Page 94 - Read Online

Shu et al. Intell Robot 2024;4(1):74-86 I http://dx.doi.org/10.20517/ir.2024.05 Page 82

Table 3. Performance comparison results of each classification method
Upper limb task (finger tapping) Lower limb task (toe tapping)
Classification method
Accuracy Weighted precision Kappa coefficient Accuracy Weighted precision Kappa coefficient
SVM 60.00% 60.40% 0.41 61.22% 60.92% 0.45
LSTM 62.22% 63.64% 0.45 63.27% 62.48% 0.46
CPN 66.67% 67.55% 0.51 73.47% 74.64% 0.61
Our method 75.56% 76.77% 0.64 81.63% 84.65% 0.73
SVM: Support vector machine; LSTM: long short-term memory; CPN: convolutional pro-
totype network.

class. It can be given as Equation 6.

 · · · 1 · · · 
 11 1 
 . . . . . 
 . . . . . . . . . . 
 
  (6)
=  1 · · · · · · 
 . . . . . 
 . . . . . . . 
 . . . 
 
 1 · · · · · · 
 
where denotes the number of samples that belong to class and are classified as class . represents the
dimension of the matrix, corresponding to the total number of classes. This paper employs accuracy ( ),
weighted precision ( ), and kappa coefficient ( ) as evaluation metrics to assess the overall performance
of the classification method. The respective formulas are given as Equations 7-9.
∑
=1
= (7)

( )
∑
∑
=1
= ∑ · (8)
=1 =1
( )
∑ ∑ ∑
∑ ·
=1 − =1 =1 =1
2
= ( ) (9)
∑ ∑ ∑
=1 =1 · =1
1 −
2
where denotes the total number of samples in the dataset.
Thepresentstudycomparestheproposedmethodwiththethreecomparisonmethods, andconfusionmatrices
for the four classification methods of finger and toe tapping tasks are shown in Figures 6 and 7, respectively.
ClassificationperformancemetricscalculatedfromtheCMarepresentedinTable3. Forthefingertappingtask,
the proposed method achieves an accuracy of 75.56%, a weighted precision of 76.77%, and a kappa coefficient
of 0.64. In comparison, the CPN method achieves an accuracy of 73.47%, a weighted precision of 74.64%,
and a kappa coefficient of 0.61. The LSTM method achieves an accuracy of 62.22%, a weighted precision
of 63.64%, and a kappa coefficient of 0.45. The SVM method achieves an accuracy of 60.00%, a weighted
precisionof60.40%, andakappacoefficientof0.41. Relativetothecomparisonmethods, theproposedmethod
showsimprovementsof8.89%-15.56%inaccuracy, 9.22%-16.37%inweightedprecision, and0.13-0.23inkappa
coefficient.

For the toe tapping task, the proposed method achieves an accuracy of 81.63%, a weighted precision of 84.65%,
and a kappa coefficient of 0.73. In comparison, the CPN method achieves an accuracy of 66.67%, a weighted
precision of 67.55%, and a kappa coefficient of 0.51. The LSTM method achieves an accuracy of 63.27%, a
weightedprecisionof62.48%,andakappacoefficientof0.46. TheSVMmethodachievesanaccuracyof61.22%,
a weighted precision of 60.92%, and a kappa coefficient of 0.45. The proposed method shows improvements
of 8.16%-20.41% in accuracy, 10.01%-23.73% in weighted precision, and 0.12-0.28 in the kappa coefficient.