Showing papers by "Yolanda Blanco-Fernández published in 2009"

TV program recommendation for groups based on muldimensional TV-anytime classifications

Abstract: The advent of Digital TV and Personal Digital Recorders promise to change the way people watch TV. The higher efficiency of digital coding will lead to increasing the number of contents offered to the user, demanding automatic tools for content recommendation. In the other hand, digital recorders will permit a non-linear consumption model, enabling the creation of (automatic) personalized schedules that combine the appealing contents for a specific user or group of users. This paper presents an approach to content recommendation for groups of people, based on TV-Anytime descriptions of TV contents and semantic reasoning techniques.

English to Spanish translation of signboard images from mobile phone camera

Abstract: We propose a whole architecture for English to Spanish translation of the texts present on JPEG natural scene images taken with a mobile phone camera. We detect the text using the frequency information of the DCT coefficients, binarize it using a clustering-based algorithm, recognize it by the use of an OCR algorithm and translate and phonetically transcribe it from English to Spanish. The result is a useful, simple, affordable and robust system that can handle problems like lighting distortion, out of focus, low resolution and foreground-background color variations in a very short amount of processing time, which makes its implementation very attractive on portable devices.

Receiver-side semantic reasoning for digital TV personalization in the absence of return channels

Abstract: Experience has proved that interactive applications delivered through Digital TV must provide personalized information to the viewers in order to be perceived as a valuable service. Due to the limited computational power of DTV receivers (either domestic set-top boxes or mobile devices), most of the existing systems have opted to place the personalization engines in dedicated servers, assuming that a return channel is always available for bidirectional communication. However, in a domain where most of the information is transmitted through broadcast, there are still many cases of intermittent, sporadic or null access to a return channel. In such situations, it is impossible for the servers to learn who is watching TV at the moment, and so the personalization features become unavailable. To solve this problem without sacrificing much personalization quality, this paper introduces solutions to run a downsized semantic reasoning process in the DTV receivers, supported by a pre-selection of material driven by audience stereotypes in the head-end. Evaluation results are presented to prove the feasibility of this approach, and also to assess the quality it achieves in comparison with previous ones.

Spontaneous interaction with audiovisual contents for personalized e-commerce over Digital TV

Abstract: The development of the Interactive Digital TV technologies has the potential to open new possibilities for e-commerce, linked to the broadcasting of audiovisual contents. To cater for the advertising needs, the early initiatives are resorting to the techniques traditionally employed by the television industry, which have proven deficiencies related to targeting and viewers' comfort. In response to that, we have developed a new advertising model, based on identifying products semantically related to the things that draw the viewer's attention on the screen. Thereupon, a personalization engine selects the products which are potentially interesting for the viewer, and assembles interactive services that provide him/her with tailor-made commercial functionalities. This paper provides guidelines on how to support the proposed model over the technological basis of the modern Digital TV receivers (either domestic or mobile ones), and describes a sample scenario of personalized advertising.

Methodologies to evolve formal specifications through refinement and retrenchment in an analysis–revision cycle

Abstract: The development of requirement specifications is done by accumulating knowledge about the desired systems in a progressive manner. This process can be supported by an analysis–revision cycle, in which the analysis phase checks the correctness of a given specification, and the revision phase modifies it, in case some problems are detected. To date, the analysis and revision activities have been typically considered in isolation, resulting in ineffective support to the stakeholders’ work. In response to that, this article introduces methodologies to conduct an interactive and integrated approach, grounded on the formalization of two basic types of evolutions (refinements and retrenchments) over multi-valued specification and modeling formalisms. Evaluation results are included to show that this approach can indeed help the stakeholders identify and clarify requirements through different stages of development.

Broadcasting and personalization of user-generated contents in DVB-H mobile networks

Abstract: During the last years, we have witnessed the boom of the digital market due to the proliferation of emergent audiovisual services and the increasing number of broadband networks. In this scenario, users insistently demand innovative services for exchanging and sharing their own audiovisual contents. In order to meet these needs, in this paper, we propose a system that broadcasts user-generated audiovisual contents for handheld devices in a mobile network based on the DVB-H broadcasting standard. Besides, our system offers diverse value-added services to these new active users, such as: (1) annotation, sharing and personalized distribution of audiovisual contents, (2) multi modal access, via Web or by client applications running locally in the handheld device, and (3) exploitation of return channels to transmit interactive contents that enhance the user’s experience. To achieve these goals, our system adopts well-known technologies for broadcasting and semantic annotation of audiovisual contents, as well as emergent technology from Web 2.0 and Semantic Web. We have carried out tests involving a group of students from the University of Vigo, who were satisfied with the personalization capabilities offered by our TV system for mobile settings.

Automatic Generation of Mashups for Personalized Commerce in Digital TV by Semantic Reasoning

Abstract: The evolution of information technologies is consolidating recommender systems as essential tools in e-commerce. To date, these systems have focused on discovering the items that best match the preferences, interests and needs of individual users, to end up listing those items by decreasing relevance in some menus. In this paper, we propose extending the current scope of recommender systems to better support trading activities, by automatically generating interactive applications that provide the users with personalized commercial functionalities related to the selected items. We explore this idea in the context of Digital TV advertising, with a system that brings together semantic reasoning techniques and new architectural solutions for web services and mashups.

Avoiding Fake Neighborhoods in e-Commerce Collaborative Recommender Systems: A Semantic Approach

Abstract: Recommender systems are very useful tools inapplication domains that suffer from information overload,offering the users suggestions they may be interested in.Owing to its business interest, e-commerce has become amajor domain in this research field, since identifying thoseproducts that the users will appreciate could increase users’consumption. However, current e-commerce recommendersystems overlook some implications of the great diversity ofproducts and services available in the market, giving rise toform fake neighborhoods in collaborative filtering strategies.In this paper, we propose applying semantic reasoning techniquesto solve this problem, thus improving, qualitativelyand computationally, the recommendation process.

Entering information about medication intake in standard Electronic Health Records from the networked home

Abstract: Electronic Health Records (EHR) are a crucial element towards the implantation of information technologies in healthcare. One of the goals pursued with these artifacts is to prevent medicine misuse, for which EHR standards define fields to record medical prescriptions and medication regimens. Unfortunately, the information stored in an EHR about how and when the patient does take his/her medicines is most often imprecise and incomplete, which implies severe health risks and brings down the benefits of technology. There exist solutions to get accurate records from inpatient settings (i.e. when the patient is treated in hospital), but not from contexts of daily life (e.g. when the patient takes medicines in home or at work) even though these are breeding ground for medication misuse. In this paper, we present an approach to fill in this gap, building on a system that monitors medicine intake from within a residential network, and relying on European standards for the storage and exchange of health-related information.

Procedures and algorithms for continuous integration in an agile specification environment

Abstract: One of the main ideas of agile development is to perform continuous integration, in order to detect and resolve conflicts among several modular units of a system as soon as possible. Whereas this feature is well catered for at the level of programming source code, the support available in formal specification environments is still rather unsatisfactory: it is possible to analyze the composition of several modular units automatically, but no assistance is given to help modify them in case of problems. Instead, the stakeholders who build the specifications are forced to attempt manual changes until reaching the desired functionality, in a process that is far from being intuitive. In response to that, this paper presents procedures and algorithms that automate the whole process of doing integration analyses and generating revisions to solve the diagnosed problems. These mechanisms serve to complete an agile specification environment presented in a previous paper, which was designed around the principle of facilitating the creative efforts of the stakeholders.

Semantic Reasoning and Mashups: An Innovative Approach to Personalized E-Commerce in Digital TV

Abstract: The potential of Digital TV for e-commerce remains heavily underexploited, mainly because there are no systematic approaches to the provision of applications to browse information about the advertised items, to purchase them online, etc. We present a procedure to automatically compose interactive applications that provide personalized commercial functionalities to the users, gathering contents from multiple sources and with a back-end of semantic web services. The procedure is driven SWRL rules and similarity metrics based on semantic reasoning.

How to Overcome Stumbling Blocks of Traditional Personalization Paradigms

Abstract: N owadays, users are exposed to an overwhelming amount of information in several application domains. Recommender systems fight such an overload by selecting the products which are more appealing to each user, according to his personal preferences or needs. Current personalization techniques are based on more or less sophisticated syntactic methods which miss a lot of knowledge during the elaboration of the recommendations. In this paper, we propose an approach that effectively overcomes the drawbacks of the existing personalization techniques by resorting to reasoning mechanisms inspired in Semantic Web technologies. Such a reasoning provides recommender system with extra knowledge about the user’s preferences, thus favoring more accurate personalization processes.