Visualizing Human Behavioral Features based on Signature Haptic Data

Haptic technology refers to the technology that connects the user to a computerized system via the sense of touch by applying forces, vibrations and/or motions to the user. With this technology it is possible to measure and record haptic data generated directly as users interact with the system. Haptics can be seen as a mechanism to extract behavioral features that characterize a biometric profile for an identity authentication process. Generally, the haptic data captured during an individual interaction are very large (measured every few milliseconds) and with a high number of attributes (position, velocity, force, angular orientation of the end-effector and torque data, among others). Therefore, the behavioral haptic data that describe users are defined in terms of a large number of features, which adds complexity to the analysis. It is desirable to find a 3D virtual representation that shows the similarity of a user´s haptic data during different trials, as well as the existing relationship among other users´ features. In this paper, through this approach and with data collected from a multimodal system for signing a virtual cheque, interesting patterns and relationships, which are somewhat hidden in the original data, are described for individual authentication.