Catálogo de publicaciones - libros

Subgroup discovery aims at finding interesting subsets of a classified example set that deviates from the overall distribution. The search is guided by a so-called utility function, trading the size of subsets (coverage) against their statistical unusualness. By choosing the utility function accordingly, subgroup discovery is well suited to find interesting rules with much smaller coverage and bias than possible with standard classifier induction algorithms. Smaller subsets can be considered local patterns, but this work uses yet another definition: According to this definition global patterns consist of all patterns reflecting the prior knowledge available to a learner, including all previously found patterns. All further unexpected regularities in the data are referred to as local patterns. To address local pattern mining in this scenario, an extension of subgroup discovery by the knowledge-based sampling approach to iterative model refinement is presented. It is a general, cheap way of incorporating prior probabilistic knowledge in arbitrary form into Data Mining algorithms addressing supervised learning tasks.

We elaborate on the subject of pattern change as a result of population evolution. We provide an overview of literature threads relevant to this subject, where the focus is on related works in the area of pattern adaptation rather than on modelling or understanding change. We then describe our temporal model for patterns as evolving objects and propose criteria to capture the interestingness of pattern change. We also present heuristics that trace interesting changes.

In this paper, we give an interpretation of our undirected exception rule discovery as local pattern detection and introduce some of our endeavors. Our undirected exception rule discovery outputs a set of rule pairs, each of which represents a pair of strong rule and its exception rule. A local pattern is defined as a pattern which deviates from a global model, and can be considered to correspond to our exception rule if the global model corresponds to our strong rule. Several attempts for undirected exception rule discovery are introduced in the context of local pattern detection. Our results mainly concern interestingness measure, algorithmic issues, noise modeling, and performance evaluation.

Local and more and more global musical structure is analyzed from audio time series by time-series-event analysis with the aim of automatic sheet music production and comparison of singers. Note events are determined and classified based on local spectra, and rules of bar events are identified based on accentuation events related to local energy. In order to compare the performances of different singers global summary measures are defined characterizing the overall performance.