11-06-2015, 04:08 PM
Definition
The present paper introduces a method to authenticate people from their physiological activity, concretely the combination of ECG and EEG data. We call this system STARFAST (STAR Fast Authentication bio-Scanner Test). Several biometric modalities are already being exploited commercially for person authentication: voice recognition, face recognition and fingerprint recognition are among the more common modalities nowadays. But other types of biometrics are being studied as well: ADN analysis, keystroke, gait, palm print, ear shape, hand geometry, vein patterns, iris, retina and written signature
Although these different techniques for authentication exist nowadays, they present some problems. Typical biometric traits, such as fingerprint, voice and retina, are not universal, and can be subject to physical damage (dry skin, scars, loss of voice...). In fact, it is estimated that 2-3% of the population is missing the feature that is required for authentication, or that the provided biometric sample is of poor quality. Furthermore, these systems are subject of attacks such as presenting a registered deceased person, dismembered body part or introduction of fake biometric samples. It also compares the performance of the system with the Active Two system from Biosemi.
The Active Two system is state of the art commercial equipment that is proven to have very good performance and has been used in many studies. So far 3 demonstration applications have been developed using the system. EOG based Human Computer Interface (HCI), EEG and ECG based Biometry for Authentication (presented at pHealth as a poster) and an EEG based Sleepiness Prediction system for drivers. In all cases the applications are designed around the same 4 channel system. ENOBIO has been developed with the help of the SENSATION FP6 IP 507231.
With the evolution of m-Health, an increasing number of biomedical sensors will be worn on or implanted in an a individual in the future for the monitoring, diagnosis, and treatment of diseases. For the optimization of resources, it is therefore necessary to investigate how to interconnect these sensors in a wireless body area network, wherein security of private data transmission is always a major concern. This paper proposes a novel solution to tackle the problem of entity authentication in body area sensor network (BASN) for m-Health. Physiological signals detected by biomedical sensors have dual functions:
1) for a specific medical application, and
2) for sensors in the same BASN to recognize each other by biometrics.
A feasibility study of proposed entity authentication scheme was carried out on 12 healthy individuals, each with 2 channels of photoplethysmogram (PPG) captured simultaneously at different parts of the body. The beat-to-beat heartbeat interval is used as a biometric characteristic to generate identity of the individual. The results of statistical analysis suggest that it is a possible biometric feature for the entity authentication of BASN. Advantages Since every living and functional person has a recordable EEG/ECG signal, the EEG/ECG feature is universal.
Moreover brain or heart damage is something that rarely occurs, so it seems to be quite invariant across time. Finally it seems very difficult to fake an EEG/ECG signature or to attack an EEG/ECG biometric system. An ideal biometric system should present the following characteristics: 100% reliability, user friendliness, fast operation and low cost. The perfect biometric trait should have the following characteristics: very low intra-subject variability, very high inter-subject variability, very high stability over time and universality. In the next section we show the general architecture and the global performance of the system we have developed.