Bibliographic citations
Campos, L., (2020). Clasificación de diferentes posiciones de la mano a partir del procesamiento de las señales electromiográficas superficiales del antebrazo utilizando diferentes algoritmos de Machine Learning [Tesis, Universidad Nacional de Ingeniería]. http://hdl.handle.net/20.500.14076/21747
Campos, L., Clasificación de diferentes posiciones de la mano a partir del procesamiento de las señales electromiográficas superficiales del antebrazo utilizando diferentes algoritmos de Machine Learning [Tesis]. PE: Universidad Nacional de Ingeniería; 2020. http://hdl.handle.net/20.500.14076/21747
@misc{renati/1750288,
title = "Clasificación de diferentes posiciones de la mano a partir del procesamiento de las señales electromiográficas superficiales del antebrazo utilizando diferentes algoritmos de Machine Learning",
author = "Campos Quispe, Luis Fernando",
publisher = "Universidad Nacional de Ingeniería",
year = "2020"
}
The objective of this thesis is to classify different positions of the hand from the processing of the superficial electromyographic (sEMG) signals of the forearm using different machine learning algorithms. In a first stage of the processing of the sEMG signals, a data vector was obtained containing all the sEMG information from nineteen different positions of the hand. This information vector was independently modified by two dimensionality reduction algorithms known as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) to compare with which of these two algorithms greater precision was achieved in the subsequent classification stage. After dimensionality reduction with the aforementioned algorithms, the compacted information vector was entered independently through three machine learning supervised classification algorithms to compare the results and find the algorithm with the best performance. The classification algorithms used were: an Artificial Neural Network (ANN), a Vector Support Machine (SVM) and the K-Nearest Neighbors (KNN). The algorithms with which the best performance for dimensionality reduction and classification were PCA and ANN, respectively. The final result of the investigation concludes that it is possible to classify with a precision superior to 95% nineteen different positions of the hand from the processing of the sEMG signals of the forearm.
This item is licensed under a Creative Commons License