|
|
Complex Adaptive System (CAS) is a large-scale and highly
distributed environment, which can tune itself via simple
rule-based interactions between its components. One of the most
intriguing features of CAS is the ability of such simple
interactions to form complex and “rational” system behavior.
CASs manifested themselves in various disciplines ranging
from life sciences (e.g., organizational behavior of ants and
patterns of neuronal activation) to social sciences and
economics (e.g., formation of social networks and market
regulations). In this project we explore application of the CAS
concepts in the context of information science and technology.
Rapid evolution of Web and networked information systems
strongly stimulates this research. Meanwhile, building and
deploying industrial-strength Complex Adaptive Information
Systems (CAIS) require more interdisciplinary research efforts.
This project includes the following tasks:
Task 1: Adaptive wireless sensor networks.
Task 2: Adaptive online social networks.
In
this task we explore the emergent complexity of Data Intensive
Sensor Networks (DISNs) to adapt to application requirements via
light-weight localized adjustments of the interaction between
sensors. The successful delivery of information in DISNs is
impaired by various problems such as congestion, collisions and
no route available for data in the network. The combined effect
of those factors is hard to estimate and this is one of the
major reasons why existing optimization solutions have very
limited applicability in DISN.
Our
approach is based on considering the WSN as a complex adaptive
system, where decisions made locally by individual sensors can
efficiently converge into desirable information processing
patterns.
We
investigate how such adaptation helps to meet high performance
requirements of mission-critical applications. As an example of
dealing with such application we
introduced a novel strategy for sensor data processing that
supports fire evacuation with stringent delay constraints. In
this case sensornet performs distributed emergency assessment,
continuous emergency monitoring, and dynamic selection of
optimal evacuation strategies. A notable feature of our method
is its scalability, which allows the sensornet to operate with
sufficient quality of service under heavy information loads.
The
evolution of information and communication technologies
introduces new ways to utilize information as it is getting more
accessible. Wide proliferation of Internet, Web technologies and
mobile devices facilitates further information consolidation in
networked human-centered environments. Such environments provide
us with a unique opportunity to observe, collect, and analyze
communication and information processing patterns in large-scale
collaborative communities. The emerging concept of soft sensing
and collective intelligence contributes to efficient information
fusion and sensemaking strategies, which are in the focus of
this task. In particular, we explore adaptive techniques for
automatic information reliability assessment in social networks.
Our approach utilizes subjective logic and cognitive human
traits to assess information reliability, as well as expertise
of the information provider. As a sub-project within this task
we develop a scalable
Self-Adaptive Learning through Teaching
(SALT) technology that implements efficient social adaptive
learning methodologies. This is achieved by allowing students
to be actively involved in the process of
learning-through-teaching via lightweight social
interactions. To sum up, SALT technology extends the concept of
OSN utilizing collective intelligence to gain educational
knowledge.
PhD
Students:
Andrii Cherniak
Evgeny Karataev
Alumni:
Chih-Kang Lin
Divyasheel Sharma
(ABB, India)
Selected
References:
-
Ren, Y.,
Zadorozhny, V., Oleshchuk, V., Li, F.
A Novel Approach to Trust
Management in Unattended Wireless Sensor Networks. To appear
in
IEEE Transactions on Mobile
Computing,
2013.
-
Zadorozhny, V., Lewis, M. Information Fusion based on
Collective Intelligence for Multi-Robot Search and Rescue
Missions. To appear in
Proceedings of
the 14th International Conference on Mobile Data
Management (MDM’13),
2013.
-
Ren, Y.,
Zadorozhny, V., Oleshchuk, V., Li, F. An Efficient, Robust,
and Scalable Trust Management Scheme for Unattended Wireless
Sensor Networks. Proceedings of the 13th
International Conference on Mobile Data Management (MDM’12),
2012. (Best Paper Award)
-
Lin, C-K., Zadorozhny, V., Krishnamurthy, P., Park, H.,
Lee, C. A Distributed and Scalable Time Slot Allocation
Protocol for Wireless Sensor Networks. IEEE Transactions
on Mobile Computing, v. 10, N. 4, 2011.
-
Pelechrinis, K., Zadorozhny,
V.,Oleshchuk,V. A Cognitive-based Scheme for User
Reliability and Expertise Assessment in Q&A Social Networks.
Proc. of the International Workshop on Issues and
Challenges in Social Computing (WICSOC'11). In conjunction
with the 12th IEEE International Conference on Information
Reuse and Integration, 2011.
-
Sharma, D. Zadorozhny, V.
Adaptive Information Delivery in Data-Intensive Sensor
Networks. Proc. of the 12th International Conference on
Mobile Data Management (MDM'11), 2011 .
-
Cherniak,
A., Zadorozhny, V. Towards Adaptive Sensor Data Management
for Distributed Fire Evacuation Infrastructure. Proceedings of the 11
th International Conference
on Mobile Data Management (MDM'10), 2010.
-
Zadorozhny, V., Sharma, D. Intelligent Adaptation in Data
Intensive Sensor Networks (Tutorial). The
7-th International Scientific and Practical Conference on
Programming,
Kiev, Ukraine, 2010
-
Lin, C-K., Zadorozhny, V., Krishnamurthy, P., Adaptable
Probabilistic Transmission Framework for Wireless Sensor
Networks. Proc. of 3rd International
Conference on Sensor Technologies and Applications,
Best Paper Award, 2009.
Complete
list of publications
|
|