A Two-Stage Composition Method for Danger-Aware Services Based on Context Similarity

Abstract

SUMMARYContext-aware systems detect user's physical and social contexts based on sensor networks, and provide services that adapt to the user accordingly. Representing, detecting, and managing the contexts are important issues in context-aware systems. Composition of contexts is a useful method for these works, since it can detect a context by automatically composing small pieces of information to discover service. Dangeraware services are a kind of context-aware services which need description of relations between a user and his/her surrounding objects and between users. However when applying the existing composition methods to danger-aware services, they show the following shortcomings that (1) they have not provided an explicit method for representing composition of multi-user' contexts, (2) there is no flexible reasoning mechanism based on similarity of contexts, so that they can just provide services exactly following the predefined context reasoning rules. Therefore, in this paper, we propose a two-stage composition method based on context similarity to solve the above problems. The first stage is composition of the useful information to represent the context for a single user. The second stage is composition of multi-users' contexts to provide services by considering the relation of users. Finally the danger degree of the detected context is computed by using context similarity between the detected context and the predefined context. Context is dynamically represented based on two-stage composition rules and a Situation theory based Ontology, which combines the advantages of Ontology and Situation theory. We implement the system in an indoor ubiquitous environment, and evaluate the system through two experiments with the support of subjects. The experiment results show the method is effective, and the accuracy of danger detection is acceptable to a danger-aware system.

A Flexible and Accurate Reasoning Method for Danger-Aware Services Based on Context Similarity from Feature Point of View

“…context level. Therefore, we have proposed a composition based method to integrate pieces of useful information automatically compose contexts for providing context-aware services in [25]. In the method, firstly, pieces of useful information compose together to represent contexts.…”

“…Definition 1: Single-User Context In this paper, same with [25] the information to be used to adapt a single user, including the user's information, related surrounding objects, relation between the user and objects, and environment factors, is called single-user context, which is a 4-tuple and can be described as follows.…”

“…In this paper, same with [25] a multi-user context contains more than one user, all the related surrounding objects and environment factors. For the simplicity of discussion, we mainly focus on the situation including two users.…”

“…However, the above method proposed in [25] is not so accurate in some cases, since it considers only basic knowledge by taxonomy similarity but it cannot account for feature similarity when computing similarity as discussed in Sect. 1 and 2.…”

“…To solve the above problems, some ontology-based methods [22], [23], [25] have been proposed by computing similarity based on basic knowledge in ontology. These methods sometimes help with specification and detection of dangers, but they are not always effective and accurate, since the similarity is computed from only basic knowledge, e.g.…”