Classifying accelerometer data via Hidden Markov Models to authenticate people by the way they walk

Promising results have been obtained when using Hidden Markov Models for accelerometer-based biometric gait recognition. So far, the used testing data contains only walking straight on a flat floor, which is not a realistic scenario. This paper shows the results when using a more realistic data set containing walking around corners, upstairs and downstairs etc. It is analyzed to which extent the biometric performance is degraded when this more demanding data set is used. To show practical results the cross-day performance is analyzed and compared with the same-day results. Error rates will be given depending on the amount of training data and after a voting scheme is applied. We obtain an Equal Error Rate (EER) of 6.15% which is less than a third of the EER obtained when applying a cycle extraction method to the same data set.