Optimizing EKG signal analysis using the MaxEnt-Burg algorithm

Through its repeating patterns, the electrocardiogram (EKG) is an essential tool for diagnosing cardiac activity. We explore the use of the Maximum-Entropy (ME) Burg algorithm in EKG signal analysis. A comparison is made with traditional Fourier Transformation (FT). Detecting anomalous activity in EKG time series is challenging for FT & curve fitting. FT & FFT problems include sinc wiggles caused by time-window effects and noise transformation. These become evident, if weak time signals &/or deviations from normal patterns are present. If signals are strong, these effects overwhelm any deviations from normalcy. To resolve these issues, the ME-Burg method is proposed for EKG analysis. This early AI technique uses autoregression to maximize information and minimize noise. In the ME-Burg algorithm, each signal S(i) at time 𝑖 is assumed to be related to earlier S(i - k). That is true for magnetic resonance & EKG data. As shown by muon-spin resonance data analysis, this efficiently decreases noise, prevents sinc wiggles and improves the detection of anomalous or weak repetitive signals. If the ME-Burg method is used for EKG signals, two approaches are promising: •1> To reduce noise, one averages signals over a period To (repeated several times in an interval Tm) & applying the ME-Burg algorithm to this . •2> Applying ME-Burg to each To period and geometrically averaging the resulting ME transforms. .