Skip to main content

Table 5 User identification results for activities G1–G7 based on chosen performance metrics

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

GesturesClassifierAccuracy %F-measureKappaRMSE
G1SVM69.750.6990.68510.1867
Random forests73.450.7200.72380.1445
Bayes net65.430.6280.64030.1519
G2SVM70.460.7450.69250.1866
Random forests67.780.6770.66460.1471
Bayes net59.730.5810.58080.1585
G3SVM85.900.8580.85340.1861
Random forests83.220.8240.82540.1327
Bayes net73.820.7360.72770.1317
G4SVM89.870.9000.89470.1861
Random forests87.340.8720.86840.1271
Bayes net83.540.8330.82890.1085
G5SVM84.170.8380.83530.1862
Random forests83.540.8300.82880.1397
Bayes net70.880.7050.69720.1385
G6SVM92.150.9180.91840.186
Random forests92.810.9220.92520.1218
Bayes net90.190.9010.8980.0836
G7SVM92.150.9210.91840.1861
Random forests92.810.9250.92520.1178
Bayes net90.840.9040.90480.0786