An
Integrated Model of Information Security and Risk
Management
Funding
source: Bear Stearns Research Center
Abstract: Empirical
research is required to determine security risks, and to
verify
the effectiveness of security technologies. The proposed research will
first empirically determine the probability of breaches for various
information security controls. It will then provide an
approach that is grounded in empirical data for assessing the
probability of security breaches for various security configurations.
Finally, an analytical model for
determining the optimal security configuration will be developed.
Publications
“Assessing
and managing
information security risk: An experimental investigation and analytical
modeling,”
Kaushal Chari, Manish Agrawal and Varol Kayhan
(working paper)
Prediction
and Estimation Markets
Abstract: Information markets are mechanisms
that allow a group of possibly geographically dispersed participants to
reach and continuously re-evaluate consensus by discovering the value
of alternative outcomes. Evidence suggests that these
markets can
produce better quality decisions than a small subset of selected
decision makers: a finding in direct opposition to the trust we place
on expertise. In challenging and uncertain decision making
arenas
information markets offer an interesting, and somewhat
counter-intuitive approach. In practice, information markets
may be
used in combination with other decision making methods, but these
market-based mechanisms offer many advantages.
Market types include
event and estimation-based prediction markets, decision markets, and
idea markets. This research investigates an integrated
research
landscape that is assessing various aspects of market types.
Notably,
the use of information markets to continually aggregate the individual
estimates of diverse software project stakeholders. A market
mechanism
for software cost estimation has been designed to explore the
characteristics that make such an approach possible, and initial
experiments based on a simple estimation tasks have been completed.
Publications:
“Project
Management Markets”,
Berndt, D.J. and Jones, J.L., Project
Management Institute (in press, 2008), Newtown Square, PA
“Is
That a Cultural
Cluster? Mining Trading Behaviors in Prediction Markets”,
Berndt, D. J., A.M. Yassin, J.L. Jones, R. W. Collins, 8th Annual
Global Information Technology Management Association World Conference,
Naples, Italy 17-19 June 2007
“Workshop
on Information
and Prediction Markets”,
Berndt, D., Jones, J.L. and
Collins, R., Global Information Technology Management Association
(GITMA) World Conference, June 11-13, 2006, Orlando FL
“Milestone
Markets:
Software Cost Estimation through Market Trading”, Berndt,
D., Jones, J.L. and Finch, D., Proceedings of the Thirty-ninth Annual
Hawaii International Conference on Systems Sciences, January 2006,
Kauai, Hawaii
“Authority, Credibility, Power and Rewards in Global Information Markets”, Yassin,
A.M., R. W. Collins, and D.J. Berndt, 8th Annual Global Information
Technology Management Association Conference, Naples Italy, June 17-19,
2007. (Refereed)
“The Impact of Culture on Global Information Markets for Software Cost Estimation”, Yassin, A.M., R. W. Collins, and D.J. Berndt, 7th Annual Global Information Technology Management Association Conference, Orlando FL., June 11-13, 2006. (Refereed)
Software
Agents for Automated Negotiations
Abstract: This
research develops software agents that can automate negotiations by
implementing a multi-issue learning heuristic. Agents learn
from
the bidding behavior of opponents. The performance of agents is
evaluated using
an experimental study involving human subjects. Results indicate that
software agents can act as effective surrogates of human negotiators.
Publications
“Negotiation behaviors in agent-based
negotiation
support
systems”, Manish
Agrawal and Kaushal Chari, International
Journal of
Intelligent Information Technologies, (to appear)
“Multi-issue automated negotiations
using agents”,
Kaushal Chari and Manish Agrawal,
INFORMS Journal on Computing, 19 (4), pg. 588-595, Fall 2007
Auctions
Abstract: Today’s supply chains
require more
dynamic trading
practices to better match suppliers with their customers.
Additionally,
the purchase decisions faced are rarely made on price alone; but rather
on a
bundle of attribute values. With ubiquitous computing and
Internet
connectivity, newer types of negotiation are emerging such as reverse
auctions. This research looks to develop a heuristic
algorithm for
multi-attribute reverse auction bid selection that considers two tiers
of the
supply chain. The suppliers place bids to meet just-in-time
requirements
of a manufacturer to quote their consumers’ RFQs. The
heuristic solution
is a collection of near optimal bids that attempt to maximize overall
profit
subject to capacity constraints, supplier delivery dates, and component
costs,
as well as consumer late delivery penalties.
Publications
“An Allocation Heuristic
For
Multi-Attribute
Supply Chain Reverse Auctions”, Jones, J.L. and
Jarman, J., Twenty Eighth
International Conference on
Information Systems, Montréal, Québec, Canada December 9 - 12, 2007
Bioterrorism
Surveillance Systems
Abstract: The use of real-time or flash data warehousing provides the essential
ability to compare unfolding health events with historical patterns of
key surveillance indicators. A principal contribution of this
research is the adroit use of online analytic processing (OLAP)
techniques, along with spatial and statistical analyses, to study the
adverse effects of biochemical agents. These techniques will
provide important capabilities for epidemiologist-in-the-loop
surveillance systems, enabling the rapid exploration of unusual
situations and guidance for follow-up investigations.
Publications
“The
Role of Data
Warehousing for Bioterrorism Surveillance”,
D. Berndt, J. Fisher, J. Griffiths, A. Hevner, S. Luther, and J.
Studnicki, Decision Support Systems, Special Issue on
Cyberinfrastructure for Homeland Security, 43(4): 1383-1403, August
2007.
“Managing
Real-Time
Bioterrorism Surveillance Data”,
D. Berndt, A. Hevner, and J. Griffiths, Chapter in National
Security, Edited by H. Chen, T.S. Raghu, R. Ramesh, A. Vinze, and D.
Zeng, Handbooks in Information Systems Series, Elsevier, Inc., 2006.
Software
Testing
Funded
by: National Institute for Systems Test and Productivity
(NISTP), (A National Research Center funded by USA Space and Naval
warfare Systems Command, Grant No. N00039-01-1-2248)
Abstract: This
research extends an exponential reliability growth model to
determine the optimal number of test cases to be executed for various
use case scenarios during the system testing of software.
Publications
“System
Test Planning of Software: An Optimization Approach”,
Kaushal Chari and
Al Hevner, IEEE Transactions on Software Engineering, 32(7), pg.
503-509, July 2006
Decision
Fusion
Abstract: Improved classification performance has practical real-world
benefits ranging from improved effectiveness in detecting diseases to
increased efficiency in identifying firms committing financial frauds.
Multi-classifier combination (MCC) aims to improve classification
performance by combining the decisions of multiple individual
classifiers. In this paper we present Information Market based Fusion
(IMF), a novel multi-classifier combiner method for decision fusion
that is based on information markets. In IMF, the individual
classifiers are implemented as participants in an information market
where they place bets on different object classes. The reciprocals of
the market odds that minimize the difference between the total betting
amount and the potential payouts for different classes represent the
MCC probability estimates of each class being the true object class. By
using a market based approach, IMF can adjust to changes in
base-classifier performance, while not requiring training data or a
static ensemble composition. Experimental results show that when the
true classes of objects are only revealed for objects classified as
positive, for low positive ratios, IMF outperforms three benchmarks
combiner methods, Majority, Average and Weighted Average
Publications
“Information Market Based Decision Fusion”, Johan Perols, Kaushal Chari and Manish Agrawal, Management Science, (Forthcoming)
“Information
Market Based Decision Fusion”, Johan Perols,
Kaushal Chari
and Manish Agrawal, Utah Winter Conference, Feb. 2007
“Information
Market
Based Decision Fusion”,
Johan Perols, Kaushal Chari
and Manish Agrawal, ICIS 2006, Milwaukee, WI, Dec. 2006
“Information
Fusion and
Information Markets in Multi-Agent Systems”,
Johan Perols and Manish Agrawal, WITS 2005, Las Vegas, Dec. 2005
Health
Informatics
CATCH Data Warehouse
Funding
source: U.S. Department of Commerce
Abstract: The Comprehensive
Assessment for Tracking Community Health (CATCH) data warehouse
provides systematic methods for community-level assessment that is
invaluable for resource allocation and health care policy
formulation.
CATCH is based on health status indicators from multiple data sources,
using an innovative comparative framework and weighted evaluation
process to produce a rank-ordered list of critical community health
care challenges. The community-level focus is intended to
empower
local decision-makers by providing a clear methodology for organizing
and interpreting relevant health care data. Extensive field
experience
with the CATCH methods, in combination with expertise in data
warehousing technology, has led to an innovative application of
information technology in the health care arena.
Publications
“Hispanic
Health Status
in Orange County, Florida”,
J. Studnicki, D. Berndt, S. Luther, J. Fisher, K. van Caulil, M.
Brennan, Y. Martinez, and P. Clarke, Journal of Public Health
Management and Practice, 11(4): 326-332, 2005.
“The
Application of
Volume-Outcome Contouring in Data Warehousing”,
J. Studnicki, D. Berndt, S. Luther, and J. Fisher, Journal of
Healthcare Information Management, 18(4): 49-55, Fall 2004.
“The
CATCH Data
Warehouse: Support for Community Health Care Decision Making”,
Donald J. Berndt, Alan R. Hevner, and James
Studnicki, Decision Support Systems, 35: 367-384, 2003.
Text Mining
of Electronic Medical Records
Abstract: This research investigates the use of computer-based methods
of
extracting information from the textual components of medical
records.
Progress notes and patient histories represent a rich source of data
that is difficult to use in large-scale studies. Unlocking
these
sources of information is an important goal. Again, this
electronic
medical record research could offer tremendous opportunities in the
classroom.
Publications
“Use
of Artificial
Neural Networks to Determine Cognitive Impairment
and Therapeutic Effectiveness in Alzheimer’s Transgenic Mice",
R. Leighty, M. Runfeldt, D. Berndt, W. Schleif, J. Cracchiolo, H.
Potter, and G. Arendash, Journal of Neuroscience Methods, 167(2):
358-366, January 2008.
“Feature
Selection for
Predicting Surgical Outcomes”,
Monica Chiarini Tremblay, Donald J. Berndt, and James
Studnicki, Proceedings of the 39th Hawaii International
Conference on
System Sciences (HICSS 39), January 4-7, 2006.
“Utilizing
Text Mining
Techniques to Identify Fall Related Injuries”,
M. Chiarini-Tremblay, D. Berndt, P. Foulis, and S. Luther, Proceedings
of the Eleventh Americas Conference on Information Systems (AMCIS
2005), Omaha, Nebraska, August 11-14, 2005.
“Using
Knowledge
Discovery in Databases to Identify Fall-Related Injuries”,
S. L. Luther, M. Tremblay, D. J. Berndt, P. Foulis, D. D. French, L. Z.
Rubenstein, Academy Health Annual Research Meeting, Boston,
Massachusetts, 2005. |
