Skip to main content

Table 2 Confusion matrix for classifier using EMG 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

EMG dataset

Predicted Class

EF

AB

ER

HAB

EE

AD

IR

HAD

Actual Class

Flexion

Elbow Flexion (EF)

88

5

3

2

0

0

1

1

Abduction (AB)

6

76

17

1

0

0

0

0

External Rotation (ER)

2

17

76

4

0

0

0

0

Horizontal Abduction (HAB)

2

1

6

91

0

0

0

0

Extension

Elbow Extension (EE)

0

0

0

0

89

5

3

2

Adduction (AD)

0

0

0

0

3

78

17

2

Internal Rotation (IR)

0

0

0

0

3

18

76

4

Horizontal Adduction (HAD)

0

0

0

0

1

3

6

90

  1. Refer to Table 1 text for description. Larger classification errors using EMG alone as compared to other classifiers