Cristina Frà

A comprehensive context modeling framework for pervasive computing systems

Context management in pervasive computing environments must reflect the specific characteristics of these environments, e.g. distribution, mobility, resource-constrained devices, or heterogeneity of context sources. Although a number of context models have been presented in the literature, none of them supports all of these requirements to a sufficient extent at the same time. In this paper, we present a comprehensive and integrated approach for context modeling in pervasive computing environments. It combines the advantages of existing approaches and addresses the need for supporting effective software development. The proposed context model follows an ontology-based approach and has three layers of abstraction, i.e. conceptual layer, exchange layer, and functional layer. This layered approach facilitates a model-driven development of context-aware applications. Throughout the paper we compare our solution with the related work in order to clearly demonstrate why we needed to develop a new context management framework and where we have adopted existing ideas.

ContextML: A light-weight context representation and context management schema

Context representation is a fundamental process in developing context aware systems for the pervasive world. We present a light weight XML based context representation schema called ContextML in which context information is categorized into scopes and related to different types of entities (e.g. user, device). The schema is also applied for encoding management messages in order to allow for a flexible framework supporting gradual plug & play extendibility and mobility. ContextML is tailored to be used for REST-based communication between the framework components. Explanation of the schema is provided with the help of real world examples. Moreover, the European C-CAST testbed is introduced, embracing a variety of context providers and application domains.

A Context Query Language for Pervasive Computing Environments

This paper identifies requirements for querying and accessing context information in mobile and pervasive computing environments. Furthermore it studies existing query languages showing that they satisfy only a subset of these requirements or cover some of them only to a limited extent. A new context query language is presented to overcome these shortcomings, improving the state of the art in several respects: heterogeneous representations of context information, definition of complex filtering mechanisms, elaborate aggregation functions and ontology integration, all in one language.

A Requirements-Driven Approach Towards Decentralized Social Networks

A new generation of distributed social networks is promising to give back users full control over their personal information as shared in private and business life. However, there are many aspects to this control, such as information ownership, access to third parties and limited persistence. This paper compares various existing solutions against an analytically elaborated list of user requirements. Based on this comparison, we also present a comprehensive and integrated approach to overcome the major issues outlined for the existing solutions, including first experiences of applying the reference implementation.

Context Grouping Mechanism for Context Distribution in Ubiquitous Environments

Context distribution is a key aspect for successful applications within mobile and ubiquitous computing environments. In such environments, context information is acquired by several and multiple context sensors distributed over the environment. Applications collect and react to these data, according to predefined adaptation mechanisms. The success of these mechanisms depends on the availability of context information, which is disseminated over the network. However, in practice, only a fraction of the observable context information is required by the adaptation mechanisms. Moreover, for privacy reasons, it is important to delimitate a scope for context dissemination. In this work we address these issues by proposing a context grouping mechanism which allows the definition of groups based on the context characteristics. Each group is defined by these characteristics and delimitate a given context information set that can be distributed among group members. This approach of context grouping acts as a two-fold mechanism. On the one hand, it controls and organizes context distribution over a peer-to-peer network. On the other hand, it proposes a primary and low-level privacy mechanism for context distribution, which is an important aspect influencing context distribution.

High level context query processing: An experience report

Pervasive applications want to describe in simple ways which context information they need about users, and be notified when low level context matches specified constraints defined by semantic expressions. In this paper we report our experience while implementing our Context Query Language and using it in a real context framework to support mobile context-aware applications in two European-funded projects. Our experience has shown that both the language design and its implementation are suitable to support complex asynchronous high-level context notification requirements from applications.

Towards a smart retail environment

Over the last decades, the advancements in digital technologies pervasiveness increasingly transformed regular physical spaces in smart ambients, where humans and objects are seamlessly hyper-connected. Large screens are commonly part of these smart environments, although most of these displays are single and not personalized installations that provide general contents and features, regardless the actual users interacting with them. This work presents challenges and opportunities of our interactive system that, applied to a smart retail environment, takes advantage of technologies that are already familiar to shoppers (smartphones, smart watches, touch screens, etc.), offering new interaction methods to virtually present to users personalized products information.

Context data management: an architectural framework for context-aware services

Mobile devices are equipped with increasing processing power and sensing capabilities, and mobile services can benefit from these features to provide a more personalized and context-aware experience to final users. To efficiently collect and deliver context information, a proper architecture is required, where heterogeneous context information can be processed to provide higher-level context information, context data are represented uniformly, and applications can process context data with high-level queries. This paper fulfils this goal of interoperability and domain independence by defining a framework for context data management relying on open standards (XMPP and REST), acting as an enabler for third-party context-aware applications; other main novelties of our work are the definition of a ContextML for standard context data representation, and a Context Query Language (CQL) to access context information based on high-level data filtering.

Personalized interaction on large displays: the StreetSmart project approach

The StreetSmart Project develops information services that integrate multiple (touch and touchless) interaction paradigms on personal devices and large public displays. It exploits personalization techniques in order to offer new engaging user experiences involving large amounts of multimedia contents.

SPECTRA: A SPEech proCessing plaTform as smaRtphone Application

In this paper, an Android SPEech proCessing plaTform as smaRtphone Application (SPECTRA) is presented. Such application, developed by the authors, has three main functions: i) Gender Recognition (GR), ii) Speaker Recognition (SR) and iii) Language Recognition (LR). All these recognition functions are performed simultaneously by using unsupervised Support Vector Machine (SVM) classifiers. An innovative point of this paper lies in the automatic re-training of the employed SVMs which are able to dynamically update themselves when a (new) audio from a (new) speaker is provided. This allow to build more robust classifiers, which results in better recognition performances. In terms of accuracy, the GR reaches about 98% of correct classifications, SR performs around 80% while LR shows an accuracy of about 74%.