Data Fusion Algorithms in Multi-parameter Patient Monitoring
The current used alarm mechanism in patient monitoring is threshold based on single physiological signal which generates a huge number of false alarms. This could increase the workload of the caregivers and increase the life threatening risk. In principle, multi-parameter patient monitoring provides significant advantages over single-parameter monitoring, especially for highly intricate medical diseases and symptoms, which usually involve the correlated rhythms and changes of a set of physiological behaviors. In addition to the statistical advantage gained by combining same-source data, the use of multiple types of physiological information may increase the accuracy with which a quantity can be characterized.
EEG based Biometrics for User Identification and Authentication
Widely used methods of individual identification and authentication, like passwords,
PINs, and RF cards, are easily forgotten, stolen or lost. However, "biometrics" which
refers to the technique used to identify individuals using unique human biological
features, such as fingerprints, face, iris and voice, are more attractive.
Electroencephalogram (EEG) records the brain's electrical activity by measuring the voltage fluctuations on the scalp surface with simple placement of the electrodes on the skin. The brain signals are brain activities determined by the person's unique pattern of neural pathways. Thus it is impossible to imitate. Those signals can be influenced by mood, stress and mental state of the individual which makes them very difficult to be obtained under force and threat. Furthermore, brain signals are related to the subject's genetic information, making them unique for each individual and stable over time. Therefore, brain signals are more reliable and secure and have been proposed as an identification and authentication biometric