Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/28264
Title: Distributed Optimisation in Wireless Sensor Networks: A Hierarchical Learning Approachs
Authors: YEOW WAI LEONG
Keywords: Hierarchical Learning, Distributed Optimisation, Sensor Networks
Issue Date: 9-Jun-2008
Source: YEOW WAI LEONG (2008-06-09). Distributed Optimisation in Wireless Sensor Networks: A Hierarchical Learning Approachs. ScholarBank@NUS Repository.
Abstract: Wireless sensor networks (WSNs) are an emerging technology of the 21st century. Massively deployed, tiny and intelligent sensors cooperatively network among themselves, instrument and control environments from wildlife habitats to homes and cities worldwide. However, with limited resource, can these tiny sensors meet hard application demands? This thesis addresses the question through hierarchical reinforcement learning. Reinforcement learning has its roots in Markov Decision Processes (MDP), which have been popularly used to model optimisation problems, and a hierarchical architecture makes it suitable for sensors. We addressed how soft constraints can be incorporated into MDP and apply it to optimise data quality and up-to-date data-gathering WSNs. We further develop a hierarchical solution for significant memory savings. The hierarchical architecture is further explored in multiple-target tracking which demonstrates significant energy savings with uncompromised accuracy. In all, hierarchical learning is effective in supporting two canonical applications of WSNs.
URI: http://scholarbank.nus.edu.sg/handle/10635/28264
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
YWL_thesis.pdf2.52 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

176
checked on Dec 15, 2017

Download(s)

187
checked on Dec 15, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.