Loading...
Please wait, while we are loading the content...
Similar Documents
Clasificación de Gestos de la Lengua de Señas Colombiana a partir del Análisis de Señales Electromiográficas utilizando Redes Neuronales Artificiales
| Content Provider | Semantic Scholar |
|---|---|
| Author | Galvis-Serrano, Elvis H. Sánchez-Galvis, Iván Flórez, Natalia Zabala-Vargas, Sergio Andrés |
| Copyright Year | 2019 |
| Abstract | espanolEl objetivo del presente trabajo es clasificar los 27 gestos del alfabeto de senas colombiano, mediante un clasificador de redes neuronales artificiales a partir de senales electromiograficas. El clasificador fue disenado en cuatro fases: 1) Adquisicion de senales electromiograficas provenientes de los ocho sensores de la manilla Myo Armband, 2) Extraccion de caracteristicas de las senales electromiograficas empleando la transformada Wavelet de Paquetes, 3) Entrenamiento de la red neuronal y 4) Validacion del metodo de clasificacion utilizando la tecnica de validacion cruzada. Para el presente estudio se adquirieron registros de senales electromiograficas de 13 sujetos con discapacidad auditiva. El clasificador presento un porcentaje de precision promedio de 88,4%, muy similar a otros metodos de clasificacion presentados en la literatura. El metodo de clasificacion puede ser escalado para clasificar, adicional a los 27 gestos, el vocabulario de la lengua de senas colombiana. EnglishThe objective of this article is to classify the 27 gestures of the Colombian sign alphabet, by means of a classifier of artificial neural networks based on electromyographic signals. The classifier was designed in four phases: Acquisition of electromyographic signals from the eight sensors of the Myo Armband handle, extraction of characteristics of the electromyographic signals using the wavelet transform of packages, training of the neural network and validation of the classification method using the cross-validation technique. For the present study, records of electromyographic signals from 13 subjects with hearing impairment were acquired. The classifier presented an average accuracy percentage of 88.4%, very similar to other classification methods presented in the literature. The classification method can be scaled to classify, in addition to the 27 gestures, the vocabulary of the Colombian sign language. |
| Starting Page | 171 |
| Ending Page | 180 |
| Page Count | 10 |
| File Format | PDF HTM / HTML |
| DOI | 10.4067/s0718-07642019000200171 |
| Volume Number | 30 |
| Alternate Webpage(s) | https://repository.usta.edu.co/bitstream/handle/11634/13021/2018elvisgalvis.pdf?isAllowed=y&sequence=1 |
| Alternate Webpage(s) | https://doi.org/10.4067/s0718-07642019000200171 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
