Emerging and Vanishing Association Pattern Mining in Hydroclimatic Datasets

Abstract

Emerging and vanishing association patterns can be defined as association patterns whose frequencies (supports) get stronger and weaker over time, respectively. Discovering these patterns is important for several application domains such as financial and communication services, public health, and hydroclimatic studies. Classical association pattern mining algorithms do not consider how the strengths of association patterns change over time. An association pattern can be defined as an emerging or vanishing pattern when its support measure changes over time. In this paper, we focus on discovery of time evolving association patterns (i.e., emerging and vanishing association patterns) from datasets. To discover such patterns, a novel algorithm, named as Emerging and Vanishing Association Pattern Miner (EVAPMiner) algorithm, was proposed. The proposed algorithm was evaluated using hydroclimatic dataset of Turkey. The analyses showed that the proposed algorithm successfully detects emerging and vanishing association patterns in hydroclimatic datasets.