Table 8.

Most common time domain features and their formula.

Time Domain Feature	Definition	Formula	Remark
Root mean square (RMS)	It is used to compute the average energy of the signal.	$\mathit{R}\mathit{M}\mathit{S}=\sqrt{\left(\frac{{\sum }_{n=1}^N{X}^2\left[n\right]}{N}\right)}$	N = sample size. n = single value of N. X = amplitude value of sample size. μ = mean value of sample data. σ = standard deviation. Xpeak = maximum peak value of X. XRMS = root mean square value.
Standard deviation	Represents the degree of variation or dispersion from the average.	$\mathit{\sigma }={(\frac{1}{N}{\displaystyle \sum _{n=1}^N}{(X-\mu )}^2)}^{1/2}$
Kurtosis	It is dimensionless and the fourth-order normalized moment of sample data sensitive to impact signal and represents the steepness of the data distribution density function.	K = $\sqrt{(\frac{\frac{1}{N}{\sum }_{n=1}^N{(X\left[n\right]-\mu )}^4}{{(X\left[n\right]-\mu )}^2{)}^2}})$
Skewness	This is a dimensionless indicator of the degree of asymmetry of the data distribution as represented by the third-order normalized moment of the data distribution.	S = $\frac{\frac{1}{N}{\sum }_{n=1}^N{(X\left[n\right]-\mu )}^3}{\frac{1}{N}{\sum }_{n=1}^N{(X\left[n\right]-\mu )}^3{)}^{\frac{3}{2}}}$
Peak to the average value (PAR)	It is defined as the ratio of the peak to the average value of a sample of data and can be used to indicate significant transient noise.	PAR = $\frac{X_{Peak}}{X_{RMS}}$