No abstract

In this paper is described the design and implementation of a wireless atrial fibrillation monitoring system, for realtime remote patient monitoring in a limited area, using wireless sensor networks (WSN). The proposed system consists of a lightweight and low power wireless ECG acquisition and processing device, connected to a central monitoring station through WSN. The device is able to detect the paroxysmal atrial fibrillation episodes and transmits alerts to the central monitoring station. The system can be used for long-time continuous monitoring of patients suspected to have atrial fibrillation, as part of a diagnostic procedure, or recovery from an acute or surgical event. In order to detect the atrial fibrillation episodes we used a simple method based on RR intervals, extracted from ECG signal. We evaluated the performance of the method on MIT-BIH Atrial Fibrilation Database from Physionet. The central monitoring station runs a patient monitor application that receives the real time heart rate and atrial fibrillation alerts from WSN. A user-friendly Graphical User Interface was developed for the patient monitor application to display the heart rate and alerts coming from the monitored patient. A prototype of the system has been developed, implemented and tested.

No abstract

No abstract

A learning algorithm based on a gradient technique is introduced for the algebraic fuzzy neural network with fuzzy weights. The fuzzy weights can be triangular fuzzy numbers (usually nonsymmetric), or trapezoidal fuzzy numbers. The network is able to map a vector of triangular (trapezoidal) fuzzy numbers into any other vector of triangular (trapezoidal) fizzy numbers.