DocumentCode :
2393295
Title :
Application of local linear neuro-fuzzy model in prediction of mean arterial blood pressure time series
Author :
Janghorbani, Amin ; Arasteh, Abdollah ; Moradi, Mohammad Hassan
Author_Institution :
Amirkabir Univ. of Technol. Tehran, Tehran, Iran
fYear :
2010
fDate :
3-4 Nov. 2010
Firstpage :
1
Lastpage :
4
Abstract :
Predicting the future behavior of human´s biosignals can help clinicians to prevent occurrence of physiological disorders such as hypotension, hypertension, epilepsy, etc. In addition this prediction helps clinicians to buy some time in order to select a more effective treatment for physiological disorders without exposing the patient to additional risks of delay in receiving treatment. In this paper a local linear neuro-fuzzy model was applied to predict mean arterial pressure time series. In order to evaluate the accuracy of prediction, Normalized Mean Square Error (NMSE) was chosen as an error index. 10 mean arterial pressure signals (2.5 hours each) from 10 patients were selected for training and prediction. Mean of NMSE for these signals was 0.023 in train and 0.0514 in test.
Keywords :
bioelectric phenomena; blood pressure measurement; blood vessels; fuzzy neural nets; mean square error methods; medical disorders; medical signal processing; neurophysiology; physiological models; biosignals; epilepsy; hypertension; hypotension; local linear neurofuzzy model; mean arterial blood pressure time series; mean arterial pressure signals; normalized mean square error method; physiological disorders; Analytical models; Electromagnets; Hypercubes; Local Linear Model; Local Linear Model Tree (LoLiMoT) algorithm; Neuro-Fuzzy; Prediction; Time Series;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Engineering (ICBME), 2010 17th Iranian Conference of
Conference_Location :
Isfahan
Print_ISBN :
978-1-4244-7483-7
Type :
conf
DOI :
10.1109/ICBME.2010.5704926
Filename :
5704926
Link To Document :
بازگشت