Patient Identification Based on Wrist Activity Data

In the hospital environment, authentication is required to allow patients to access constrained areas such as dedicated patient rooms. Identification is necessary for any authentication design, as the purpose of the authentication is to verify the identity of the user. This paper proposes a novel patient identification approach based on sensory data collected by activity sensors placed on the patients' wrist. It uses a support vector machine based classifier to identify different patients based on statistical and biophysical features extracted from the data. The evaluation results show that the proposed approach can achieve a high identification accuracy of 94.21%.