Skip to main content

Table 4 User identification results for activities S1–S5 based on chosen performance metrics

From: Identifying smartphone users based on how they interact with their phones

Short-term activitiesClassifierAccuracy %F-measureKappaRMSE
S1SVM71.790.7160.7060.186
Random forests71.150.7010.7000.141
Bayes net60.890.5950.5930.163
S2SVM45.390.4500.4310.187
Random forests57.230.6680.5540.162
Bayes net28.280.2430.2530.209
S3SVM75.560.7540.7440.186
Random forests76.200.7480.7510.133
Bayes net60.450.5950.5860.160
S4SVM60.360.5870.5870.187
Random forests59.750.5800.5800.151
Bayes net50.000.4700.4790.175
S5SVM59.750.5880.5790.187
Random forests54.260.5160.5200.162
Bayes net38.410.3230.3550.179