Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Related Work
The Prototype System Overview
Conclusion
References

Scalable and Personalised Broadcast Service

Profile image of Marie-Luce BourguetMarie-Luce Bourguet

Abstract

An aspect of the European IST SAVANT (Synchronised and Scalable Audio Visual content Across NeTworks) project is the personalisation of interactive TV systems combining broadcast programmes with additional content transmitted via the Internet. This paper describes scalability by selection of service components within the available services according to user preferences. This service adaptation is based on a developed metadata model. The personalisation techniques used in the first SAVANT prototype were demonstrated at IFA 2003 in Berlin, based on a news scenario. This demonstration showed content scalability by using a TV, a tablet PC and a PDA as display devices in addition to recommendations and personalisation by the selection of appropriate service components.

Figures (7)
Figure 2: Topics contents page of the Archive tab in the News Manager cq ser 2, a married man with two children and a niversity education in his forties, who lives in erlin and has a leading position in a bank, was haracterised as being interested in the latest ews, mostly in national issues in politics, ulture and art. Since he has a family he follows 1 social issues in German politics, while his interest in Israel is decreasing. As he is usually rather busy, he has no time for reading background information and prefers watching news summaries. 7 OWE ie @
Figure 2: Topics contents page of the Archive tab in the News Manager cq ser 2, a married man with two children and a niversity education in his forties, who lives in erlin and has a leading position in a bank, was haracterised as being interested in the latest ews, mostly in national issues in politics, ulture and art. Since he has a family he follows 1 social issues in German politics, while his interest in Israel is decreasing. As he is usually rather busy, he has no time for reading background information and prefers watching news summaries. 7 OWE ie @
Figure 3: Applying personalisation in the News Manager for User 1. Clicking on one of the user icons at the top right allows the personalisation of the content lists as if one of the predefined users had logged in.
Figure 3: Applying personalisation in the News Manager for User 1. Clicking on one of the user icons at the top right allows the personalisation of the content lists as if one of the predefined users had logged in.
Figure 4: Recommendations for User 2 AS well aS prioritizing topics and individual news items, the personalisation system also builds recommendations according to user profiles. Figure 4 shows the “Empfehlung” (Recommendations) page for User 2. For example, the “Gesundheitsreform” (Health reform) article now appears at the top of the list. This is a national social politics issue, which User 2 is very likely to be interested in. The difference between personalisation and recommendation is that recommendations only include the ranked list of content items that the user is likely to be interested in, while personalised pages include all content items, but place the user’s “favourites” at the top of the list. This helps to make the list more manageable and to reduce _ information overload. It would also be possible to implement a threshold value (ie. minimum interest level or maximum number of items), which is used to limit the number of items displayed. This would benefit a user who has a large number of interests. For example, a user could choose to view only the top 5 matches on gts: se sere ese ee ce Be we Se es
Figure 4: Recommendations for User 2 AS well aS prioritizing topics and individual news items, the personalisation system also builds recommendations according to user profiles. Figure 4 shows the “Empfehlung” (Recommendations) page for User 2. For example, the “Gesundheitsreform” (Health reform) article now appears at the top of the list. This is a national social politics issue, which User 2 is very likely to be interested in. The difference between personalisation and recommendation is that recommendations only include the ranked list of content items that the user is likely to be interested in, while personalised pages include all content items, but place the user’s “favourites” at the top of the list. This helps to make the list more manageable and to reduce _ information overload. It would also be possible to implement a threshold value (ie. minimum interest level or maximum number of items), which is used to limit the number of items displayed. This would benefit a user who has a large number of interests. For example, a user could choose to view only the top 5 matches on gts: se sere ese ee ce Be we Se es
Figure 5: News Manager as viewed on a PDA. Figure 5 shows a PDA version of the News Manager. The user interface is kept as similar as possible to the main TV interface (for example the order and colours of the tabs on top of the screen are the same). However, access to the news items by category, topic or programme is obtained via the navigation screen shown in Figure 5. The introduction of a navigation screen overcomes the problem of reduced space availability on the small screen of a PDA.
Figure 5: News Manager as viewed on a PDA. Figure 5 shows a PDA version of the News Manager. The user interface is kept as similar as possible to the main TV interface (for example the order and colours of the tabs on top of the screen are the same). However, access to the news items by category, topic or programme is obtained via the navigation screen shown in Figure 5. The introduction of a navigation screen overcomes the problem of reduced space availability on the small screen of a PDA.
Figures 6 and 7 show the PDA version of the topics contents page within the News Manager’s archive tab, the TV and Tablet PC version of which can be seen in Figure 2. All images have been removed to save screen space. Similarly, video and items to be played on the PDA are streamed to it in a reduced size MPEG- 4 format. The streaming also means that the video and audio items do not have to be stored on the PDA itself. Currently these alternative video formats are sent as part of the broadcast, although future work on this project will provide a transcoding system within the HMS.
Figures 6 and 7 show the PDA version of the topics contents page within the News Manager’s archive tab, the TV and Tablet PC version of which can be seen in Figure 2. All images have been removed to save screen space. Similarly, video and items to be played on the PDA are streamed to it in a reduced size MPEG- 4 format. The streaming also means that the video and audio items do not have to be stored on the PDA itself. Currently these alternative video formats are sent as part of the broadcast, although future work on this project will provide a transcoding system within the HMS.

Related papers

Personalisation technologies for the digital TV world
Barry Smyth

2000

Abstract. The information overload problem is becoming a serious issue on the Internet and users are finding it increasingly difficult to quickly locate the right information at the right time. Content personalisation techniques may provide a useful solution by enabling information services to respond to the implicit and explicit preferences of individual users.

View PDFchevron_right
Semantics-based framework for personalized access to TV content: the iFanzy use case
Lora Aroyo

The Semantic Web, 2007

View PDFchevron_right
Advanced IPTV Services Personalization Through Context-Aware Content Recommendation
Hassnaa Moustafa

IEEE Transactions on Multimedia, 2012

The advances in Internet Protocol Television (IPTV) technology enable new user-centric and interactive TV model, in which context-awareness is promising in making users' interaction with the TV dynamic and transparent. This paper considers user-centric personalized IPTV services applying context-awareness. We present a solution for enriched IPTV services personalization introducing context-awareness on top of IPTV architecture to gather different information on the user and his environment allowing each user to be distinguished by the system in a unique and real-time manner. Based on the different context information gathered, a novel solution for content recommendation is presented allowing to customize IPTV content according to the context of each user and his environment and hence guaranteeing better users' experience. We implemented the proposed solution on top of an IPTV platform considering the NGN IPTV architecture as a proof of concept and as a mean to evaluate the performance.

View PDFchevron_right
Handling multiple channel video data for personalized multimedia services: A case study on soccer games viewing
Nikolaos Papaoulakis

2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops), 2011

Personalization is undoubtedly present in today's pervasive and ubiquitous environments and tends to be an increasingly popular requirement in every technological aspect of the everyday life. When it comes to live multimedia services, however, there is still a lot to be done to satisfy the demanding user who wishes to view the most important parts of events that take place in parallel. In this paper, a service that allows users to personalize the provision of multimedia streaming services offered through broadcasting networks is described. The service is aimed at offering full personalization capabilities over traditionally broadcast oriented terminals such as TV sets and Set Top Boxes. Complete personalization can be achieved through analog TV or DVB broadcasts with the use of personal devices such as mobile phones by using IP connection for the return channel (RC) (DVBRC). A use case scenario featuring one example related to personalized viewing of two parallel athletic events (such as Champions League soccer matches) is described and used for the evaluation of a prototype implementation of the service.

View PDFchevron_right
Personal TVware: An Infrastructure to Support the Context-Aware Recommendation for Personalized Digital TV
Graça Bressan

International Journal of Computer Theory and Engineering, 2012

The coming of the Digital TV will bring a significant increase in the number TV programs offered by TV operators. Consequently, the user are facing it difficulty to find out the most interesting TV programs among the various options available. In this new scenario, the recommender systems stand out as a possible solution to the information overload problem. However, the current approaches to recommend content for Digital TV rarely considers the context during the recommendation process. Thus, this paper presents a software infrastructureentitled PersonalTVware-to support context-aware recommendation of TV programs. To validate the PersonalTVware, a context-aware recommender system was implemented as a concept proof. In order to evaluate the quality of the recommendation, a number of experiments have been conducted. The results indicate that consider both user's profile and context can provide better recommendations. Index Terms-Context-awareness, interactive digital TV, recommender systems, ubiquitous computing. applications. Luiz Gustavo Pacola Alves holds a M.Sc. in Electrical Engineering and B.Sc. in Computer Engineering from Polytechnic School of University of Sã o Paulo (EP-USP), Brazil. He has published academic papers on his main research areas which include Interactive Digital TV (metadata, middleware and applications), Context-Aware Computing and Collaborative Systems (CSCW). He worked as a researcher engineer at Laboratory of Computer Architecture and Network (LARC-USP) from 2002 to 2008. Since joining SAMSUNG Electronics in 2009 he has worked with broadcasters, consumer electronics manufacturers, software industries, universities and regulatory governmental agencies to establish technical standards for Brazilian Digital Television System, called SBTVD. Recently he has been focusing on collaboration on GINGA Test Suite specification, a collection of tests to drive the interoperability among the GINGA (SBTVD middleware based on NCL/Lua and Java technologies) implementers. Graç a Bressan got her PhD in Electronic Engineering (1986) at Polytechnic School of University of Sã o Paulo (EP-USP), Brazil. Nowadays, at the Computer Engineering Department at EP-USP, she teaches and develops research on Computer Network, Digital TV and Performance Analysis and has published articles and has oriented Msc and PhD degree students. Her current research interests includes Computer Networks and Digital TV focusing in the aspects of Distributed Systems, Distributed Middleware, QoS Mechanisms, Collaborative Virtual Environment, Middleware for Digital TV, Video-Conferencing, Modeling and Performance Analysis of Networks, and Application in Distance Education.

View PDFchevron_right
Context-Awareness for IPTV Services Personalization
Hassnaa Moustafa

Architectures, Applications, and Standards, 2012

TV and video services landscape is currently undergoing significant changes. Traditional TV broadcasting model is supplemented and often even replaced by digital content distribution services over the Internet. As a result of this trend, a range of services and contents available for users is rapidly expanding. As a side-effect, designing efficient user interfaces for discovering the content, as well as for manipulating associated interactive services, becomes more and more cumbersome. Pervasive computing and context-awareness principles seem to be promising for making user interaction with the system more seamless and fluid. This paper discusses context-awareness as a new trend for services personalization, defining the meaning of "context" and different contextual data relevant for IPTV (Internet Protocol Television) services. A novel architecture for unified storage and processing situational data in IPTV service domain is presented, together with discussion of its implementation issues and validation by testbed experiments. The UP-TO-US context-aware architecture is designed for seamless monitoring of user's environment (including networks and terminals), interpreting user's requirements and making the user's interaction with the TV system dynamic and transparent. Consequently, content personalization is achieved, matching the user's needs and current state of his surrounding environment.

View PDFchevron_right
IPTV Services Personalization Using Context-Awareness
Hassnaa Moustafa

The advances in IPTV (Internet Protocol Television) technology enable a new user-centric and interactive TV model, in which context-awareness is promising in making the user's interaction with the TV dynamic and transparent. Our research interest is how to achieve user-centric personalized IPTV services applying context-awareness. In this paper, we present a solution for IPTV services personalization introducing context-awareness on top of the IPTV architecture on one hand to gather different information about the user and his environment and on the other hand allowing each user to be distinguished to the system in a unique manner. Consequently, IPTV services personalization is achieved in a real-time manner for each user. We implemented the proposed solution on top of an IPTV platform considering the NGN IPTV architecture as a proof of concept and as a means to evaluate the performance. Povzetek: Članek opisuje prilagajanje televizije IP posamičnim uporabnikom z uporabo konteksta.

View PDFchevron_right
Content personalization and adaptation for three-screen services
Harris Drucker

Proceedings of the 2008 international conference on Content-based image and video retrieval - CIVR '08, 2008

Three-screen services provide the right solution for consumers to access rich multimedia resources by any device, anytime and anywhere. In this paper, we describe a prototype system of content personalization and adaptation for three-screen services. The system continuously acquires content from TV broadcast feeds, indexes and adapts the content for users according to their interests defined in preference profiles. Automatically compiled segments of content can be rendered on a variety of devices that the customers prefer to facilitate a smoother video consuming experience. Simulation results show that the proposed content analysis modules, including shot boundary detection, anchorperson detection, and multimodal story segmentation are effective. The resulting personalized content is suitable for consumption on devices with limited input capabilities.

View PDFchevron_right
Personalized Digital Television
Markus Stolze

Springer eBooks, 2004

View PDFchevron_right
SenSee framework for personalized access to TV content
Lora Aroyo

Interactive TV: a Shared …, 2007

In this paper we present our framework, SenSee, designed to provide context-aware and personalized search that can be used to support multimedia applications in making content recommendations. Our primary demonstration application built upon the framework targets the growing digital television domain where we foresee an increasing need for user-adaptive functionality to counter the looming content explosion which will make current television zapping inadequate. Via our AJAX-based interface we show how different user contexts, such as location, time and audience, in combination with a standard user profile can improve the multimedia (TV content) consumption experience. In modeling the user (profile and context) SenSee exploits ontologies to express the semantics involved. We illustrate via experiments the influence of the user's current context and demonstrate the difference when we dis/enable the inclusion of different ontologies describing time, geographical, lexical and TV domain knowledge.

View PDFchevron_right

References (22)

  1. Ardissono, L, Faihe, Y (Editors). Proceedings of the 1st Workshop on Personalization in Future TV in conjunction with User Modeling 2001, Sonthofen, Germany, July, 2001.
  2. Ardissono, L, Buczak, A (Editors). Proceedings of the 2nd Workshop on Personalization in Future TV in conjunction with 2nd International Conference on Adaptive Hypermedia and Adaptive Web Based Systems, Malaga, Spain, May 2002.
  3. Ardissono, L, Goy, A, Petrone, G, Segnan, M, Torasso, P. Intrigue: Personalized Recommendation of Tourist Attractions for Desktop and Handset Devices. Applied AI: Special Issue on AI for Cultural Heritage and Digital Libraries, 17(8-9), pp. 687-714, 2003.
  4. Ardissono, L, Kobsa, A, Maybury, M (editors) Personalized Digital Television: Targeting Programs to Individual Viewers. Kluwer. (To Appear)
  5. Baeza-Yates, R. and Ribeiro-Neto, B. (1999). Modern Information Retrieval., Addison-Wesley.
  6. Chorianopoulos, K., Lekakos, G. and Spinellis, D. The Virtual Channel Model for Personalized Television. In [Masthoff et. al., 2003]
  7. Chuah, M. Reality Instant Messenger: The Promise of iTV Delivered Today. In [Ardissono & Buczak, 2002]
  8. Correia, N. and Peres, M. Design of a Personalisation Service for an Interactive TV Environment. In [Ardissono & Buczak, 2002].
  9. Cotter, P. and Smyth, B. PTV: Intelligent Personalised TV Guides. Proceedings of the 7 th National Conference on Artificial Intelligence, AAAI Press, pp 957-964, 2000.
  10. Dempski, K.L. Real Time Television Content Platform: Personalised Programming over Existing Broadcast Infrastructures. In [Ardissono & Buczak, 2002].
  11. Dimitrova, N, Zimmerman, J, Janevski, A, Agnihotri, L, Haas, N, & Bolle, R. Content Augmentation Aspects of Personalized Entertainment Experience. Proceedings of the Third Workshop on Personalization in Future TV in conjunction with User Modeling 2003, Johnstown, PA, June 2003. pp 42-51.
  12. Durand, G., Kazai, G., Rauschenbach, U., Wolf, P., Hemmje, M. and Lalmas, M. A metadata model supporting scaleable interactive TV services. Submitted to IEEE International Conference on Multimedia and Expo (ICME), 2004.
  13. ETSI TS 102 822-3-1: Broadcast and On-line Services: Search, select and rightful use of content on personal storage systems ("TV- Anytime Phase 1"), Part 3 Metadata, Sub-part 1: Metadata Schemas. 2002.
  14. ISO MPEG-7, Part 5 -Multimedia Description Schemes, ISO/IEC JTC1/SC29/WG11/N4242, 2001.
  15. ISO MPEG-21, Part 7 -Digital Item Adaptation, ISO/IEC JTC1/SC29/WG11/N5231, 2002.
  16. Kazasis, F.G., Moumoutzis, N., Pappas, N., Karanastasi, A. and Christodoulakis, S. Designing Ubiquitous Personalised TV- Anytime Services. Workshops proceedings of the 15th Conference on Advanced Information Systems Engineering (CAiSE '03), Klagenfurt/Velden, Austria, June, 2003.
  17. Masthoff, J, Griffiths, R & Pemberton, L (Editors). Proceedings of the European Conference on Interactive Television: from Viewers to Actors? Brighton, UK, April 2003.
  18. Maybury, M, Greiff, W, Boykin, S, Ponte, J, McHenry, C & Ferro, L. Personalcasting, Tailored Broadcast News. User Modeling and User-Adapted Interaction 14, 2004. pp 119-114
  19. Merialdo, B., Tak Lee, K., Luparello, D. and Roudaire, J. Automatic Construction of Personalised TV News Programs. In Proceedings of the Seventh ACM Conference on Multimedia, Orlando, Florida, pp 323-332, 1999.
  20. O'Sullivan, D, Smith, B, Wilson, D, McDonald, K, & Smeaton, A. Improving the Quality of the Personalized Electronic Program Guide. User Modeling and User-Adapted Interaction 14, 2004. pp 5-36.
  21. Rölleke, T. and Luebeck, R. and Kazai, G., The HySpirit Retrieval Platform, Demonstration, 2001, Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New Orleans, USA, pp 454.
  22. Zimmerman, J, Dimitrova, N, Agnihotri, L, Janevski, A & Nikolovska, L. Interface Design for MyInfo: a Personal News Demonstrator Combining Web and TV Content. Ninth IFIP

Related papers

Personalized and Ubiquitous Information Services for TV Programs
Fotis Kazasis

Workshop on Multimedia …, 2003

We present an overview of ongoing research, system design and middleware that has been implemented on top of a relational DBMS to provide advanced personalized information services in an integrated digital TV and Internet environment. The middleware provides automatic selection of programs or parts of programs based on users' preferences. It is compatible to the TV-Anytime Forum specifications for user and program metadata providing extended capabilities for information retrieval using the Extended Boolean model. Adaptation of preferences based on users' viewing histories is also supported as well as the integration of domain specific ontologies to metadata standards. The metadata are managed robustly by a relational dbms allowing concurrency, remote access and modification. The system design and implementation emphasizes the use of standards (like TV-Anytime, MPEG-7, XML) for interfacing with the open outside world. Video is accessed based on its content and delivered in a variety of delivering channels i ncluding TVs, PCs, mobiles and PDAs.

View PDFchevron_right
USING METADATA TO PROVIDE SCALABLE BROADCAST AND INTERNET CONTENT AND SERVICES
Marie-Luce Bourguet

Digital Media Processing for Multimedia Interactive Services - Proceedings of the 4th European Workshop on Image Analysis for Multimedia Interactive Services, 2003

The SAVANT project is developing scalability and synchronisation techniques for delivering multimedia content over a variety of broadcast and IP networks to a variety of user devices. This paper deals with the use of metadata standards such as MPEG-7 and MPEG-21 to drive the automatic adaptation and personalisation of scalable broadcast and Internet content and services.

View PDFchevron_right
Designing Ubiquitous Personalized TV-Anytime Services
Nick Lardo

2003

In this paper we present the design of an environment that offers personalized, ubiquitous information services in the emerging integrated world of the digital-TV and the Internet. This environment is based on extended TV sets with a large capacity disk and Internet connection. We present an architecture that integrates external service providers that provide extended information services about broadcasts with powerful retrieval, personalization and ubiquitous access capabilities. We assume that the metadata information about the content of the TV programs follows the TV-anytime Forum Metadata (TVAM) specifications. The architecture allows content based matching and/or retrieval based on the description of the broadcast or parts of the broadcast according to the interests of the viewers. The viewer has access to his/her "personal channel" any time not only from home, but also while on move. It is obvious that due to communication, storage and processing limitations of handy devices, it is not possible to access normal digital-TV content. Thus, special mechanisms that filter and appropriately adapt the content are necessary, in order to meet user's preferences and make its delivery and presentation feasible on the handy devices.

View PDFchevron_right
A context-aware architecture for IPTV services personalization
Hassnaa Moustafa

J. Internet Serv. Inf. Secur., 2013

TV and video services landscape is currently undergoing significant changes. Traditional TV broadcasting model is supplemented and often even replaced by digital content distribution services over the Internet. As a result of this trend, a range of services and contents available for users is rapidly expanding. As a side-effect, designing efficient user interfaces for discovering the content, as well as for manipulating associated interactive services, becomes more and more cumbersome. Pervasive computing and context-awareness principles seem to be promising for making user interaction with the system more seamless and fluid. This paper discusses context-awareness as a new trend for services personalization, defining the meaning of ”context” and different contextual data relevant for IPTV (Internet Protocol Television) services. A novel architecture for unified storage and processing situational data in IPTV service domain is presented, together with discussion of its implementation...

View PDFchevron_right
Intelligent broadcasting system and services for personalized semantic contents consumption
Yong Man Ro

Expert Systems With Applications, 2006

Currently, digital broadcasting tends to personalize the TV watching environment by offering services that can adapt to viewer preferences. In this paper, an intelligent broadcasting system for enhanced personalized-services, based on the semantics of broadcasting contents, is proposed. To implement the system, the MPEG-7 and TV-Anytime Forum (TVAF), as well as agent technology, are employed. For content-level services, real-time content filtering, personalized video skimming, and content-based retrieval using audio characteristic are implemented. To verify the usefulness of the proposed system, we demonstrate it with a test-bed on which content-level personalized services are implemented 1 .

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved