eCite Digital Repository

Autonomous framework for sensor network quality annotation: maximum probability clustering approach


Dutta, R and Das, A and Smith, D and Aryal, J and Morshed, A and Terhorst, A, Autonomous framework for sensor network quality annotation: maximum probability clustering approach, Procedia Computer Science Volume 29: ICCS 2014, 10-12 June 2014, Cairns, Australia, pp. 2201-2207. ISSN 1877-0509 (2014) [Refereed Conference Paper]


Copyright Statement

Copyright The Authors. Licenced under Creative Commons Attribution 3.0 (CC BY 3.0)

DOI: doi:10.1016/j.procs.2014.05.205


In this paper an autonomous feature clustering framework has been proposed for performance and reliability evaluation of an environmental sensor network. Environmental time series were statistically preprocessed to extract multiple semantic features. A novel hybrid clustering framework was designed based on Principal Component Analysis (PCA), Guided Self-Organizing Map (G-SOM), and Fuzzy-CMeans (FCM) to cluster the historical multi-feature space into probabilistic state classes. Finally a dynamic performance annotation mechanism was developed based on Maximum (Bayesian) Probability Rule (MPR) to quantify the performance of an individual sensor node and network. Based on the results from this framework, a "data quality knowledge map" was visualized to demonstrate the effectiveness of this framework.

Item Details

Item Type:Refereed Conference Paper
Keywords:maximum (Bayesian) probability rule (MPR), PCA, FCM, SOM, sensor network
Research Division:Engineering
Research Group:Geomatic engineering
Research Field:Photogrammetry and remote sensing
Objective Division:Environmental Management
Objective Group:Other environmental management
Objective Field:Other environmental management not elsewhere classified
UTAS Author:Das, A (Dr Aruneema Das)
UTAS Author:Aryal, J (Dr Jagannath Aryal)
ID Code:92518
Year Published:2014
Web of Science® Times Cited:2
Deposited By:Geography and Environmental Studies
Deposited On:2014-06-23
Last Modified:2017-10-24
Downloads:400 View Download Statistics

Repository Staff Only: item control page