This paper describes an approach to the design of optimum QRS detector
s. We report on detectors including a linear or nonlinear polynomial f
ilter, which enhances and rectifies the QRS complex, and a simple, ada
ptive maxima detector. The parameters of the filter and the detector,
and the samples to be processed are selected by a genetic algorithm wh
ich minimizes the detection errors made on a set of reference ECG sign
als. Three different architectures and the experimental results achiev
ed on the MIT-BIH Arrhythmia Database are described.