Name
Abstract | ||
|---|---|---|
We consider a classification process, that the representation precision of new examples is interactively increased. We use an attribute value ontology (AVO) to represent examples at different levels of abstraction (levels of precision). This precision can be improved by conducting diagnostic tests. The selection of these diagnostic tests is generally a non-trivial task. We consider the hypothesis-driven interactive classification, where a decision maker chooses diagnostic tests that approve or reject her hypothesis (the classification of a new example to a one or more selected decision classes). Specifically, we present two approaches to the selection of diagnostic tests: the use of the measure of information gain and the analysis of the classification results for these diagnostic tests using an ontological Bayes classifier (OBC). |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1007/978-3-319-02309-0_7 | MAN-MACHINE INTERACTIONS 3 |
Keywords | Field | DocType |
levels of abstraction,interactive classifier,naive Bayes | Ontology,Data mining,Abstraction,Naive Bayes classifier,Diagnostic test,Information gain,Artificial intelligence,Machine learning,Mathematics,Bayes classifier,Decision maker | Conference |
Volume | ISSN | Citations |
242 | 1867-5662 | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tomasz Łukaszewski | 1 | 51 | 6.55 |
| Jedrzej Potoniec | 2 | 21 | 7.79 |
| Szymon Wilk | 3 | 461 | 40.94 |