Data mining methods for quality assurance in an environmental monitoring network

  • Authors:

  • Ioannis N. Athanasiadis;Andrea-Emilio Rizzoli;Daniel W. Beard

  • Affiliations:

  • Dalle Molle Institute for Artificial Intelligence, Lugano, Switzerland;Dalle Molle Institute for Artificial Intelligence, Lugano, Switzerland;Environmental Protection Department, Saudi Aramco, Dhahran, Saudi Arabia

  • Venue:
  • ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper presents a system architecture that employs data mining techniques for ensuring quality assurance in an environmental monitoring network. We investigate how data mining techniques can be incorporated in the quality assurance decision making process. As prior expert decisions are available, we demonstrate that expert knowledge can be effectively extracted and reused for reproducing human experts decisions on new data. The framework is demonstrated for the Saudi Aramco air quality monitoring network and yields trustworthy behavior on historical data. A variety of data-mining algorithms was evaluated, resulting to an average predictive accuracy of over 80%, while best models reached 90% of correct decisions.