Tutorial on Swarm Intelligence for Sensor Networks Applications

kneewastefulAI and Robotics

Oct 29, 2013 (3 years and 11 months ago)

104 views

Tutorial
o
n

Swarm
Intelligence for Sensor Networks Applications

(Half Day Tutorial)



Abstract:


A sensor network is a network of distributed autonomous devices that can sense or monitor
physical or environmental conditions cooperatively. Sensor networks
are used in numerous
applications like environmental monitoring, habitat monitoring, prediction and detection of
natural calamities, medical monitoring and structural health monitoring. Advances in sensor
technology and computer networks have enabled senso
r networks to evolve from small
clusters of large sensors to large
networks

of miniature sensors, from wired communications
to wireless communications, and from static network topology to dynamic topology. In spite of
these technological advances, sensor n
etworks still face the challenges of communication
and processing of large amount of data in resource constrained environments.
A
lgorithms

of
swarm intelligence (SI)

have been widely used as attractive tools to address the challenges in
sensor networks.

SI

is
a computational

intelligence

paradigm

based on the
collective beh
avior

of
decentralized
,
self
-
organized
,

unsophisticated agents

which
interac
t

locally

with their environment
and
cause
coherent functional global

patterns to emerge
. The agents follow very simple rules, and
although there is no centralized control structure dictating how individual agents should
behave, local interactions between such agen
ts lead to the
emergence

of complex global
behavior. Natural examples of SI include
ant colonies
, bird
flocking
, animal
herding
,
bacterial
growth
, and fish
schooling
.

Successful applications
of SI include

function optimization, finding
optimal

routes, scheduling, structural optimization, and image and

data

analysis.

This tutorial will introduce
SI

and its algorithms,

and review recently reported
S
I applications
in sensor

networks.
Particle swarm optimization, ant colony optimization
,

and the hybrids of
these
algorithms
with other computational intelligence
paradigms
will be covered.

Emphasis
will be
given
on how the algorithms are
tailored

to address issues in sensor networks, namely
,

optimal sensor

placement, self coordination, optimal routing, source localization,

sensor
aggregation and fusion
, and
network

life extension
.


Speaker
s
:
Raghavendra
V.
Kulkarni,
Senior Member,

IEEE, and
Ganesh Kumar
Venayagamoorthy,
Senior Member
, IEEE
,
Real
-
Time Power

and Intelligent Systems
Laboratory
,

Department of Electrical and

Computer Engineering
,

Missouri
University of
S
cience and Technology,
Rolla, MO 65409, USA
.


Bios:


Raghavendra V. Kulkarni

(M’97

SM’05)

received the B.E. degree in electronics and
communication engineering from Karnatak University, Dharwad, India, in 1987 and the M.
Tech. degree in electronics enginee
ring from the Institute of Technology, Banaras Hindu
University, Varanasi, India, in 1994. He was an Assistant Professor with Gogte Institute of
Technology, Belgaum, India, prior to August 2006. He is currently pursuing his PhD. degree in
Electrical Engine
ering in the Missouri University of Science and Technology, Rolla, USA.


His research interests are in the development of computational intelligence tools for real world
applications in sensor networks. He is a life member of Indian Society for Technical E
ducation
(ISTE).



Ganesh Kumar Venayagamoorthy

(S’91

M’97

SM’02) received the B.Eng. degree (Hons.)
in electrical and electronics engineering from Abubakar Tafawa Balewa University, Bauchi,
Nigeria, in 1994, and the M.Sc.Eng. and Ph.D. degrees in electri
cal engineering from the
University of KwaZulu Natal, Durban, South Africa, in 1999 and 2002, respectively. He was a
Senior Lecturer with the Durban University of Technology, Durban, South Africa prior to
joining the Missouri University of Science and Tech
nology (Missouri S&T), Rolla, USA in
2002. Currently, he is an Associate Professor of Electrical and Computer Engineering and
Director of the Real
-
Time Power and Intelligent Systems Laboratory at Missouri S&T. He was
a Visiting Researcher with ABB Corporat
e Research, Vasteras, Sweden, in 2007. His
research interests are the development and applications of computational intelligence for real
-
world applications, including power systems stability and control, alternative sources of
energy, FACTS devices, power

electronics, sensor networks, collective robotic search, signal
processing and evolvable hardware. He has published 2 edited books, 5 book chapters, 55
refereed journals papers, and over 200 refereed international conference proceeding papers.
Dr. Venayag
amoorthy was an Associate Editor of the IEEE TRANSACTIONS ON NEURAL
NETWORKS (from 2004 to 2007) and the IEEE TRANSACTIONS ON INSTRUMENTATION
AND MEASUREMENT (2007). He is currently the IEEE St. Louis Computational Intelligence
Society (CIS) and IAS Chapte
r Chairs. He has organized and chaired several panels, invited
and regular sessions, and tutorials at international conferences and workshops. He is General
Chair of 2008 IEEE Swarm Intelligence Symposium and Program Chair of the 2009 IEEE
-
INNS Internation
al Joint Conference on Neural Networks. Dr. Venayagamoorthy was a
recipient of the 2007 US Office of Naval Research Young Investigator Program Award, the
2004 NSF CAREER Award, the 2006 IEEE Power Engineering Society Walter Fee
Outstanding Young Engineer A
ward, the 2006 IEEE St. Louis Section Outstanding Section
Member Award, the 2005 IEEE Industry Applications Society (IAS) Outstanding Young
Member Award, the 2005 SAIEE Young Achievers Award, the 2004 IEEE St. Louis Section
Outstanding Young Engineer Award
, the 2003 INNS Young Investigator Award, the 2001
IEEE CIS Walter Karplus Summer Research Award, five prize papers from the IEEE IAS and
IEEE CIS, a 2007 MST Teaching Commendation Award, a 2006 MST School of Engineering
Teaching Excellence Award, and a 20
07/2005 MST Faculty Excellence Award.