Table 7 Feature description human activity recognition using smartphones dataset (variables from the signal)
From: Selecting critical features for data classification based on machine learning methods
No | Variables |
|---|---|
1 | Mean value |
2 | Standard deviation |
3 | Median absolute deviation |
4 | The largest value in an array |
5 | The smallest value in an array |
6 | Signal magnitude area |
7 | Energy measure |
8 | Interquartile range |
9 | Signal entropy |
10 | Auto regression coefficients |
11 | Correlation coefficient |
12 | Index of the frequency component with the largest magnitude |
13 | Weighted average |
14 | The skewness of the frequency domain signal |
15 | Kurtosis of the frequency domain signal |
16 | The energy of a frequency interval within the 64 bins of the FFT of each window. |
17 | Angle between vector |