Event Detection in Wireless Sensor and Actuator Networks

Description of research

A wireless sensor network (WSN) is typically composed of a large number of small, low-power, and cheap sensor nodes distributed over a large area. WSN can be considered as a large distributed database in which users can make some queries or it can be reactive and push information or alerts upon detection of events. Designing effective and efficient event detection techniques coping with limited resources of WSNs is the goal of this research.

Event detection can be done in two ways: (1) centralized (in a base station) and (2) decentralized (in-network). In this research we focus on decentralized event detection, in which sensor nodes collaboratively detect events using Artificial Intelligence, data-fusion, and distributed pattern recognition performed locally in the WSN. Since WSNs can be deployed in different environments (contexts) for different applications, number and type of events may vary under different circumstances and context. Consequently, we aim at designing online, distributed, and adaptive event detection to cope with dynamic nature of the deployment area, use cases, and the network itself.

Advisor(s)

Prof. dr. Ir. Paul J. M. Havinga

Dr. ir. Nirvana Meratnia

Duration

2008 - 2012

Project

SENSEI (Integrating the Physical with the Digital World of the Network of the Future)

Funding institution

EU FP7 Framework

Strategic Research Orientation

WiSe - Wireless and Sensor Systems

Links to relevant web pages:

http://ps.cs.utwente.nl/

http://www.ict-sensei.org/index.php

http://wwwhome.cs.utwente.nl/~bahrepourm/

Publications

Pictures

Majid Bahrepour

	CTIT Home > Meet the PhDs > Majid Bahrepour
Home CTIT symposium 2013 About CTIT News NIRICT Research Meet the PhDs Working at CTIT Internal Information Conferences Open Calls (updated May 3, 2013) Library and Videos Knowledge Transfer Links Sitemap Search	Event Detection in Wireless Sensor and Actuator Networks Description of research A wireless sensor network (WSN) is typically composed of a large number of small, low-power, and cheap sensor nodes distributed over a large area. WSN can be considered as a large distributed database in which users can make some queries or it can be reactive and push information or alerts upon detection of events. Designing effective and efficient event detection techniques coping with limited resources of WSNs is the goal of this research. Event detection can be done in two ways: (1) centralized (in a base station) and (2) decentralized (in-network). In this research we focus on decentralized event detection, in which sensor nodes collaboratively detect events using Artificial Intelligence, data-fusion, and distributed pattern recognition performed locally in the WSN. Since WSNs can be deployed in different environments (contexts) for different applications, number and type of events may vary under different circumstances and context. Consequently, we aim at designing online, distributed, and adaptive event detection to cope with dynamic nature of the deployment area, use cases, and the network itself. Advisor(s) Prof. dr. Ir. Paul J. M. Havinga Dr. ir. Nirvana Meratnia Duration 2008 - 2012 Project SENSEI (Integrating the Physical with the Digital World of the Network of the Future) Funding institution EU FP7 Framework Strategic Research Orientation WiSe - Wireless and Sensor Systems Links to relevant web pages: http://ps.cs.utwente.nl/ http://www.ict-sensei.org/index.php http://wwwhome.cs.utwente.nl/~bahrepourm/ Publications Pictures