Damian Kelly

Single access point location tracking for in-home health monitoring

There is a steady increase in the importance placed on location based systems, particularly in the field of elder care. The focus of this paper is on the development of a single access point indoor location tracking system. It is believed that with a single access point localisation system, room-level location accuracy can be reliably achieved. This paper will introduce such a localisation method and provide the basis for its functioning.

A Prototype Sourceless Kinematic-Feedback Based Video Game for Movement Based Exercise.

This paper presents a prototype kinematic and audio feedback based video game, availing of a scalable motion capture acquisition system, based around a number of orientation sensors. The orientation sensors used are USB based tri-axis magnetic and gravitational field transducers. The novel video-game is capable of incorporating the real time data from these sensors to control an on screen avatar, which in turn can be programmed to give appropriate instructions to the user i.e. play a sound file, once the user obtains a certain posture. The video game is designed to promote physical exercise and movement based relaxation, in particular; yoga. In addition, design considerations; implementation and performance of the system are analyzed, discussed and the accuracy qualitatively analyzed by comparing movement data obtained from it to that of a validated motion analysis technique, the CODA motion analysis system

A Bluetooth-based minimum infrastructure home localisation system

Indoor location tracking is a function best suited to wireless LAN devices. This generally precludes it from home use in isolated rural areas, where WLAN is a rare commodity. We propose an affordable localisation system which can be implemented using a variety of Bluetooth enabled mobile phones. This permits the incorporation of cellular network signal measurements as well as Bluetooth link measurements into the localisation framework. This paper presents a Hidden Markov Model localisation method, utilising the Viterbi algorithm, which enables single Bluetooth access point localisation. The improvement of accuracy this presents over a Naive Bayes classifier is illustrated, along with the optimal method of obtaining training data.

Single access point localisation for wearable wireless sensors

Knowledge of a subjects location and motion throughout an environment is of significant use to in-home health monitoring and activity recognition systems. This work develops a method of tracking a subjects location using the radio frequency (RF) signals emanating from wearable wireless sensors. It differs from other RF location tracking work in that it utilises the hardware which would already be deployed in a biomedical monitoring application. This is achieved by combining the RSSI (Received Signal Strength Indicator) and LQI (Link Quality Indicator) readings from a single basestation. It is shown that accuracy approaching that of a multiple basestation localisation deployment is achievable by using a suitable level of filtering. As a result of this work, location information can be more readily and cheaply incorporated into future biomedical monitoring applications.

Minimal hardware Bluetooth tracking for long-term at-home elder supervision

The ability to automatically detect the location of an elder within their own home is a significant enabler of remote elder supervision and interaction applications. This location information is typically generated via a myriad of sensors throughout the home environment. Even with high sensor redundancy, there are still situations where traditional elder monitoring systems are unable to resolve the location of the elder. This work develops a minimal infrastructure radio-frequency localisation system for long-term elder location tracking. An RFID room-labelling technique is employed and with it, the localisation system developed in this work is shown to exhibit superior performance to more traditional localisation systems in realistic long-term deployments.