Skip to main content

Table 3 Experimental results data of static section

From: Machine-learning-based children’s pathological gait classification with low-cost gait-recognition system

Algorithm

Recall

Average precision (%)

Time cost (ms)

Accuracy/time cost P-value

LDA + SVMrbf

0.85/0.92/1.00/0.80

89.39

1.10

0.698/ <  < 0.01

LDA + SVMlin

0.85/0.96/1.00/0.83

90.90

0.50

PCA + SVMlin

0.82/0.90/1.00/0.86

89.49

0.89

0.690/ <  < 0.01

PCA + SVMrbf

0.89/0.91/1.00/0.90

92.41

2.07

0.623/ < 0.01

LDA + NN

0.82/0.95/1.00/0.81

89.75

0.46

0.765/0.388

  1. “–” means the P--value of this column is computed based on this algorithm. In the Recall column, the value separated by “/” means recall value of normal, toe-in, toe-out, and flat, respectively