Skip to main content

Table 1 Classification accuracy (%) on 5-class EMG-based gesture recognition task using 64-channel flexEMG data [22]

From: Near-channel classifier: symbiotic communication and classification in high-dimensional space

Classifier Representation   SVMa [49]
Float
HDa [22]
Float
HD (ours)
Bipolar
Subject Session    
1 1 98.13 99.60 97.20
3 100.00 99.20 98.20
2 1 99.53 98.33 98.53
3 96.47 97.53 96.07
3 1 99.60 90.40 92.27
3 83.07 90.87 82.53
Average 96.13 95.99 94.13
  1. We compare a linear SVM, an HD classifier with multiplicative embedding, and our HD classifier with bipolar CiM embedding. Both HD classifiers operate at dimension \(D=10\,000\)
  2. aReproduced