The parameters used with the ANN in the classifying system.
|1. Energy||Sum of squared values of signal.|
|2. Frequency roughness||Mean of the absolute value of the second derivative of the signals’ % Fourier Spectrum.|
|3. Variance||Variance of the track.|
|4. Max-minus-median||Maximum value minus median value.|
|5. Fraction over half-max||The fraction of the signal’s values that are greater from 40% of its maximum value.|
|6. RMS||Root mean square value of the track.|
|7. Fractal dimension||The fractal dimension of the signal with values 1–2.|
|8. Stdev of variances||The standard deviation of the variance values of the signal using a sliding window of 100 measurements.|
|9. Maximum||Maximum value of track.|
|10. Zero-cross area variance||The variance of the integral from one zero-crossing of the signal to another.|
|11. Zero-cross norm area variance||The variance of the integral from one zero-crossing of the signal to another normalized by it duration.|
|12. Zero-cross area difference mean||The mean difference of consecutive integrals from one zero-crossing of the signal to another.|
|13. Zero-cross area difference variance||The variance of the differences of consecutive integrals from one zero-crossing of the signal to another.|
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.