Background: Pulse transit time has been demonstrated as one of the potential parameters for a cuffless blood pressure measurement. The accuracy of this method depends on the initial calibration that is obtained by several measurements. The aim of this study was to employ artificial neural network in order to estimate the blood pressure based on PTT. PTT is defined as the time delay between the R-wave of the ECG and the peak of the pulse wave in the finger. To train the ANN for modeling the blood pressure, this study used a database containing 65 subjects. For each subject, BP was taken several times in different condition. The trained ANN was capable of establishing a function between the PTT and the BP as an input and a response, respectively. The results of estimating BP were compared with the results of sphygmomanometer method and the error rate was calculated. The absolute error and error percentage in systolic blood pressure between cuff method and the present method were 5.41±2.63 mmHg, 4.09±1.59% and for diastolic blood pressure were 7.01±2.52 mmHg, 6.88±2.43%. The results indicated that the BP measurement by cuff method and BP predicted with trained ANN differ by only less than 10%. It is obvious that the neural network prediction fit properly to the cuff results. The results of proposed method were closely in agreement with the results of the sphygmomanometer cuff. So the present method could be applied as an effective tool for the blood pressure estimation.
Dialysis hypotension is one of the most prevalence symptoms of dialysis and occurs in 40% of treatment sessions. Detection and prediction of hypotension is important for the well-being of the patient and for optimizing treatment. The aim of this study was to construct optical system to monitor blood pressure (BP) continuously and without cu® in hemodialysis based on pulse transit time (PTT) method. To measure the BP changes, dual-channel optical system were developed. In this study, individuals were classi¯ed into two groups of normal and hemodialysis. In both groups, BP and consequently PTT were earned three times in di®erent positions. After the initial calibration, the regression equation was drawn for each subject. In normal group, each subject was placed in the supine position and BP was measured both by designed system and sphygmomanometer cu®. During BP measurements, in addition to BP, blood pressure decline was also monitored by optical system. For hemodialysis group, the same measurement setup was adopted. In both groups, the error between cu® method and PTT was calculated. Correlation coe±cients for BP cuff vs BP PTT were calculated and Bland-Altman plot was performed for the normal and hemodialysis groups. In this study 16 subjects participated. The results for normal group showed that maximum di®erence between cu® method and the present method was 14 mmHg and for dialysis group was 16 mmHg. Bland-Altman plot in normal group revealed limits of agreement from À13.98 to 13.18 mmHg. Considering hemodialysis group, limits of agreement were from * Corresponding author. This is an Open Access article published by World Scienti¯c Publishing Company. It is distributed under the terms of the Creative Commons Attribution 4.0 (CC-BY) License. Further distribution of this work is permitted, provided the original work is properly cited. À15.94 to 13.88 mmHg. The correlation coe±cient was 0.74 for normal group and was 0.72 for hemodialysis group. The proposed system can monitor BP continuously and diagnose sudden hypotension. So it can be recommended as a useful method to indicate hypotension and can be used for dialysis unit.
In this paper, a control approach for tracking control of robot manipulators is developed which not only parametric uncertainties but also unstructured uncertainties such as friction, disturbances and un-modeled dynamics are considered. Disregarding the unstructured uncertainties may cause an unstable closed loop control system. A robust controller is designed based on Lyapunov method, using robot physical properties and known bounds of uncertainties. It is then proven that the closed loop system has global exponential stability. The bounds of unstructured uncertainties are estimated by adding an adaptive controller to the robust controller. It is verified that the proposed control system has global asymptotic stability. A case of study is a three links elbow robot where the analytical works and simulation results show a good performance of the control system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.