Daniele Riboni

A survey of context modelling and reasoning techniques

Development of context-aware applications is inherently complex. These applications adapt to changing context information: physical context, computational context, and user context/tasks. Context information is gathered from a variety of sources that differ in the quality of information they produce and that are often failure prone. The pervasive computing community increasingly understands that developing context-aware applications should be supported by adequate context information modelling and reasoning techniques. These techniques reduce the complexity of context-aware applications and improve their maintainability and evolvability. In this paper we discuss the requirements that context modelling and reasoning techniques should meet, including the modelling of a variety of context information types and their relationships, of situations as abstractions of context information facts, of histories of context information, and of uncertainty of context information. This discussion is followed by a description and comparison of current context modelling and reasoning techniques.

COSAR: hybrid reasoning for context-aware activity recognition

Human activity recognition is a challenging problem for context-aware systems and applications. Research in this field has mainly adopted techniques based on supervised learning algorithms, but these systems suffer from scalability issues with respect to the number of considered activities and contextual data. In this paper, we propose a solution based on the use of ontologies and ontological reasoning combined with statistical inferencing. Structured symbolic knowledge about the environment surrounding the user allows the recognition system to infer which activities among the candidates identified by statistical methods are more likely to be the actual activity that the user is performing. Ontological reasoning is also integrated with statistical methods to recognize complex activities that cannot be derived by statistical methods alone. The effectiveness of the proposed technique is supported by experiments with a complete implementation of the system using commercially available sensors and an Android-based handheld device as the host for the main activity recognition module.

OWL 2 modeling and reasoning with complex human activities

In recent years, there has been a growing interest in the adoption of ontologies and ontological reasoning to automatically recognize complex context data such as human activities. In particular, the Web Ontology Language (OWL) emerged as the language of choice, being a standard for the Semantic Web, and supported by a number of tools for knowledge engineering and reasoning. However, the limitations of OWL 1 in terms of expressiveness have been recognized in various fields, and important research efforts have been made to extend the language while preserving decidability of its OWL 1 DL fragment. The result of such work is OWL 2. In this paper we investigate the use of OWL 2 for modeling complex activities and reasoning with them. We show that the new language constructors of OWL 2 overcome the main limitations of OWL 1 for the representation of activities; OWL 2 axioms can be used to represent certain rules and rule-based reasoning previously demanded to hybrid approaches, with the advantage of having a unique semantics, avoiding potential inconsistencies. Then, we propose a system architecture showing the integration of a novel OWL 2 activity ontology and reasoning modules with distributed modules for sensor data aggregation and reasoning. The feasibility of our solution is shown by an extensive experimental evaluation with simulations of different intelligent environments.

Context-Aware Activity Recognition through a Combination of Ontological and Statistical Reasoning

In the last years, techniques for activity recognition have attracted increasing attention. Among many applications, a special interest is in the pervasive e-Health domain where automatic activity recognition is used in rehabilitation systems, chronic disease management, monitoring of the elderly, as well as in personal well being applications. Research in this field has mainly adopted techniques based on supervised learning algorithms to recognize activities based on contextual conditions (e.g., location, surrounding environment, used objects) and data retrieved from body-worn sensors. Since these systems rely on a sufficiently large amount of training data which is hard to collect, scalability with respect to the number of considered activities and contextual data is a major issue. In this paper, we propose the use of ontologies and ontological reasoning combined with statistical inferencing to address this problem. Our technique relies on the use of semantic relationships that express the feasibility of performing a given activity in a given context. The proposed technique neither increases the obtrusiveness of the statistical activity recognition system, nor introduces significant computational overhead to real-time activity recognition. The results of extensive experiments with data collected from sensors worn by a group of volunteers performing activities both indoor and outdoor show the superiority of the combined technique with respect to a solely statistical approach. To the best of our knowledge, this is the first work that systematically investigates the integration of statistical and ontological reasoning for activity recognition.

A probabilistic ontological framework for the recognition of multilevel human activities

A major challenge of ubiquitous computing resides in the acquisition and modelling of rich and heterogeneous context data, among which, ongoing human activities at different degrees of granularity. In a previous work, we advocated the use of probabilistic description logics (DLs) in a multilevel activity recognition framework. In this paper, we present an in-depth study of activity modeling and reasoning within that framework, as well as an experimental evaluation with a large real-world dataset. Our solution allows us to cope with the uncertain nature of ontological descriptions of activities, while exploiting the expressive power and inference tools of the OWL 2 language. Targeting a large dataset of real human activities, we developed a probabilistic ontology modeling nearly 150 activities and actions of daily living. Experiments with a prototype implementation of our framework confirm the viability of our solution.

Is ontology-based activity recognition really effective?

While most activity recognition systems rely on data-driven approaches, the use of knowledge-driven techniques is gaining increasing interest. Research in this field has mainly concentrated on the use of ontologies to specify the semantics of activities, and ontological reasoning to recognize them based on context information. However, at the time of writing, the experimental evaluation of these techniques is limited to computational aspects; their actual effectiveness is still unknown. As a first step to fill this gap, in this paper, we experimentally evaluate the effectiveness of the ontological approach, using an activity dataset collected in a smart-home setting. Preliminary results suggest that existing ontological techniques underperform data-driven ones, mainly because they lack support for reasoning with temporal information. Indeed, we show that, when ontological techniques are extended with even simple forms of temporal reasoning, their effectiveness is comparable to the one of a state-of-the-art technique based on Hidden Markov Models. Then, we indicate possible research directions to further improve the effectiveness of ontology-based activity recognition through temporal reasoning.

Loosely coupling ontological reasoning with an efficient middleware for context-awareness

Context-awareness in mobile and ubiquitous computing requires the acquisition, representation and processing of information which goes beyond the device features, network status, and user location, to include semantically rich data, like user interests and user current activity. On the other hand, when services have to be provided on-the-fly to many mobile users, the efficiency of reasoning with these data becomes a relevant issue. Experimental evidence has lead us to consider currently impractical a tight integration of ontological reasoning with rule based reasoning at the time of request. This paper illustrates a hybrid approach where ontological reasoning is loosely coupled with the efficient rule-based reasoning of a middleware architecture for service adaptation. While rule-based reasoning is performed at the time of service request to evaluate adaptation policies and reconcile possibly conflicting context information, ontological reasoning is mostly performed asynchronously by local context providers to derive non-shallow context information. A limited form of ontological reasoning is activated at the time of request only when essential for service provisioning.

Towards Highly Adaptive Services for Mobile Computing

The heterogeneity of device capabilities, network conditions and user contexts that is associated with mobile computing has emphasized the need for more advanced forms of adaptation of Internet services. This paper presents a framework that addresses this issue by managing distributed profile information and adaptation policies, solving possible conflicts by means of an inference engine and prioritization techniques. The profile information considered in the framework is very broad, including user preferences, device and network capabilities, and user location and context. The framework has been validated by experiments on the efficiency of the proposed conflict resolution mechanism, and by the implementation of the main components of the architecture. The paper also illustrates a specific testbed application in the context of proximity marketing.

Hybrid reasoning in the CARE middleware for context awareness

The Context Aggregation and REasoning (CARE) middleware aims at supporting context-aware adaptation of internet services in a mobile computing environment. Context awareness requires the acquisition, representation and processing of information that goes beyond raw context data – like device features, network status and user location – to include semantically rich data such as the current activity and interests of users. Representing and reasoning with the latter class of data require the use of ontologies and ontological reasoning. It is well known that reasoning with ontologies poses significant performance issues. The CARE hybrid reasoning mechanism is based on a loose interaction between ontological reasoning and efficient reasoning in a restricted logic programming language. In this paper we illustrate the hybrid reasoning approach adopted by CARE and report the extensive experimental results on ontology-based context reasoning that support our approach.

MIMOSA: context-aware adaptation for ubiquitous web access

The ubiquitous computing scenario is characterized by heterogeneity of devices used to access services, and by frequent changes in the user’s context. Hence, adaptation according to the user’s context and the used devices is necessary to allow mobile users to efficiently exploit Internet-based services. In this paper, we present a distributed framework, named MIMOSA, that couples a middleware for context-awareness with an intermediary-based architecture for content adaptation. MIMOSA provides an effective and efficient solution for the adaptation of Internet services on the basis of a comprehensive notion of context, by means of techniques for aggregating context data from distributed sources, deriving complex contextual situations from raw sensor data, evaluating adaptation policies, and solving possible conflicts. The middleware allows programmers to modularly build complex adaptive services starting from simple ones, and includes tools for assisting the user in declaring her preferences, as well as mechanisms for detecting incorrect system behaviors due to a wrong choice of adaptation policies. The effectiveness and efficiency of MIMOSA are shown through the development of a prototype adaptive service, and by extensive experimental evaluations.