Efficiently mining large volumes of time series data is amongst the most challenging problems that are fundamental in many fields such as industrial process monitoring, medical data analysis and business forecasting. This paper discusses a high-performance neural network for mining large time series data set and some practical issues on time series data mining. Examples of how this technology is used to search the engine data within a major UK eScience Grid project (DAME) for supporting the maintenance of Rolls-Royce aero-engine are presented.
|Title of host publication
|IEEE International Conference on Industrial Technology (ICIT) 2005 (14-17 December 2005, City University of Hong Kong)
|Place of Publication
|Number of pages
|Published - Dec 2005