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...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: González Rubio, Tahimy, Salgado Castillo, Antonio
Formato: Objeto de conferencia
Lenguaje:Español
Publicado: 2012
Materias:
Ciencias Informáticas
Real time
Signal processing
SVM
ANN
Pulse Waves
Diabetic Neuropathy
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23819
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
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

Ejemplares similares