Application of Hammerstein-Wiener Recurrent Neural Network to Accelerate Time-Series Skyline Queries

Skyline queries are popular among researchers because of their capacity to assist decision-makers in the context of multiple criteria. However, existing studies were aimed at single objects or events. Time series, such as observing the long-term trends of stocks to select for highest profit and lowest risk, are rarely discussed. This study fills this gap. Conventional skyline queries directed at single objects or events are already time-consuming. All conventional algorithms compare data items in pairs, greatly increasing time complexity. Given the additional complexity of time series problems, we propose a method based on recurrent neural networks. To the best of our knowledge, this study is the first to propose a method for time-series skyline queries, which represents a significant contribution. Experiment results demonstrate the validity of the proposed method.