Research Article

Weighted Domain Transfer Extreme Learning Machine and Its Online Version for Gas Sensor Drift Compensation in E-Nose Systems

Table 2

Comparisons of classification accuracy in 9 batches.

Batch numberAccuracy (%)
Ensemble
SVM
Ensemble
ELM
SVM
-rbf
ELM
-rbf
DAELM
(30)
DAELM
(50)
WDTELM
(<30)
WDTELM
(<48)

77.475.358.576.885.596.290.298.2
74.876.966.975.494.098.890.194.6
72.064.574.569.8100100100100
65.996.044.256.699.510098.999.5
71.371.358.362.073.482.195.398.5
55.168.868.968.064.379.878.184.7
42.981.860.587.794.697.694.697.3
56.649.650.940.010010099.1100
32.949.418.419.341.555.862.664.6

Ave.64.172.555.761.783.890.189.993.0