Table 1 Overview of the pretreatment methods used in this study. In the Unit column, the unit of the data after the data pretreatment is stated. O represents the original Unit, and (-) presents dimensionless data. The mean is estimated as: ${\overline{x}}_i=\frac{1}{J}{\displaystyle \sum _{j=1}^J{x}_{ij}}$ and the standard deviation is estimated as: $s_i=\sqrt{\frac{{\displaystyle \sum _{j=1}^J{\left(x_{ij}-{\overline{x}}_i\right)}^2}}{J-1}}$. $\tilde{x}$ and $\widehat{x}$ represent the data after different pretreatment steps.

I

${\tilde{x}}_{ij}=x_{ij}-{\overline{x}}_i$

O

II

${\tilde{x}}_{ij}=\frac{x_{ij}-{\overline{x}}_i}{s_i}$

(-)

${\tilde{x}}_{ij}=\frac{x_{ij}-{\overline{x}}_i}{\left(x_{i_{\max }}-x_{i_{\min }}\right)}$

(-)

${\tilde{x}}_{ij}=\frac{x_{ij}-{\overline{x}}_i}{\sqrt{s_i}}$

O

${\tilde{x}}_{ij}=\frac{\left(x_{ij}-{\overline{x}}_i\right)}{s_i}\cdot \frac{{\overline{x}}_i}{s_i}$

(-)

${\tilde{x}}_{ij}=\frac{x_{ij}-{\overline{x}}_i}{{\overline{x}}_i}$

(-)

III

$\begin{array}{l}{\tilde{x}}_{ij}{=}^{10}\log \left(x_{ij}\right)\\ {\stackrel{⌢}{x}}_{ij}={\tilde{x}}_{ij}-{\overline{\tilde{x}}}_i\end{array}$

Log O

$\begin{array}{l}{\tilde{x}}_{ij}=\sqrt{\left(x_{ij}\right)}\\ {\stackrel{⌢}{x}}_{ij}={\tilde{x}}_{ij}-{\overline{\tilde{x}}}_i\end{array}$

√O