The paper concerns mining data lacking the uniform structure. The
data are collected from a riumber of objects during repeated measurenients, all of which are tagged by a corresponding time. No attribute-valued machine learning algorithm can be applied directly on such data since the number of measurements is not fixed but it varies. The available data háve to be transformed and preprocessed in such a way that a uniform type of Information is obtained about all the considered objects. This can be achieved, e.g., by aggregation. But this process can introduce anachronistic variables, i.e., variables containing Information which cannot be available at the moment when a prediction is needed. The paper suggests and tests a method how to preprocess the considered type of data without falling into a trap of introducing anachronistic attributes. The method is illustrated on a čase study baaed on STULONG data.
This paper presents an analysis of trends and causes of changes of selected hydroclimatic variables influencing the runoff regime in the upper Hron River basin (Slovakia). Different methods for identifying trends in data series are evaluated and include: simple mass curve analysis, linear regression, frequency analysis of flood events, use of the Indicators of Hydrological Alteration software, and the Mann-Kendall test. Analyses are performed for data from two periods (1931-2010 and 1961-2010). The changes in runoff are significant, especially in terms of lower QMax and 75 percentile values. This fact is also confirmed by the lower frequency and extremity of flood events. The 1980s are considered a turning point in the development of all hydroclimatic variables. The Mann-Kendall test shows a significant decrease in runoff in the winter period. The main causes of runoff decline are: the considerable increase in air temperature, the decrease in snow cover depth and changes in seasonal distribution of precipitation amounts., Andrea Blahušiaková, Milada Matoušková., and Obsahuje bibliografické odkazy