Pattern recognition, and in particular dynamic time warping has been applied to the ECG for many different purposes over the last decade. Significant research on creating adaptive, feature based, and more complex forms of the algorithm in order to increase its ability to classify an ECG signal accurately has been performed. Despite this increase in complexity and in the number of variations of the dynamic time warping algorithm there has been less focus on actually using the results of dynamic time warping to relate the reference and test signals to each other as accurately as possible. The majority of dynamic time warping algorithms published in the literature, even the most complex of them, classify the most accurate match to a reference signal based only on resulting Euclidean distance or slope difference between samples of the known reference and unknown query signal. This article demonstrates how a combination of measurements including heart-rate, amplitude and required warping time alignment can be used to reduce the resulting error in the classification of a query signal after the query and reference signals have been warped together. Its benefits are verified with significant testing.

Dynamic time warping techniques have been used to characterize the timing variation of the constituent components of the human electrocardiogram (ECG). Lead II ECG recordings were obtained in 21 subjects, 10 male and 11 female aged between 13-65 years. The fiducial points in each cardiac cycle were identified in the recordings across the range of heart rate from 46-184 beats/min. A set of second order equations in the square root of the cardiac cycle time was obtained to describe the duration each of the constituent components in the ECG signal. The accuracy of the dynamic time warping technique was verified against professionally annotated clinical recordings in the on-line PhysioNet™ database. The equations obtained allow a Lead II ECG signal to be synthesized in which the variation with heart rate of the profile of each in the signal mirrors the true in-vivo behaviour.

This paper reports the design and development of a precision ECG signal generator intended for use in test and calibration of electrocardiographic equipment, ECG signal processing systems and as a cardiac teaching tool. It generates a Lead II signal which maintains the timing and profile characteristics of a Lead II electrocardiograph signal across a range of heart rates between 45 and 185 bpm in 1 bpm steps. The QRS amplitude can be adjusted in 1 microV increments from 100 microV to 10 mV. The up-slope of the QRS can be set between 15 ms and 45 ms with 1 ms resolution. The P and T wave amplitudes can be adjusted as a 1-100% scaling of the QRS complex amplitude with a 1% resolution. A color LCD with touch screen capability provides the user with facilities for inputting parameters, viewing the output wave parameters and a graphical representation of the resulting output waveform. The signal generator outputs a precision differential signal via a digital to analogue stage which has been designed using low noise techniques to produce accurate signals at the lower end of the QRS amplitude range.

The use of ECG recordings as a diagnostic tool relies heavily on the fidelity of the recorded signal. ECG signal synthesis is therefore vital in the testing and commissioning of ECG recording equipment. A number of signal generators have been previously presented in the literature, however the platforms they were developed on have become dated and more importantly their architectures do not provide a temperature-stable generator capable of operating at the necessary levels of precision in the voltage range required. The shortcomings of previous instruments are overcome here using a novel approach to the digital and analogue stages of the signal conditioning process. It offers significantly increased precision over the 100 μV-10 mV amplitude range, includes voltage offset correction and full temperature stability. The devices capability has been analysed and tested significantly more than any of its predecessors, and the results demonstrate it is a significant step forward in ECG signal synthesis.