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.
This paper presents an estimation of missed samples recovery of Synthetic electrocardiography (ECG) signals by an ANFIS (Adaptive neuro-fuzzy inference system) method after designing the ANFIS model using FCM (Fuzzy C Means) clustering method. In MATLAB’s standard library for ANFIS, only least-square-estimation and the back-propagation algorithms are used for tuning membership functions and generation of fis (fuzzy inference system) file, but at current work, we have used the FCM method that shows better results. Root mean square error (difference of the reference input and the generated data by ANFIS) for the three synthetic data cases are: a. Train data: RMSE = 1.7112e-5 b. Test data: RMSE = 5.184e-3 c. All data: RMSE = 2.2663e-34
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.