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

doi:10.21203/rs.3.rs-1102921/v1

Download PDF

Research

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

https://doi.org/10.21203/rs.3.rs-1102921/v1

This work is licensed under a CC BY 4.0 License

Version 1

posted

You are reading this older preprint version

Read the latest preprint version →

This paper presents 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 FCM method that shows better result.

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-3

Health Economics & Outcomes Research

ANFIS

ECG

FCM

Estimation

Adaptive

Missing samples recovery

FCMANFIS

Synthetic

Missing samples recovery [1] is a known problem that was addressed in some contexts such as:

-audio restoration [2, 3],

-image completion [4, 5],

-data recovery in electricity distribution systems [6],

-biomedical applications [7,8].

The rest of this paper is structured as follows. In Section 3 we propose a model for the ECG signal generation and formulate the problem of missing samples recovery in this context. In Section 4 we present the proposed estimation procedure for the recovery of the missing samples. Comparative simulation results on synthetic ECG data [11] are presented in Section 4.2.

ANFIS is a fuzzy logic method for function approximation and control of various engineering fields such as biomedical engineering systems; AC and DC motor control and power plant control and even social engineering problems [12,13].

Our proposed estimation scheme presents generation of missed samples recovery of ECG signals by a fuzzy method called ANFIS (Adaptive neuro-fuzzy inference system). In this study FCM used as a method to tune fuzzy system parameters (membership functions).

ANN has strong learning capabilities. Fuzzy logic has ability of interpretability. The true scheme of the two method is a hybrid neural/fuzzy system, which uses the merits of both systems, ANFIS. The general ANFIS structure is presented in this section. The ANFIS model with one input and one output variable and five layers is shown at figures 1a,1b.

The functions of the various layers are given in the form of an algorithm as described in [9]. The structure contains the same components as fis (fuzzy inference system), except for the NN block. The ANFIS structure is adjusted by least-square-estimation and back-propagation algorithms.

For a given data set, different ANFIS models can be constructed using three different identification methods such as grid partitioning, subtractive clustering method and fuzzy C-means clustering [9]. In the present paper, the FCM method is used to find the premise

membership functions for the ANFIS model.

Considering that the training data will be given from patient ECG signal, the online method of receiving the data will not be useful. Instead offline data from healthy people will be used to train ANFIS. Offline training methods are:

I. Grid Partitioning:

II. Subtractive clustering:

III. Fuzzy C -Means (FCM):

Methods one and two are investigated in our earlier work [10]. FCM method was used and compared with other methods in this paper. FCM convergence speed is very faster than other two previous methods.

FCM was introduced by Bezdek [14] is a clustering method in which each data point belongs to two or more clusters. FCM is an algorithm, that wants to find cluster centers based on minimization of an objective function. This function is the summation of squares distances between each data points

and the cluster center.

3.1 ANFIS controller design by FCM method and comparison with other methods

Because FCM method is not available in MATLAB toolboxes, we have used a script developed by Dr. Kalami[1] to realize FCM. As before Input and output data pairs used as train and test data for generating the ANFSI model (fis) to be used in generating the estimated data.

The generated fis file is used in a MATLAB script to generate the missed signal ECG data with FCM method. FCM method has been simulated and input parameters and output results are shown at figures 2-7.

The ECG data is generated by a script taken from Quiroz and et al. work [11]. The main .m file has two parts. First part is used to generate 12 lead ideal noise-free ECG signals. At this noiseless state, we can obtain RR intervals with a simple algorithm for recognition of the signal maximums. For second state i.e. noisy ECG signal, we should use complex algorithms. The latter state also consists of 12 leads.

4.1 ANFIS learning methods:

The training data is collected from artificial 12 lead ECG signals (50 percent of data) and fuzzy ‘fis’ file is used to simulate the remained 50 percent to test the generated ECG data by ANFIS.

The ANFIS method used at this article is used for generation of the missed ECG signal offline but it can be used in applications that needs real-time and online estimation of missed signal.

The offline methods that investigated are:

-Grid Partitioning

-Subtractive Clustering

-FCM

-GA

And the online methods that can be investigated later are:

- CANFIS (Co-Active ANFIS)

-DENFIS (Dynamic Evolving Neural Fuzzy Inference System)

4.2 Design of FCM based ANFIS:

With ANFIS, we can estimate any missed signal from 12 lead ECG signals with a good accuracy.

First the following 12 lead ECG are generated by the MATLAB script [11]:

lead_I, lead_II, lead_III, lead_aVL, lead_aVL, lead_aVL, lead_V1, lead_V2, lead_V3, lead_V4, lead_V5, lead_V6

The V3 signal omitted from the data. Then by FCM method for ANFIS with following parameters as input the lost signal (V3) has been reconstructed:

Number of clusters: 10

Maximum repetition rate: 100

Minimum improvement error: 1e-5

Maximum no. of epocs: 100

Error Goal: 0

Initial Step Size:0.01

Step Size Decrease Rate: 0.9

Step Size Increase Rate: 1.1

The train and test signals and ALL data is shown at figures 5,6 and 7.

Rms error for the three cases are:

a. Train data, RMSE = 1.7112e-5

b. Test data, RMSE = 5.184e-3

c. All data (train and test), RMSE = 2.2663e-3

In this section we test and evaluate the performance of the proposed fuzzy method on synthetic ECG data. Test signals were generated synthetically by a MATLAB script from [15], consisting of 12 ECG signals for twelve ECG leads. The V3 ECG test signals were zeroed in 50 percent position of data so as to simulate lost samples, where the size of the lost sample interval was 50 percent of consecutive samples. Then the generated data is fed to another script that uses a fis file generated previously that its output is reconstructed (lost) ECG signal i.e. the V3 signal.

In the context of missing samples recovery of ECG signals, we proposed a fuzzy approximation model (ANFIS) to generate the lost signal among input ECG stream data which was empirically shown to be more suitable due to its fuzzy and Neural characteristics. Additionally, we proposed an appropriate estimation procedure according to the ANFIS model, which is comprised of two phases, model parameters estimation by FCM clustering, followed by the missing samples estimation and generation based on the ANFIS model. In comparison to previously published works, our model and estimation procedure yield more accurate results and better recovered ECG signals.

Also this study shows the capability of AI methods for modelling biomedical engineering problems containing ECG signals based on input output data, which were published in literature, for this purpose, the FCM-ANFIS method was developed for modelling and function approximation.

The next step will be to use the proposed method for real ECG data instead of synthetic data.

ANFIS: Adaptive Neuro-Fuzzy Inference System

FCM: Fuzzy C Means

RMSE: Root Mean Squared error

ECG: Electrocardiogram

GA: Genetic Algorithm

CONSENT FOR PUBLICATION

No applicable.

Availability of data and materials

The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.

Competing interests

The authors declare that they have no competing interests.

Funding

No applicable.

Authors’ contributions

AD developed and implemented the whole concepts of the algorithm presented within this manuscript, NJ provided refinements and performed data acquisition and generation as well as further supplemental programming, FN and KM provided further technical knowledge and support. All authors read and approved the final manuscript.

ACKNOWLEDGEMENTS

The authors would like to thank the anonymous referees for providing valuable suggestions which helped clarify the exposition of the material. Furthermore, the authors would like to thank Dr. Kalami for FCM MATLAB code.

AUTHORS' INFORMATION

Asghar Dabiri Aghdam is a PhD student at the Medical Sciences and

Technologies Faculty department of Biomedical Engineering

Islamic Azad University, Science and Research Branch, Tehran

Nader Jafarnia Dabanloo, PhD, received his PhD degree in 2005 Biomedical

engineering f r o m Iran University of Science and Technology

He is currently a professor at the Medical Sciences and Technologies Faculty

department of Biomedical Engineering Islamic Azad University,

Science and Research Branch, Tehran

Fereidoun Nooshiravan PhD, received his PhD degree in 20011 in Biomedical engineering

f r o m Islamic Azad University, Science and Research Branch, Tehran

He is currently a professor at the Medical Sciences and Technologies Faculty

department of Biomedical Engineering

Islamic Azad University, Science and Research Branch, Tehran

Keivan Maghooli PhD, received his PhD degree in 2003 in Biomedical engineering

f r o m Islamic Azad University, Science and Research Branch, Tehran

He is currently a professor at the Medical Sciences and Technologies Faculty

department of Biomedical Engineering Islamic Azad University,

Science and Research Branch, Tehran

A. Weiss and A. Yeredor, "Non-Iterative Missing Samples Recovery of ECG Signals by Lmmse Estimation for an Autoregressive Cyclostationary Model," 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada, 2018, pp. 930-934, doi: 10.1109/ICASSP.2018.8462567.
AJEM Janssen, R Veldhuis, and L Vries, “Adaptive interpolation of discrete-time signals that can be modeled as autoregressive processes,” IEEE Transactions 933 on Acoustics, Speech, and Signal Processing, vol. 34, 2, pp. 317–330, 1986.
JJK ´O Ruanaidh and WJ Fitzgerald, “Interpolation of missing samples for audio restoration,” Electronics Letters, vol. 30, no. 8, pp. 622–623, 1994.
Shwu-Huey Yen, Hsien-Yang Li, and Po-Yen Kuo, “Image completion using sample synthesis,” in Proc. of IEEE International Conference on Advanced Information Networking and Applications (AINA), 2017, pp. 328–335.
Radhakrishna Achanta, Nikolaos Arvanitopoulos Darginis, and Sabine S¨usstrunk, “Extreme image completion,” in Proc. of ICASSP, 2017.
Cristian Genes, Inaki Esnaola, Samir M Perlaza, Luis F Ochoa, and Daniel Coca, “Recovering missing data via matrix completion in electricity distribution systems,” in Proc. of IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2016, pp. 1–6
Diego Mart´ın-Mart´ınez, Pablo Casaseca-de-la Higuera, Marcos Mart´ın-Fern´andez, Abbes Amira, Chunbo Luo, Christos Grecos, and Carlos Alberola-L´opez, “A stochastic modelling framework for the reconstruction of cardiovascular signals,” in Proc. of the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2014, pp. 676– 679.
Kyoung Jae Kim, Vibhor Agrawal, Ignacio Gaunaurd, Robert S Gailey, and Christopher L Bennett, “Missing sample recovery for wireless inertial sensor-based human movement acquisition,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 24, no. 11, pp. 1191–1198, 2016.
JANG J-S. R, SUN C-T, MIZUTANI E. “Neuro-Fuzzy and Soft Computing”, 1997, Prentice All, Inc. ISBN 0-13-261066-3
A. D. Aghdam, N. J. Dabanloo, M. Sattari, G. Attarodi and N. Hemmati, "Design and processing of a novel algorithm using ANFIS for new generation of cardiac pacemakers," 2017 Computing in Cardiology (CinC), Rennes, 2017, https://doi: 10.22489/CinC.2017.110-367.
Quiroz-Juárez, M. A., et al. (2018). "Cardiac Conduction Model for Generating 12 Lead ECG Signals with Realistic Heart Rate Dynamics." IEEE Transactions on Nano Bioscience 17(4): 525-532.
Grabowski, P.Z. Kazmierkowski, M.P. Bose, B.K.Blaabjerg F, “A simple direct-torque neuro-fuzzy control of PWM-inverter-fed induction motor drive,” IEEE Trans. on Industrial Electronics, Vol. 47, Issue 4, Aug. 2000, pp.863-870 https://doi.org/10.1109/41.857966
Nasir Uddin M., Hao Wen, “Model Reference Adaptive Flux Observer Based Neuro-Fuzzy Controller for Induction Motor.
J.C. Bezdek, Fuzzy Mathematics in Pattern Classification. PhD dissertation, Cornell University, Ithaca, NY, 1973.

Download PDF

Version 1

posted

You are reading this older preprint version

Read the latest preprint version →

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

Status:

Version 1

Abstract

Figures

1. Introduction

2. ANFIS Concept and Design

3. Anfis Learning Methods

3.1 ANFIS controller design by FCM method and comparison with other methods

4. Synthetic data generated at MATLAB environment (The Proposed Method)

4.1 ANFIS learning methods:

4.2 Design of FCM based ANFIS:

5. Results And Discussion:

6. Conclusion

Abbreviations

Declarations

References

Status:

Version 1