Mining Patterns and Changes of Wave Shapes for Efficiently Querying Periodic Data Streams

许多数据流周期性地变化，例如重要的生理参数（例如，心率、动脉压和呼吸阻抗）和季节性环境数据流（例如，河水的温度和浊度）。然而，周期性数据流的查询面临着巨大的挑战，包括关键信号通常被隐藏在海量数据中的问题，而由于移位、缩放和噪声，相似波形之间的关键变化难以识别。该项目将开发新的挖掘算法，通过分割周期性波形，发现形状模式和形状变化，并汇总原始数据流，以便汇总的数据可以直接回答各种用户查询，以提高效率，从而解决这些挑战。

Many data streams change periodically, such as vital physiological parameters (for example, heart rate, arterial pressure and respiratory impedance) and seasonal environmental data streams (for example, temperature and turbidity of river water). However, the querying of periodic data streams faces great challenges, including the issue of critical signals being generally buried within massive data while critical changes between similar wave shapes are difficult to recognise due to shifting, scaling and noise. This project will develop new mining algorithms to resolve these challenges by segmenting periodic wave shapes, discovering shape patterns and shape changes, and summarising raw data streams so that the summarised data can directly answer various user queries for efficiency.