Skip to main content

Table 4 The mean of the accuracy on data stream Hyperplane3

From: Comparative study between incremental and ensemble learning on data streams: Case study

  Data-chunk size 500 1000 2000
Classifier number Algorithm    
10 SEA 77.08±9.59 78.44±11.07 77.42±4.03
  AWE 88.04±2.52 86.99±2.97 85.13±2.20
20 SEA 79.4±18.41 78.58±5.78 75.8±4.98
  AWE 88.26±2.61 87.17±3.12 85.53±2.04
30 SEA 79.26±6.22 78.82±8.45 75.44±1.84
  AWE 88.75±2.36 87.86±2.70 86.44±1.84
  1. SEA get the optimal accuracy at a 500 data chunk size and 20 base classifiers, while AWE algorithm get optimal accuracy at a 500 data chunk size and 30 base classifiers.