No description available.

Wearable wireless sensor devices, which are implemented by deploying sensor nodes on objects, are widely utilized in a broad field of applica-tions, especially in the healthcare system for improving the quality of life or monitoring different types of physical data from the observed objects. The aim of this study is to design an in-home, small-size and long-term wearable fall detection system in wireless network by using barometric pressure sensing for elderly or patient who needs healthcare monitoring. This threshold-based fall detection system is to measure the altitude of different positions on the human body, and detect the fall event from that altitude information. As a surveillance system, it would trigger an alert when the fall event occurs so that to protect people from the potential life risk by immediate rescue and treatment. After all the performances evaluation, the measurement result shows that standing, sitting and fall state was detected with 100% accuracy and lying on bed state was detected with 93.3% accuracy by using this wireless fall detection system. Furthermore, this system with low power consumption on battery-node can operate continuously up to 150 days.

In partnership with iMonSys - an emerging company in the passive care field - a new system, 'Verity', is being developed to fulfil the role of a passive behaviour monitoring and alert detection device, providing an unobtrusive level of care and assessing an individual's changing behaviour and health status whilst still allowing for independence of its elderly user. In this research, a Hidden Markov Model incorporating Fuzzy Logic-based sensor fusion is created for the behaviour detection within Verity, with a method of Fuzzy-Rule induction designed for the system's adaptation to a user during operation. A dimension reduction and classification scheme utilising Curvilinear Distance Analysis is further developed to deal with the recognition task presented by increasingly nonlinear and high dimension sensor readings, and anomaly detection methods situated within the Hidden Markov Model provide possible solutions to identification of health concerns arising from independent living. Real-time implementation is proposed through development of an Instance Based Learning approach in combination with a Bloom Filter, speeding up the classification operation and reducing the storage requirements for the considerable amount of observation data obtained during operation. Finally, evaluation of all algorithms is completed using a simulation of the Verity system with which the behaviour monitoring task is to be achieved.

In partnership with iMonSys - an emerging company in the passive care field - a new system, 'Verity', is being developed to fulfil the role of a passive behaviour monitoring and alert detection device, providing an unobtrusive level of care and assessing an individual's changing behaviour and health status whilst still allowing for independence of its elderly user. In this research, a Hidden Markov Model incorporating Fuzzy Logic-based sensor fusion is created for the behaviour detection within Verity, with a method of Fuzzy-Rule induction designed for the system's adaptation to a user during operation. A dimension reduction and classification scheme utilising Curvilinear Distance Analysis is further developed to deal with the recognition task presented by increasingly nonlinear and high dimension sensor readings, and anomaly detection methods situated within the Hidden Markov Model provide possible solutions to identification of health concerns arising from independent living. Real-time implementation is proposed through development of an Instance Based Learning approach in combination with a Bloom Filter, speeding up the classification operation and reducing the storage requirements for the considerable amount of observation data obtained during operation. Finally, evaluation of all algorithms is completed using a simulation of the Verity system with which the behaviour monitoring task is to be achieved.