Research Interests and Short Bio:
This is an exciting time to be. We have seen how the world becomes smaller and
“flat” due to
internet, Web, and a broad range of information and communication technologies. While these technologies have enabled us
to have access to a large amount of information; getting relevant
information to the right people in time remains a challenging problem
because we (human) have limited cognitive capacity in processing and
interpreting information. Many
research advancements in the academics and innovations in the industry in
the 21st century have (and will continue to) contribute toward
developing a comprehensive solution to this problem for a wide range of
applications.
One critical piece of this solution, we believe, is the
capability to quickly and accurately link what people needs to choose/decide
in a rapidly changing environment to what information they need to
have. To achieve this, we need a
technology that can understand “the context” of decision-makings, anticipate
relevant information requirements from the context, and proactively assist
decision making teams in seeking and sharing relevant information. Toward this vision, our research team (in
collaboration with Dr. Mike McNeese)
has developed a novel intelligent
agent technology, R-CAST,
inspired by a cognitive model about human decision-making under time stress,
namely Recognition-Primed
Decision (RPD) developed by Dr. Garry Klein.
Using a computational collaborative RPD model, R-CAST agents to support and collaborate
with human decision-making teams as both "smart aids" as well as an "effective teammates"
by anticipating, investigating, seeking, and interpreting informatoin relevant to
decision-makings. A key feature of R-CAST is that the proactive sharing of information
relevant to decision making is automatically generated by the computational RPD model.
The formal foundation of this feature, published in an
AI Journal article,
is an extension of SharedPlans theory, developed by Drs.
Barbara Grosz and Sarit Kraus,
using semantics of communication acts, developed by Drs. P. R. Cohen and
H. J. Levesque.
Our current projects related to R-CAST include
(1) human-agent collaboration, trust, and learning (with Dr. Mike McNeese),
(2) agent-based modeling of coordination of NGO's for disaster relief
(with Drs. Carleen Maitland and Andrea Tapia), and
(3) agent-based support for emergency medicine (with Drs. Madhu Reddy and Mike McNeese).
Yen's long-term research interest is to develop technologies
that facilitate human teams in transforming information into knowledge, decisions,
and actions. In addition to research related to R-CAST, his team is also
investigating technologies for extracting knowledge from large-scale social networks
and developing models that capture principles about the dynamic growth of
large-scale complex networks. For more information about his research,
please visit Laboratory for Intelligent Agents.
Yen received his Ph.D. in Computer
Science from University of California, Berkeley in 1986. His thesis
advisor is Prof. Lotfi A. Zadeh, the
father of fuzzy logic. Between 1986
and 1989, he was the main architect at USC Information
Sciences Institute (ISI) for an AI architecture that pioneers a
knowledge-level integration involving semantic-Web knowledge representation
technologies. From 1989 to 2001, he was a
Professor of Computer Science and the Director of Center for Fuzzy Logic,
Robotics, and Intelligent Systems at Texas A&M University. He joined Penn State's new information school (i.e., College of Information Sciences and Technology) in 2001, and became Professor-in-Charge from 2003 to 2007. He is currently the Associate Dean for Research and Graduate Programs of the college. Yen was
the Vice President of Publication for IEEE Neural Networks Council, now IEEE Computational Intelligence Society. He received the NSF Young Investigator Award in 1992, and is a Fellow of IEEE.
He is currently the Chair of IEEE FIPA Working Group on
Human Agent Communications, a Sponsoring co-Chair of AAMAS 2008, and a member of ACM Senior Member Committee.
|
