Application solutions today are not sensitive to the user’s environments and the user’s needs. It constantly requires user’s input in order to react. Even with the user’s input, it does not always react in the appropriate manner that is required by the user. With the introduction of device heterogeneity in our daily lives, humans will be surrounded by intelligent interfaces supported by computing and networking technologies. Intelligence will be incorporated in everyday objects like clothes, vehicles, picture frames, even the cup of which we drink from.
Many powerful visual tracking techniques exist. Most of them are built using model estimation concepts, such as Kalman filters or Sequential Monte Carlo methods, particularly particle filters. A significant advantage that particle filters have over Kalman filters is that particle filters can represent ambiguity in the target’s position, whereas Kalman filters can only represent a single hypothesis at a time. The multiple hypotheses maintained by particle filters can be viewed as physical particles sprinkled over the image plane, and are often shown as spots of different colours or intensity.
It is believed that in the future, services will likely be highly customised to an individual’s situational requirement. Devices will communicate with each other in their presence sphere. For such highly personalised services, a communication infrastructure would need to support new functionalities for it to exhibit situational awareness of the surroundings and the inherent knowledge of ones behaviour towards it.
To provide these user centric solutions, information that surrounds the user needs to be sensed in a structured manner. Information about the user’s intentions or activity at any moment in time needs to be inferred. This sensed information is required to be interpreted and assessed by applications in order to provide user centric solutions. Upon detection of the right stimulus, the application would be required to act appropriately according to the user’s needs. All these requirements of a user centric solution prompts the importance of a dedicated framework, to collate, predict and act, making development of such user centric solutions more structured and manageable.
The review of research literature today reveals that there are a multitude of issues that are required to be addressed ranging from architectural, sensing, context modelling, context processing, context discovery and dissemination, and many more. The study of these issues coupled with the understanding of behaviours through established Information Systems (IS) theories enabled the development of a framework for context aware solutions.
We have developed a context aware service platform based on the proposed framework that utilises ontologies
as representation of knowledge models and exposed application programming interfaces (APIs) that would
simplify the process of creating a context aware solution. To demonstrate the platform developed, we have
also developed a simulation environment that allows the simulation of service scenarios within a single
computer. This makes it easy for any future extension of study in this area of research.