Abstract
The Web is rapidly becoming the prime medium for human socialization. The resources that enable that process (social web sites, blogs, media objects, etc.) present growing complexity and, collectively, weave an ever more intricate web of relationships. Current technology for declaring those relationships is predominantly implicit, ambiguous and semantically poor. As a consequence, their automatic assessment is complex and error prone, preventing the satisfaction of users' needs such as effective semantic searches. To address these limitations, whilst enabling the explicit declaration of semantically unambiguous relationships between digital resources, a solution employing structured semantic descriptors and ontologies was conceived, based on MPEG-21. This paper explains the functioning of the devised mechanism, and goes beyond that, into the definition of two novel employment venues for it, at the service of two real-world usage scenarios. These demonstrate the mechanism's added value as a powerful alternative for the semantically aware interconnection of web resources, and highlight the increased QoE that said mechanism enables.

Abstract
The Web is rapidly becoming the prime medium for human socialization. As it evolves towards an information-centric operation, it records everything and forgets nothing, assuming that every online resource disclosed by people (photos, posts, multimedia files, etc.) is permanently valid and is to be stored forever. However, throughout their lives, people tend to change, both in their habits as well as in their views and opinions. In many situations, as the years go by, information released loses relevance or people may decide they no longer want others to access information they have previously published. The work presented in this paper strives for a new information persistence paradigm, whereby the enforcement of "digital forgetting" is implemented over an information-centric model for the Internet. The defined solution enables the definitive elimination of digital objects, either on-demand or on a pre-scheduled basis, and, hence, their "forgetting." The solution, conceived within the framework of the European project CONVERGENCE, is based on the employment of metadata descriptions about resources, which unambiguously identify their rightful owners. This additional data is efficiently bound to the resource through the use of an extended version of the MPEG-21 Digital Item specification, and its prescriptions are enforced by CONVERGENCE's distributed provisions.

Abstract

Abstract
Context recognition is an indispensable functionality of context-aware applications that deals with automatic determination and inference of contextual information from a set of observations captured by sensors. It enables developing applications that can respond and adapt to user's situations. Thus much attention has been paid to developing innovative context recognition capabilities into context-aware systems. However, some existing studies rely on wearable sensors for context recognition and this practice has limited the incorporation of contexts into practical applications. Additionally, contexts are usually provided as low-level data, which are not suitable for more advanced mobile applications. This article explores and evaluates the use of smartphone's built-in sensors and classification algorithms for context recognition. To realize this goal, labeled sensor data were collected as training and test datasets from volunteers' smartphones while performing daily activities. Time series features were then extracted from the collected data, summarizing user's contexts with 50% overlapping slide windows. Context recognition is achieved by inducing a set of classifiers with the extracted features. Using cross validation, experimental results show that instance-based learners and decision trees are best suitable for smart phone -based context recognition, achieving over 90% recognition accuracy. Nevertheless, using leave one -subject-out validation, the performance drops to 79%. The results also show that smartphone's orientation and rotation data can be used to recognize user contexts. Furthermore, using data from multiple sensors, our results indicate improvement in context recognition performance between 1.5% and 5%. To demonstrate its applicability, the context recognition system has been incorporated into a mobile application to support context-aware personalized media recommendations.

Abstract
The present phenomenon of technology convergence is blurring away the frontiers between the Internet and the TV, operating a shift on the way TV is consumed. TV viewers have now access to a huge selection of TV programming as well as online contents, either previously broadcasted or natively produced for the Internet. This reality creates new necessities whilst opening new opportunities for the creation of services capable of filtering this information and presenting the user with the most relevant content. This article describes an innovative hybrid strategy for delivering recommendations of TV content to individual users. It was developed specifically for the TV entertainment services of hotels, but it can be applied to any multimedia consumption service. Without requiring users to explicitly rate the programs they have watched, it is still able to recommend similar programs to similar users. It adopts an improved Pearson correlation method to establish similarities between different users, comparing profiles that have been automatically generated based on the user viewing history. It builds a predicted user profile, which is then used within a content-based approach to generate recommendations.

Abstract
Media content recommendations for a mobile user based on his changing contextual preferences, otherwise called context-aware media recommendations, constitute a very important challenge. Context-aware media recommendation systems take context information such as user preferences, activities, time, location, device, and network capabilities as inputs for media recommendations, whereas the traditional recommendation systems use only user preferences in the form of ratings to deliver media recommendations. This paper presents a generic high-level architecture of context-aware recommendations, discussing its key techniques and solutions, which are based on context acquisition, recognition, and representations, using MPEG-21 and ontology model, and a contextual user profiling process, as well as MPEG-7 for media description model and media presentation adaptation.