Mining time series data via linguistic summaries of trends by using a modified Sugeno integral based aggregation

Linguistic summaries as descriptions of trends in time series data are proposed. We further extend our (cf. Kacprzyk, Wilbik and Zadrozny, 2006) previous works in which we put forward a new approach to the linguistic summarization of time series. In this paper we basically propose a modification of our previous work on the use of the Sugeno integral developed in 2006 by employing a modified fuzzy measure and its related modified Sugeno integral. This gives better results in particular in the case of some more sophisticated and extended types of summaries