn)
The size, complexity, and heterogeneity of geospatial collections pose formidable challenges for the National Archives in terms of high performance data storage, access, integration, analysis, and visualization. These challenges become even more complex when temporal aspects of data processing are involved. One example is capturing electronic records produced by computer-aided decision-making processes.
One of NARA's ERA Research partners, the National Center for Supercomputing Applications (NCSA), is part of a team that is addressing the problems of gathering, preserving, and analyzing information about decision-making processes using geospatial electronic records. The ultimate goal of this collaboration is to understand the cost of long term preservation of such electronic records using the cutting edge technologies, high performance computing, and novel computer architectures.
IP2Learn provides software tools for (a) simulating complex decision-making scenarios, (b) preserving the gathered information in data containers that are sustainable over the long term, and (c) reconstructing those decision-making processes.
IP2Learn focuses on decision processes based on examining images, tracking all operations by a user during image inspection, and reconstructing the image-based decision process by using multiple variable settings.
It allows archivists, for example, to empirically examine the tradeoffs related to the questions: what should be preserved; how should the data be gathered, stored, and retrieved; how should the decision-making processes be reproduced; and what questions will researchers be able to answer using the reproduced information.
The prototype can record and reproduce information about how a digital image is manipulated (e.g., select, crop, magnify, or adjust the color of an image) at varying levels of detail - from a textual summary of the actions taken to a full video replay of the actions taken in inspecting an individual image.
IP2Learn also captures, summarizes, and displays information about the costs (storage space and computing cycles) associated with each approach to capturing, preserving, and providing access to these records. We envision the use of IP2Learn for not only evaluations of cost versus information granularity tradeoffs of information gathering, but also for auditing and quality control purposes, as well as for education and training purposes.
For more information about IP2Learn, visit the web site at:
http://isda.ncsa.uiuc.edu/CompTradeoffs/
Page Last Updated: 06/06/08
