Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy
Diabetic neuropathy is a disease that affects a large proportion of the world population, so that its prevention and early detection is of vital importance at the present time. In this paper we evaluate an ANN and SVM designed using MatLab 7.9.0.529 for the classification and prediction of patients...
Guardado en:
Autores principales: | , |
---|---|
Formato: | Objeto de conferencia |
Lenguaje: | Español |
Publicado: |
2012
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/23819 |
Aporte de: |
id |
I19-R120-10915-23819 |
---|---|
record_format |
dspace |
institution |
Universidad Nacional de La Plata |
institution_str |
I-19 |
repository_str |
R-120 |
collection |
SEDICI (UNLP) |
language |
Español |
topic |
Ciencias Informáticas Real time Signal processing SVM ANN Pulse Waves Diabetic Neuropathy |
spellingShingle |
Ciencias Informáticas Real time Signal processing SVM ANN Pulse Waves Diabetic Neuropathy González Rubio, Tahimy Salgado Castillo, Antonio Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy |
topic_facet |
Ciencias Informáticas Real time Signal processing SVM ANN Pulse Waves Diabetic Neuropathy |
description |
Diabetic neuropathy is a disease that affects a large proportion of the world population, so that its prevention and early detection is of vital importance at the present time. In this paper we evaluate an ANN and SVM designed using MatLab 7.9.0.529 for the classification and prediction of patients with diabetic neuropathy, using Pulse Waves Sequences of Blood Volume. Efficiency was evaluated taking into account the algorithms and training time as well as effectiveness in classification and prediction. Considering 40 cases in the process of learning and 18 in the validation, the best classification results were obtained with the ANN for an 88.88% effective with the Gradient descent learning algorithm with adaptive learning rate, and the SVM was obtained 72.22% success rate using the Quadratic programming algorithm. In predicting both methods were 100% effective. |
format |
Objeto de conferencia Objeto de conferencia |
author |
González Rubio, Tahimy Salgado Castillo, Antonio |
author_facet |
González Rubio, Tahimy Salgado Castillo, Antonio |
author_sort |
González Rubio, Tahimy |
title |
Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy |
title_short |
Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy |
title_full |
Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy |
title_fullStr |
Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy |
title_full_unstemmed |
Evaluation of ANN and SVM for the classification and prediction of patients with diabetic neuropathy |
title_sort |
evaluation of ann and svm for the classification and prediction of patients with diabetic neuropathy |
publishDate |
2012 |
url |
http://sedici.unlp.edu.ar/handle/10915/23819 |
work_keys_str_mv |
AT gonzalezrubiotahimy evaluationofannandsvmfortheclassificationandpredictionofpatientswithdiabeticneuropathy AT salgadocastilloantonio evaluationofannandsvmfortheclassificationandpredictionofpatientswithdiabeticneuropathy |
bdutipo_str |
Repositorios |
_version_ |
1764820466275450881 |