Home
Currently Funded Projects
CAMRA is the EPA-DHS jointly funded Center for Advancing Microbial Risk Assessment. CAMRA gathers a community of scientists that investigate several stages in the life cycle of bacterial agents of concern. We are implementing a knowledge management (KM) approach with the goals of knowledge sharing, integration, and collaboration. Additional information available here: (CAMRA KM page @ Drexel iSchool). Download a paper about it here: (http://www.ischool.drexel.edu/faculty/rweber/pdf/43330315.pdf). Other Projects This team has recently demonstrated a breakthrough in using artificial intelligence to manipulate inductive models (Weber et al. 2005). We showed that a methodology based on analogical reasoning could be effectively used to recommend a model to represent a previously unknown data system based on the similarities between that system and previously known systems. Our study also showed how to manipulate models within such a reasoning methodology, addressing the problem of managing large amounts of data. Read about it here ( http://www.ischool.drexel.edu/faculty/rweber/pdf/Weberetal2005.pdf and here http://www.ischool.drexel.edu/faculty/rweber/pdf/f770327591462h27.pdf). Reasoning from text becomes reality when textual knowledge is used in case-based reasoning. Read about it here ( http://www.ischool.drexel.edu/faculty/rweber/pdf/cunn.pdf). Reasoning from experience can help project managers predict the outcome of a software development project and what to change in order to reverse an unwanted outcome. Read about it here (http://www.pages.drexel.edu/~rw37/iccbr03.pdf) and here (http://www.ischool.drexel.edu/faculty/rweber/pdf/flairs04.pdf). Inconspicuous content may be an intent, opinion, or underlying goal buried in text that may be disguised in some way to mislead automated methods but keeps a clear message for humans (e.g., terrorist sites, spam). Our approach relies on manual engineering for natural language interpretation and pattern extraction using no more than ten examples, but is sufficiently fast to complement methods based on term-frequencies in a real-time application (http://www.ischool.drexel.edu/faculty/rweber/pdf/37820304.pdf). This research investigates the extended use of a standardized knowledge representation formalism inspired by an industry-conceived knowledge artifact whose existence and validation depends upon its applicability to an existing process. The assumption is that such a formalism can support intelligent behavior by performing unobtrusive acquisition, understanding, reasoning, and continuous learning from experience, reducing knowledge engineering effort, the biggest bottleneck in building knowledge-based systems (KBS); and giving computer systems the ability to learn from their own experience.  Dr. Rosina Weber Associate Professor College of Information Science and Technology Drexel University 3141 Chestnut Street Philadelphia, PA 19104 (tel) +1-215-895-1911 (fax) +1-215-895-2494 Rosina.Weber@cis.drexel.edu Last modified in 2007 |