Design and Presenting of a Novel Algorithm Using Anfis for New Generation of Cardiac Pacemakers

Abstract

This paper presents a new intelligent control algorithm using Anfis (Adaptive neuro fuzzy inference system) for new generation of Cardiac Pacemakers. Anfis uses both merits of Fuzzy and Neural networks (Learning and speed). Based on various states of body (rest, walking and exercising) and preprogramed states of patient (Sex, age, blood pressure) heart rate and amplitude of exciting pulses will be changed. A feedback from output ECG signal fed back and compared in Anfis controller. Anfis compared with other fuzzy control algorithms provides better control scheme for estimation and generation of pacing pulse parameters including rate and amplitude. Accelerometer sensors and HRV and GSR are used for stabilization of ECG signal during the three body states [1]. Old designs of pacemakers cannot solve problems but Fuzzy can do the job very fast and accurately. Anfis method designed externally regarding patient conditions and normal ECG signals data captured from a known database (based on age and sex of patient) then calculated in MATLAB (Simulink) and programmed directly or wirelessly by ultrasound signals (a novel proposed method). Previous researches [4-19-20] are based on fuzzy PID and fuzzy logic controller in patients with cardiovascular diseases. Anfis controller offers good adaptation of the heart rate and other ECG parameters to the physiological needs of patient.

Interval Type 2 Adaptive Neuro-Fuzzy Inference System-Based Artificial Pacemaker Design and Stability Analysis

“…Subtractive clustering 3. Fuzzy C Means (FCM Methods one and two are investigated in reference [9]. FCM method was used and compared with other methods in this paper.…”

“…Figure. 9 The ANFIS and the old PID controller method simulation After the rule base is specified, the ANFIS adjusts only the MFs of the antecedents and the consequent parameters. The BP algorithm can be used to train both the premise and consequent parameters.…”

“…The main idea was to design a controller for a system that is structurally difficult to model because of nonlinearities and modeling difficulties [6,7]. This method analyzed and investigated in [9].…”

Design and Stability Analysis of an Adaptive Neuro-Fuzzy Inference System (ANFIS) Based Pacemaker controller in MATLAB Simulink

“…Offline learning methods are: 1.Grid Partitioning: 2.Subtractive clustering: 3.Fuzzy C Means (FCM): Methods one and two are investigated in our earlier work [9]. FCM method has been used in this paper and compared with other methods.…”

Missing Samples Estimation of Synthetic ECG Signals by FCM-based Adaptive Neuro-Fuzzy Inference System (FCMANFIS)

“…Instead o ine data from healthy people will be used to train ANFIS. Methods one and two are investigated in our earlier work [10]. FCM method was used and compared with other methods in this paper.…”