Back to Search
Start Over
A Weighted Deep Ensemble for Indian Sign Language Recognition.
- Source :
-
IETE Journal of Research . Feb2023, p1-8. 8p. 7 Illustrations, 3 Charts. - Publication Year :
- 2023
-
Abstract
- This work concentrates on developing an Indian sign language (ISL) recognition system using a forearm-worn wearable device to assist hearing-impaired persons. A novel ensemble of convolution neural networks (CNN) is proposed for robust ISL recognition using multi-sensor data. The accuracy for classification of 50 ISL signs improved from 92.5% obtained using a single CNN to 94.2% with 10 ensemble members created using the bagging approach and soft-voting for decision aggregation. Then, the ensemble of CNNs was optimized using weighted voting, where the weights were determined using a differential evolution algorithm. This further improved the classification accuracy to 96.6% with 10 ensemble members. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 03772063
- Database :
- Academic Search Index
- Journal :
- IETE Journal of Research
- Publication Type :
- Academic Journal
- Accession number :
- 161900727
- Full Text :
- https://doi.org/10.1080/03772063.2023.2175057