Linguistic Summaries of Time Series: On Some Additional Data Independent Quality Criteria

摘要: We further extend our approach on the linguistic summarization of time series (cf. Kacprzyk, Wilbik and Zadrozny) in which an based a calculus linguistically quantified propositions is employed, essence problem equated with quantifier driven aggregation partial scores (trends). Basically, we present here some reformulation extension works mainly by including more complex evaluation summaries obtained. In addition to basic criterion degree truth (validity), also use as additional criteria imprecision, specificity, fuzziness focus. However, for simplicity tractability, first shot degrees (validity) focus, usually reduce space possible considerable extent, then - much smaller set obtained remaining three specificity making final choice appropriate summaries. show application absolute performance type analysis daily quotations investment fund.