Electrocardiogram (ECG) modeling is important for synthesis of the signal for pathology and compressed representation of the signal. Autoregressive integrated moving average (ARIMA) model provides model parameters based on current and previous samples. In this paper, we present the optimization of the ARIMA model hyperparameters using grid search (GS) and particle swarm optimization (PSO) techniques. At first, the preprocessing of the ECG is done using a discrete wavelet transform base approach. Then, the R-peaks are detected along with the cardiac beat extraction. Each cardiac cycle is then modeled using ARIMA model, whose hyperparameters are optimized by GS and PSO. For validation and testing, the different cardiac rhythms (normal and abnormal) and healthy and cardiac diseases are used from mitdb and ptbdb data under PhysioNet. Over six types of cardiac rhythms from the mitdb database, the mean absolute error of $1.56\times 10^{-2}\ \text{mV}$ and $0.46\times 10^{-2}\ \text{mV}$ and three types of cardiac rhythms from ptbdb database, the mean absolute error of $0.29\times 10^{-2}\text{mV}$ and $0.19\times 10^{-2}\text{mV}$ were obtained with GS and PSO respectively. In general, it was found that the error figures are better for PSO based technique.

Hyperparameter Optimization of AutoRegressive Integrated Moving Average (ARIMA) Model-based Synthesis of Electrocardiogram

Background: ECG modeling has wide application in signal representation, compression and synthetic ECG generation. Method: CardioSim generates synthetic ECG waveform in real-time using PC-based system. It provides dual facility of interface-based visualization with hardware-based waveform generation. It has two stages viz., development of reference model parameter database using Fourier model and generation of synthetic ECG waveform based on user defined parameters using normal and abnormal records (H, APC, PVC, LBBB, RBBB, P) from mitdb under PhysioNet. Result: It generates ten various ECG waveforms including one healthy and nine diseased rhythms from a single dynamic model with flexible user defined parameters. It gives higher reconstruction performance in terms of SNR and MSE. The mean SNR for different beat morphology is 89.2(H), 88.37(V), 86.32(A), 85.35(L), 97.22(P) and 83.3(R) and mean MSE is 2.45 × 10-6(H), 3.14 × 10-6(V), 8.98 × 10-6(A), 5.82 × 10-6(L), 0.43 × 10-6(P) and 0.25 × 10-6(R). Conclusion: It improves the performance parameters over published research work on ECG modeling and simulation. It can be used as a self-learning tool for entry level medical students.

CardioSim: a PC-based cardiac signal simulator using segmental modeling of electrocardiogram.

Electrocardiogram (ECG) modeling is useful for abnormality detection and data compression. The common research problem in modeling is retaining pathological information using minimum number of model coefficients. In this paper, a new modeling technique for different wave segments of ECG signal, viz., baseline to P-onset, P wave, P-offset to Q, QRS complex, S to T-onset, T wave and T-offset to next baseline is presented. The processing steps included preprocessing, R-peak detection, beat segmentation and waveform partitioning, followed by modeling of individual partitions. For P, QRS and T wave, Gaussian model was adopted and for other segments, Fourier model was adopted to minimize reconstruction error. For testing of the proposed model, normal sinus rhythm (NSR) and myocardial infarction (MI) data records of PTB Diagnostic ECG database (ptbdb) and atrial premature (APC), premature ventricular contraction (PVC), left bundle branch block (LBBB) and right bundle branch block (RBBB) data records of MIT-BIH arrhythmia database (mitdb) under PhysioNet were used. The average SNR, and MSE using proposed method for ptbdb NSR was 86.33, and 4.41×10-6, respectively; for AMI 96.18, and 3.70×10-6 respectively; for IMI 80.86, and 1.36×10-6 respectively; for mitdb NSR 90.94 and 3.50×10-6 respectively; for APC 89.42, and 2.34×10-6 respectively; for PVC 93.28 and 3.06×10-6, respectively; for LBBB 93.77 and 2.74×10-6, respectively; for RBBB 92.83 and 3.52×10-6 respectively. Segment specific modelling approach provides better reconstruction performance in comparison with the few published works using Gaussian and Fourier model.

Anumita Mitra

Papers

Hyperparameter Optimization of AutoRegressive Integrated Moving Average (ARIMA) Model-based Synthesis of Electrocardiogram

CardioSim: a PC-based cardiac signal simulator using segmental modeling of electrocardiogram.

Segment Specific Modeling of Electrocardiogram for Improved Reconstruction Error