论文信息 - SumTime-Turbine: A Knowledge-Based System to Communicate Gas Turbine Time-Series Data

SumTime-Turbine: A Knowledge-Based System to Communicate Gas Turbine Time-Series Data

SumTime-Turbine produces textual summaries of archived time-series data from gas turbines. These summaries should help experts understand large data sets that cannot be visually presented in a single graphical display. SumTime-Turbine is based on pattern detection, knowledge-based temporal abstraction (KBTA), and natural language generation (NLG) technology. A prototype version of the system has been implemented and is currently being evaluated.

[1] Ehud Reiter,et al. Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[2] Yuval Shahar,et al. Knowledge-based spatiotemporal linear abstraction 2 Knowledge-Based Spatiotemporal Linear Abstraction , 1998 .

[3] Jim Hunter,et al. Segmenting Time Series for Weather Forecasting , 2003 .

[4] Robert Milne,et al. Model Based Aspects of the TIGER Gas Turbine Condition Monitoring System , 1997 .

[5] Martin Molina,et al. Knowledge-based spatiotemporal linear abstraction , 2005, Pattern Analysis and Applications.

[6] Ehud Reiter,et al. S UM T IME : Observations from KA for Weather Domain , 2001 .

[7] Richard Ellis,et al. Applications and Innovations in Intelligent Systems VII , 2000, Springer London.

[8] Robert Dale,et al. Building Natural Language Generation Systems: Figures , 2000 .

[9] Robert Milne,et al. TIGER with model based diagnosis: initial deployment , 2001, Knowl. Based Syst..

[10] Yuval Shahar,et al. Knowledge-based temporal abstraction in clinical domains , 1996, Artif. Intell. Medicine.

[11] Emiel Krahmer,et al. From data to speech: a general approach , 2001, Natural Language Engineering.