Multivariate Trajectory Clustering for False Positive Reduction in Online Event Detection

Abstract

Online monitoring of multivariate water quality data is becoming a practical means of improving distribution network management and meeting water security goals. Changes in water quality are often due to changes in the hydraulic operations of the network. These operational changes create patterns of water quality change that are similar, but not exactly the same, from one instance to the next. Classification of multivariate change patterns through trajectory clustering is introduced in this paper to create a pattern library from historical water quality data and as an online process with the goal of reducing false positive water quality event detections. Prior to event declaration, a short sequence of the preceding multivariate data is compared against the pattern library to assess its similarity to a previously observed pattern. A fuzzy clustering algorithm is utilized to assign multivariate pattern memberships for water quality patterns associated with water quality events in both the offline and online modes of operation. The utility of trajectory clustering for multivariate pattern recognition in time-series data is demonstrated with two example applications. The first example uses observed water quality with simulated patterns and events. The pattern matching reduces the number of false positive event detections by 91% relative to the case of not using the pattern matching. The same false positive event reduction is achieved when both patterns and separate water quality events are added and 100% event detection is achieved. The second example uses observed water quality data from a metropolitan distribution system in the United States. The pattern matching approach developed in this paper is able to reduce the false positive event detections by 68%.