Signal shape and variation

Edge AI Lab

tags
edge-ai-lab
Feature Description
Crest Factor Calculates the ratio of a signal's peak amplitude to its root mean square (RMS) value. It is particularly useful for analyzing waveforms in:
• Electrical engineering
• Vibration analysis
• Audio processing
Root Difference Square Measures the square root of the mean squared difference between neighboring discrete points. It measures mean signal variation between neighboring points and can be used as a characteristic of the rate of change of a signal.
Average Magnitude Difference A signal processing technique used for periodicity analysis in sensor signals. It is particularly useful in:
• Sensor-based systems where detecting periodic patterns is crucial.
• Speech analysis.
• Music signal processing.

However, it may suffer from incorrect pitch detection in highly noisy conditions, which has led to the development of extended versions for improved performance.
Percentage of Signal over Mean Calculates the ratio between the number of sensor signal values greater than the mean value in a window over the total window size. It is particularly useful in applications where relative changes in the signal are more important than absolute values, such as:
• Vibration analysis
• Environmental monitoring
• Process control systems
Percentage of Signal over Zero Calculates the ratio between the number of positive sensor signal values in a window over the total window size. In other words, it measures the fraction of time the signal was positive.
Percentage of Signal over Sigma Calculates the ratio between the number of sensor signal values greater than the sigma value (mean + n standard deviations) in a window over the total window size.
Autocorrelation Measures the correlation between a signal and a time-shifted version of itself, providing valuable insights into the signal's inherent patterns, periodicities, and statistical properties.