Abstract

With the advent of automatic sensors for detection and data collection (for example, SCADA systems), it is now possible to acquire a large number of time series of critical data. In urban water and sewer systems, monitoring stations can collect data on water quantity and quality (for example, dissolved oxygen, electric conductivity, pH and turbidity, among others). The motivation for such data collection usually is to analyze if the systems are working properly. New analytical techniques are needed in order to efficiently analyze such large quantities of data and to answer questions of forensic nature (for example, how well the systems are working and whether any of the components are faulty). An

automatic inference system consisting of feature extraction, clustering, and classification steps is developed to answer categorical questions using the large amount of data.

This paper is only available in PDF Format:

  View full text PDF