Convex-Hull-based-Empirical-Mode-Decomposition-features
Area measure of the convex hull polygon of the Intrinsic Mode Functions
Convex Hull Analytics of Intrinsic Mode Functions as Feature vectors for Machine learning problems by employing a set of amplitude and frequency modulated (AM–FM) signals called Intrinsic mode functions (IMF’s). These IMF’s are generated by the Empirical Mode Decomposition (EMD) of time series and the analytic signal representation of these IMFs by means of Hilbert transformation forms the trace of the elliptical shaped analytic IMFs in the complex plane. The area measure and the centroid position of the polygon formed by the Convex Hull of these analytic IMF’s is taken as the discriminating features. Also, the efficacy of several potential bio-markers like Amplitude Modulation Bandwidth (BAM), Frequency Modulation Bandwidth (BFM) and Mean Frequency (MF) fromFourier-Bessel expansion for each of these analytic IMF’s has been discussed for its potency in diagnosis in statistical pattern recognition and classification problems.
Area measure of the convex hull polygon of the Intrinsic Mode Functions
Convex Hull Analytics of Intrinsic Mode Functions as Feature vectors for Machine learning problems by employing a set of amplitude and frequency modulated (AM–FM) signals called Intrinsic mode functions (IMF’s). These IMF’s are generated by the Empirical Mode Decomposition (EMD) of time series and the analytic signal representation of these IMFs by means of Hilbert transformation forms the trace of the elliptical shaped analytic IMFs in the complex plane. The area measure and the centroid position of the polygon formed by the Convex Hull of these analytic IMF’s is taken as the discriminating features. Also, the efficacy of several potential bio-markers like Amplitude Modulation Bandwidth (BAM), Frequency Modulation Bandwidth (BFM) and Mean Frequency (MF) fromFourier-Bessel expansion for each of these analytic IMF’s has been discussed for its potency in diagnosis in statistical pattern recognition and classification problems.