Skip to main content

Table 1 Overview of studies on swipe gesture recognition on mobile devices

From: Evaluation of stability of swipe gesture authentication across usage scenarios of mobile device

PublicationYearNumber of subjectsData collection modeScenariosFeature extractionClassificationEER
Frank et al. [6]201341Constrained data collectionNot specifiedTimestamp, X, Y, phone orientationSVM RBF kernel and k-NN0%-Intra-session and 2–3%-inter-session %
Bo et al. [7]2014100Constrained data collectionStatic (no body movement) and walkingTimestamp, X, Y, finger pressureSVMStatic scenario (FAR -Tap 22, Fling-9, Scroll- 23), walking scenario accuracy 100% after 12 steps of walking
Saravanan et al. [8]201420ConstrainedNot specifiedTimestamp, X, Y, pressureSVM, random forests and BayesNet97.9% accuracy mobile phones 96.79% - tablets
Feng at al. [9]201423 phone owners, 100 guest usersUnconstrainedReal-life scenariosTimestamp, X, Y, size, pressure, swipe length, swipe curvatureDTW with one nearest neighbour90% accuracy
Wang et al. [10]2017160 set of app usage dataUnconstrainedNot SpecifiedTimestamp, X, Y, phone orientationSVM RBF KernelAUC (area under the curve) score of 80% to 96% (detecting unauthorised access) %
Our model201850UnconstrainedSitting, walking, treadmill, travelling on a busTimestamp, X, Y, finger area, finger pressureSVM, kNN and naive Bayes1 %