Assessing and Improving Sensors Data Quality in Streaming Context

An environmental monitoring process consists of a regular collection and analysis of sensors data streams. It aims to infer new knowledge about the environment, enabling the explorer to supervise the network and to take right decisions. Different data mining techniques are then applied to the collected data in order to infer aggregated statistics useful for anomalies detection and forecasting. The obtained results are closely dependent on the collected data quality. In fact, the data are often dirty, they contain noisy, erroneous and missing values. Poor data quality leads to defective and faulty results. One solution to overcome this problem will be presented in this paper. It consists of evaluating and improving the data quality, to be able to obtain reliable results. In this paper, we first introduce the data quality concept. Then, we discuss the existing related research studies. Finally, we propose a complete sensors data quality management system.