ABSTRACT
Water quality evaluation is important in providing a reliable supply of potable water. Empirical evidence shows that water quality parameters, such as dissolved oxygen (DO), NH3-N, total phosphorus (TP), and total nitrogen (TN), are sensitive indicators of contaminants. Multisensor data fusion is a technology that enables combining information from several sources to form a unified picture. It is an important tool for improving the performance of a monitoring system when various sensors are available. Dempster-Shafer (DS) evidence theory and Bayesian methods are commonly used to handle uncertainty. DS evidence theory can be regarded as an extension of classical probabilistic reasoning, which makes inferences from incomplete and uncertain data provided by different independent sources. The chapter presents a novel multisensor data fusion approach for water quality evaluation using DS evidence theory. It proposes a method of calculating mass function based on water quality parameters and a reliability discounting to reflect the sensor node's reliability.
