Publication: Detecting Features from Confusion Matrices using Generalized Formal Concept Analysis
Loading...
Identifiers
Publication date
2010
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Abstract
We claim that the confusion matrices of multiclass problems can be analyzed by means of a generalization of Formal Concept Analysis to obtain symbolic information about the feature sets of the underlying classification task.We prove our claims by analyzing the confusion matrices of human speech perception experiments and comparing our results to those elicited by experts.
Description
Keywords
Formal Concept Analysis, confusion matrix, contingency matrix, phonetics, biclustering
Bibliographic citation
Hybrid Artificial Intelligence Systems, 5th International Conference, HAIS 2010, San Sebastián, Spain, June 23-25, 2010. Proceedings, Part II. Springer, 2010, pp 375-382.