Skip to main content

Table 1 Confusion matrix for classifier using the load cell data

From: Applying LDA-based pattern recognition to predict isometric shoulder and elbow torque generation in individuals with chronic stroke with moderate to severe motor impairment

Load cell dataset

Predicted Class

EF

AB

ER

HAB

EE

AD

IR

HAD

Actual Class

Flexion

Elbow Flexion (EF)

92

4

3

1

0

0

0

0

Abduction (AB)

3

87

10

0

0

0

0

0

External Rotation (ER)

2

8

89

1

0

0

0

0

Horizontal Abduction (HAB)

0

0

2

97

0

0

0

0

Extension

Elbow Extension (EE)

0

0

0

0

98

1

0

0

Adduction (AD)

0

0

1

0

1

84

13

0

Internal Rotation (IR)

0

0

0

0

1

14

83

2

Horizontal Adduction (HAD)

0

0

0

0

1

0

2

96

  1. Data are averaged across all participants and rounded to nearest whole number. Movements implicated in flexion synergy are in upper/left portion of table while extension synergy movements are in lower/right portion. Bold numbers identify class accuracy while non-bold numbers indicate percent of misclassification. Flexion synergy: Elbow flexion (EF), shoulder abduction (AB), external rotation (ER) and horizontal abduction (HAB). Extension synergy: elbow extension (EE), shoulder adduction (AD), internal rotation (IR), and horizontal adduction (HAD)