A fingerprint of a heterogeneous data set
| Autor: | Marco Prato, Matteo Spallanzani, Roberto Fontana, Gueorgui Mihaylov |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Statistics and Probability
Production line Bagged data Mixed-type data Mixture distributions Multivariate statistics Machine learning Computer science 02 engineering and technology Simple (abstract algebra) 020204 information systems 0202 electrical engineering electronic engineering information engineering Categorical variable business.industry Applied Mathematics Fingerprint (computing) Pattern recognition Computer Science Applications Data set Statistical classification 020201 artificial intelligence & image processing Artificial intelligence business Classifier (UML) |
| Zdroj: | Advances in Data Analysis and Classification, 16 (3) |
| ISSN: | 1862-5355 1862-5347 |
| Popis: | In this paper, we describe the fingerprint method, a technique to classify bags of mixed-type measurements. The method was designed to solve a real-world industrial problem: classifying industrial plants (individuals at a higher level of organisation) starting from the measurements collected from their production lines (individuals at a lower level of organisation). In this specific application, the categorical information attached to the numerical measurements induced simple mixture-like structures on the global multivariate distributions associated with different classes. The fingerprint method is designed to compare the mixture components of a given test bag with the corresponding mixture components associated with the different classes, identifying the most similar generating distribution. When compared to other classification algorithms applied to several synthetic data sets and the original industrial data set, the proposed classifier showed remarkable improvements in performance. Advances in Data Analysis and Classification, 16 (3) ISSN:1862-5355 ISSN:1862-5347 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink