By Topic

Energy-Efficient Pattern Recognition Approach for Wireless Sensor Networks

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
2 Author(s)
Baqer, M. ; Monash Univ., Clayton ; Khan, A.I.

Event detection and monitoring is an important application class for wireless sensor networks. Traditionally, sensory data are collected and processed at the base-station. Conveying large amounts of multidimensional sensory data is however impractical in resource-constrained sensor networks. In this paper we propose to convert event detection into pattern recognition that is particularly suited for sensor networks. Individual sensory measurements of sensor nodes are integrated into high-level event pattern, and used for recovering the state of the monitored environment. The pattern storage and pattern recognition operations are performed in a distributed manner within the network. Furthermore, a sleep mode strategy is incorporated for improving performance and prolonging the lifetime of the sensor network.

Published in:

Intelligent Sensors, Sensor Networks and Information, 2007. ISSNIP 2007. 3rd International Conference on

Date of Conference:

3-6 Dec. 2007