Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Ingeniería y Universidad
Print version ISSN 0123-2126
Abstract
VILLATE-GIL, Andrea; RINCON-ARANDIA, David Eduardo and MELGAREJO-REY, Miguel Alberto. Applying Differential Evolution to Tune Fuzzy Classifiers Intended for Sign-Language Recognition. Ing. Univ. [online]. 2012, vol.16, n.2, pp.397-413. ISSN 0123-2126.
This paper presents a methodological approach for tuning fuzzy classifiers intended to recognize the Australian sign-language considering two particular contexts. We describe the fuzzy classification architecture and the tuning process based on differential evolution. The validation results show that it is possible to find a fuzzy classifier whose classification error is around 13.0% over a group of words taken from several experts for each interaction context. This characteristic is relevant as previous works only considered recognizing words provided only by one interpreter.
Keywords : Auslan; differential evolution; fuzzy classification; pattern recognition; sign language; optimization; TSK Fuzzy Systems.