Research Interest
Context- and situation-awareness, location system, pervasive and ubiquitous computing, semantics of information, wireless sensor network, ontology, lattice theory, category theory
Research projects
- 2009-present “Autonomic Sensor Communities” in CLARITY Project
- 2008-2009 “Situation Lattices” The main part of my PhD work is to propose, develop and evaluate a sound mathematical abstraction, situation lattices, to systematically study the semantics of information in pervasive computing systems. With the help of hierarchical features and operators in lattice theory, situation lattices have a powerful ability to represent the semantics of sensor data, environmental information, and human knowledge. They are useful in learning and building consistent relationships between the above information and higher-level information that is interesting to applications, called situations. Richer semantics between situations can also be derived, such as specialisation and mutual exclusiveness relationships. We have used two publicly available third-party data sets to evaluate the performance of situation lattices in predicting situations and exploiting semantics of situations. By being compared to the classic machine learning techniques (such as Bayesian networks, decision trees, hidden Markov models, and conditional random fields), situation lattices have presented a better performance in predicting situations and a less requirement on the amount of training data needed. This proves situation lattices’ strength in representing and learning semantics of information.This work has produced two published journal papers, three internationally peer-reviewed top conference papers, a book chapter, and several other internationally peer-reviewed publications. It has also given me a deep insight into the problems of sensor fusion and programming in the presence of uncertainty.
- 2007 “Location in Pervasive Computing” Location-aware systems provide customised services or applications according to users’ locations. While much research has been carried out in developing models to represent location information and spatial relationships, it is usually limited to modelling simple environments. This paper proposes a unified space model for more complex environments (e.g., city plan or forest). This space model provides a flexible, expressive, and powerful spatial representation. It also proposes a new data structure – an integrated lattice and graph model – to express comprehensive spatial relationships. This structure not only provides multiple graphs at different abstraction levels, but it also collapses the whole map into smaller local graphs. This mechanism is beneficial in reducing the complexity of creating and maintaining a map and improving the efficiency of path finding algorithms.
- 2006 “Ontology Models in Pervasive Computing” Pervasive computing is by its nature open and extensible, and must integrate the information from a diverse range of sources. This leads to a problem of information exchange, so sub-systems must agree on shared representations. Ontologies potentially provide a well-founded mechanism for the representation and exchange of such structured information. A number of ontologies have been developed specifically for use in pervasive computing, none of which appears to cover adequately the space of concerns applicable to application designers. We compare and contrast the most popular ontologies, evaluating them against the system challenges generally recognized within the pervasive computing community. We identify a number of deficiencies that must be addressed in order to apply the ontological techniques successfully to next-generation pervasive systems.
