Skip to main content

Table 1 Summary of quality-dependent features used for supervised learning

From: nanite: using machine learning to assess the quality of atomic force microscopy-enabled nano-indentation data

Number

Feature name

Short description

1

Area of IDT spikes

Area of spikes appearing in the indentation part

2

Curvature at CP

Curvature of the force-distance data at the contact point

3

Flatness of APR residuals

Fraction of the positive-gradient residuals in the approach part

4

Maxima in IDT residuals

Sum of the indentation residuals’ maxima in three intervals in-between 25% and 100% relative to the maximum indentation

5

Monotony of IDT

Change of the gradient in the indentation part

6

Overall IDT residuals

Sum of the residuals in the indentation part

7

Relative APR size

Length of the approach part relative to the indentation part

8

Residuals at CP

Mean value of the residuals around the contact point

9

Residuals in 75% IDT

Sum of the residuals in the indentation part in-between 25% and 100% relative to the maximum indentation

10

Residuals of APR

Absolute sum of the residuals in the approach part

11

Slope of BLN

Slope obtained from a linear least-squares fit to the baseline

12

Variation in BLN

Comparison of the forces at the beginning and at the end of the baseline

  1. The features are visualized in Fig. 4; Abbreviations in feature names: indentation (IDT), contact point (CP), approach (APR), baseline (BLN)