Publications

Public Deliverables

D1.1 State-of-the-art, Stakeholder Needs, Application Scenarios
D1.3 PROTAGE Methodology Handbook
D7.2 Dissemination Master Plan
Agents: A Quick State of the Art
Agents: A Deeper State-of-the-Art Analysis - Part I
Potential of Agents in Digital Preservation

Project Video

Video of PROTAGE First Prototype for demonstrating its features

Project Flyer, Poster and Leaflet

PROTAGE Flyer
PROTAGE Poster
PROTAGE Leaflet

Presentations

Journal Papers

  • Josep Lluis de la Rosa, Nicolás Hormazábal, Silvana Aciar, Gabriel Lopardo, Albert Trias, and Miquel Montaner, A Negotiation Style Recommender Based on Computational Ecology in Open Negotiation Environments, To appear in IEEE Transactions on Industrial Electronics, 2010.

    Abstract: The system described herein represents the first example of a recommender system in digital ecosystems where agents negotiate services on behalf of small companies. The small companies compete not only with price or quality, but with a wider service-by-service composition by subcontracting with other companies. The final result of these offerings depends on negotiations at the scale of millions of small companies. This scale requires new platforms for supporting digital business ecosystems, as well as related services like open-id, trust management, monitors and recommenders. This is done in the Open Negotiation Environment (ONE), which is an open-source platform that allows agents, on behalf of small companies, to negotiate and use the ecosystem services, and enables the development of new agent technologies. The methods and tools of cyber engineering are necessary to build up Open Negotiation Environments that are stable, a basic condition for predictable business and reliable business environments. Aiming to build stable digital business ecosystems by means of improved collective intelligence, we introduce a model of negotiation style dynamics from the point of view of computational ecology. This model inspires an ecosystem monitor as well as a novel negotiation style recommender. The ecosystem monitor provides hints to the negotiation style recommender to achieve greater stability of an open negotiation environment in a digital business ecosystem. The greater stability provides the small companies with higher predictability, and therefore better business results. The negotiation style recommender is implemented with a simulated annealing algorithm at a constant temperature, and its impact is shown by applying it to a real case of an open negotiation environment populated by Italian companies.

  • Xiaolong Jin, Jianmin Jiang, and Geyong Min, PROTAGE: Towards Computerized Digital Preservation via Intelligent Agent Based Approaches, To appear in International Journal of Digital Curation, 2010.

    Abstract: The explosively growing amount of digital information results in pressing demands to transfer digital objects from active IT systems to digital repositories, libraries, and archives for long-term preservation. However, existing strategies of digital preservation are labour intensive and often require specialist skills. In order to meet the preservation demands of immense digital information, it is necessary to find new levels of automation and self-reliance in preservation strategies. On the other hand, agent-oriented computing has been widely viewed as a promising computing paradigm for developing large-scale complex software systems. It has already been successfully applied in some industrial and commercial areas. However, to the best of our knowledge, there are no initiatives that employ this computing paradigm as the general methodology to study long-term digital preservation in the open literature. In this paper, we make a brief introduction to the PROTAGE project, funded by the European FP7 Research Programme, which aims to computerize long-term digital preservation by adopting the agent-oriented computing paradigm. We specifically describe the intelligent agent based architecture of the PROTAGE system and discuss the fundamental agents as well as their interactions involved in this system. We further present a general framework of semi-automated decision making agents that are crucial for the automation of long-term digital preservation. Finally, we discuss key issues and great challenges related to the implementation of the PROTAGE system.

  • Xiaolong Jin, Jianmin Jiang, and Geyong Min, Managing Computer Files via Artificial Intelligence Approaches, Artificial Intelligence Review, vol. 31, no. 1, pp. 101-117, 2009.

    Abstract: Agent-oriented computing has been regarded as a very promising methodology to developing intelligent software systems. Intelligent agent technology has, thus, been successfully applied in many industrial and commercial areas. Cased based reasoning (CBR) is an effective and efficient analogical reasoning method for solving problems using the knowledge of past experiences, which are stored in a knowledge base as cases. CBR has been extensively employed to tackle such problems as design, planning, classification, and advising in many different application fields. On the other hand, as various files are created on computers, how to efficiently manage computer files becomes a significant issue. So far, there are a number of file management systems available. However, none of them can deal with these crucial problems of file management: Which files should be deleted after their use? Which files should be temporarily kept or permanently preserved? To the best of our knowledge, these problems have not yet been investigated in the open literature. To bridge this gap, in this paper we explore the value of the above artificial intelligence approaches in managing computer files. We develop an intelligent agent based personal file management system, where CBR is employed to guide users to managing their files. Through extensive practical experiments, we validate the effectiveness and efficiency of the developed system.

  • Araceli Moreno, Josep Lluis de la Rosa, Boleslaw K. Szymanski, and José Moisés Bárcenas, Reward System for Completing FAQs, Artificial Intelligence Research and Development, vol. 202, pp. 361-370, 2009.

    Abstract: The creation of Answer Communities around a FAQs Site is proposed to speed up the process of answering questions. Our approach combines long-term and short-term rewards. Long-term rewards are found to boost participation, motivating users to complete FAQs with proper answers faster.

  • Xiaolong Jin, Jianmin Jiang, and Geyong Min, Multi-Agent Based Personal File Management Using Case Based Reasoning, Lecture Notes in Artificial Intelligence, vol. 5572, pp. 26-33, 2009.

    Abstract: Computer users have been facing a progressively serious problem, namely, how to efficiently manage computer files so as to not only facilitate themselves to use the files, but also save the scare storage resource. Although there are a lot of file management systems available so far, none of them, to the best of our knowledge, can automatically address the deletion/preservation problem of files. To fill this gap, this study explores the value of artificial intelligence techniques in file management. Specifically, this paper develops an intelligent agent based personal file management system, where Case Based Reasoning (CBR) is employed to guide file deletion and preservation. Through some practical experiments, we validate the effectiveness and efficiency of the developed file management system.

Magazine Article

  • Xiaolong Jin, Jianmin Jiang, and Josep Lluis de la Rosa, PROTAGE: Long-Term Digital Preservation Based on Intelligent Agents and Web Services, ERCIM News, no. 80, pp. 15-16, January 2010.

    Abstract: Digital objects have emerged as the primary means by which people create, disseminate and exchange information. The huge volume of digital information being constantly produced means there is now a pressing demand for long-term preservation. In this article, we briefly introduce a European FP7 Research Programme funded project, PROTAGE, which will investigate new technology for computerizing long-term digital preservation based on intelligent software agents and Web services.

Conference Papers

  • Mari Runardotter, "With a Little Help from My Friends" - Collaboration for Digital Preservation, Submitted to the 6th International Digital Curation Conference, Chicago Mart Plaza, Chicago, USA, December 6-8, 2010.

    Abstract: The European Union funded PROTAGE (an acronym for PReservation Organizations using Tools in AGent Environments), a small targeted research project (STREP) in the seventh framework programme, aimed at exploring possibilities for using intelligent agents to help users in their digital preservation related problems. More explicitly, the project expected that software agents are able to gather digital preservation related know-how about technical tools and intellectual solutions; compare those to a userĄ¯s particular preservation needs and recommend actions and tools to solve those. The project started in November 2008 and was finished in October 2010. This paper sets out to explore the idea of collaboration between memory institutions and private persons concerning digital preservation. Building on the views that private persons and professionals convey concerning collaboration around digital preservation, I aim to elaborate around how this collaboration be should be designed...

  • Josep Lluis de la Rosa, Albert Trias, Raivo Ruusalepp, Kuldar Aas, Alex Moreno, Eloy Roura, Albert Bres, and Teresa Bosch, Agents for Social Search in Long-Term Digital Preservation, Accepted by the 2010 International Conference on Semantics, Knowledge and Grids (SKG 2010), Ningbo, China, November 1-3, 2010.

    Abstract: This paper describes the application of agents to automate information exchange for digital preservation. Agents are able to recommend preservation solutions and also apply them to different preservation situations. Trust models for question-routing and answer ranking that are implemented by means of agents, show greater performance than traditional keyword search methodologies.

  • Raivo Ruusalepp, Preservation-friendly digital objects - tools to support the automation of digital preservation tasks, Accepted by CITRA 2010, Oslo, Norway, September 13-18, 2010.

  • Albert Trias Mansilla, Josep Lluis de la Rosa, Boris Galitsky, and Gábor Dobrocsi, Automation of social networks with QA agents, Accepted by the 9th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2010), Toronto, Canada, May 10-14, 2010.

    Abstract: This paper describes a model, ASKNEXT, for connecting agents using social networks for knowledge exchanges using email. It proposes a protocol and a mathematical model to understand how emails spread throughout social networks of agents and people, which can be used to predict the scalability of agents exchanging emails to find answers to questions.

  • Mari Runardotter and Jan Aspenfjall, Organizing for Digital Preservation - Who will Do IT?, In Proceedings of the 8th European Conference on Digital Archiving (ECA 2010), Geneva, Switzerland, April 28-30, 2010.

    Abstract: This paper addresses the need of an updated professional profile for managing digital preservation. It builds on a view that we need to consider the organization's total information assets, where the information to be preserved constitutes one part. The underlying idea is that information never dies - instead it can evolve and linger throughout and beyond the organization's life. This paves way for information managers being those who take on the responsibilities for digital preservation. Thus, their professional profile and competences would differ from the traditional archivists.

  • Kuldar Aas and Raivo Ruusalepp, Let agents do the work: new digital preservation concepts from the PROTAGE project, In Proceedings of the 8th European Conference on Digital Archiving (ECA 2010), Geneva, Switzerland, April 28-30, 2010.

    Abstract: Scalability of digital preservation tools has been discussed for a long time. Using software agent technology offers a new way of re-using the know-how of large memory institutions to solve digital preservation problems for small collections. The paper discusses the concept of digital preservation with agent technology, especially the issues of making preservation related know-how accumulated in memory institutions available to users outside the heritage industry. The paper also demonstrates the tools developed in the PROTAGE project.

  • Albert Trias, Joan Puiggali, Francesc Castro, Teo Jove, Mateu Sbert, and Jose L. Marzo, Speculative parallelization of multipath radiosity algorithm, in Proceedings of the 2009 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS 2009), July 13-16, 2009, Istanbul, Turkey.

    Abstract: In computer graphics, global illumination algorithms take into account not only the light that comes directly from the sources, but also the light interreflections. This kind of algorithms produce very realistic images, but at a high computational cost, especially when dealing with complex environments. Parallel computation has been successfully applied to such algorithms in order to make it possible to compute highly-realistic images in a reasonable time. We introduce here a speculation-based parallel solution for a global illumination algorithm in the context of radiosity, in which we have taken advantage of the hierarchical nature of such an algorithm.

  • Ann Hagerfors, Hugo Quisbert, and J. Nilsson, Agent Technology Supporting Digital Preservation, in Proceedings of the 2nd International Multi-Conference on Engineering and Technological Innovation (IMETI'09), Orlando, Florida, USA, July 10-13 2009.

    Abstract: The EU FP7 PROTAGE project opens up a novel approach to digital preservation by utilizing agent ecosystems for automation of preservation processes. The resulting preservation tools have the potential to enable integrated automated digital preservation operations in digital archives and libraries of different scales throughout Europe. It could also assist individuals in preserving their personal digital collections. The PROTAGE multi-agent system, a set of integrated tools, is developed as a prototype system in several iterations. The first prototype contains functionality for pre-ingest, i.e. the preparation of information packages for transfer from active usage to a digital archive.

  • Josep Lluis de la Rosa, Albert Trias, Silvana Aciar, Esteve del Acebo, and Hugo Quisbert, Shout and Act: an Algorithm for Digital Objects Preservation Inspired from Rescue Robots, in Proceedings of the First International Workshop on Innovation in Digital Preservation (InDP 2009), Austin, Texas, USA, June 19, 2009.

    Abstract: We adapt the Shout and Act algorithm to Digital Objects Preservation where agents explore file systems looking for digital objects to be preserved (victims). When they find something they "shout" so that agent mates can hear it. The louder the shout, the urgent or most important the finding is. Louder shouts can also refer to closeness. We perform several experiments to show that this system works very scalably, showing that heterogeneous teams of agents outperform homogeneous ones over a wide range of tasks complexity. The target at-risk documents are MS Office documents (including an RTF file) with Excel content or in Excel format. Thus, an interesting conclusion from the experiments is that fewer heterogeneous (varying skills) agents can equal the performance of many homogeneous (combined super-skilled) agents, implying significant performance increases with lower overall cost growth. Our results impact the design of Digital Objects Preservation teams: a properly designed combination of heterogeneous teams is cheaper and more scalable when confronted with uncertain maps of digital objects that need to be preserved. A cost pyramid is proposed for engineers to use for modeling the most effective agent combinations.

  • Josep Lluis de la Rosa, E. del Acebo, Albert Trias, Silvana Aciar, and Hugo Quisbert, Crew Intelligence Systems for Digital Objects Preservation, in Proceedings of the 2nd Swarm Intelligence Algorithms and Applications Symposium (SIAAS-09), Edimburgh, UK, April 6-9, 2009.

    Abstract: Crew Intelligence Systems is a family of very simple algorithms for different classes of complex optimization problems in static and dynamic environments by means of reactive multi agent systems. Crew Intelligence systems are loosely inspired from the behavior shown by a staff of bartenders when serving drinks to customers in a bar or pub. In this paper we improve them by letting the bartenders also call (shout) for help, and we adapt them to Digital Objects Preservation, where agents explore file systems looking for victims, digitals objects that need change of format, or any other transformation to be preserved. When they find someone they "shout" so that agent mates can hear it. The louder the shout, the most important or urgent the finding. Louder shouts can also refer to closeness. We perform several experiments to show that this system works very scalably, showing that heterogeneous teams of agents outperform homogeneous ones over a wide range of task complexity. Finally, a properly designed combination of heterogeneous agents is more scalable when confronted with uncertain maps of digital objects to be preserved.

  • Xiaolong Jin, Jianmin Jiang, and Geyong Min, Towards Computerized Digital Preservation Based on Intelligent Agents and Web Services, in Proceedings of the 5th International Conference on Web Information Systems and Technologies (WEBIST'09), pp. 276-281, Lisbon, Portugal, March 22-26, 2009.

    Abstract: The explosively growing volume of digital information results in pressing demands to transfer digital objects from active IT systems to digital repositories, libraries, and archives for long-term preservation. However, existing strategies of digital preservation are labour intensive and often require specialist skills. In order to meet the preservation demands of immense digital information, it is necessary to find new levels of automation and self-reliance in preservation strategies. On the other hand, intelligent agent technology is widely viewed as a promising approach to developing large-scale complex software systems. It has already been successfully applied in some industrial and commercial areas. Meanwhile, Web services have evolved into a key paradigm for distributed computing. They provide an efficient way to realize loosely-coupled architecture and interoperable solutions across heterogeneous platforms and systems. Therefore, Web services have received great attention from both industry and academia. However, to the best of our knowledge, there are no initiatives that employ the technologies of intelligent agents andWeb services as the general methodology to study long-term digital preservation in the open literature. In this paper, we describe an intelligent agent and Web service based architecture of the PROTAGE system, which is funded by the European FP7 Research Programme and aims to computerize long-term digital preservation. We discuss the fundamental agents involved in the PROTAGE system as well as their interactions. We further present a general framework of automated decision making based on intelligent agents andWeb services, which are crucial for the automation of long-term digital preservation. Finally, we discuss several key issues related to the implementation of the PROTAGE system.

  • Josep Lluis de la Rosa, Joan Batlle, Boleslaw K. Szymanski, Elisabet Batlle, and Mukkai Krishnamoorthy,  A Design of Complementary Community Currencies for Education, in Proceedings of the 2nd International Conference on Computer Supported Education (CSEDU 2009), pp. 410-414, Lisboa, Portugal, March 23-26, 2009.

    Abstract: This paper proposes a design for complementary community currencies for education communities to boost cooperation of the more advanced students with the less advanced ones. Its design follows two goals: motivating students to learn by doing extra homework (effort) and share knowledge with younger students (tutoring), and shifting the role of teachers towards a more supervisory, tutoring and dynamic tasks. The hypothesis, following a Brazilian example, is that colleges may accept as payment for their tuitions not only conventional legal currencies, but also educational complementary currencies. The traditional grants policies based on personal effort will be paid with bunnies, and modern community tutoring effort will be paid with knowls. The bunnies and knowls will be obtained as a reward of doing homework and providing help for homework, respectively, and as an expected result, students will have more solid knowledge background at all levels resulting from their boosted personal and community effort.

  • Josep Lluís de la Rosa, Gábor Dobrocsi, and Boleslaw K. Szymanski, Scholar Agent Alfa: the Agents and Web Services Architecture for Citation Auctions, in Proceedings of the 6th European Workshop on Multi-Agent Systems 2008 (EUMAS 2008), pp: 359-367, Bath, UK, December 18-19, 2008.

    Abstract: This paper introduces the design of a multi agent system for citations auctions that aim at changing the current Congresses and Journals peer-reviewed selection of papers. The presented version of the system, Alpha Rel. 1, allows the users to create agents along with the call for papers arena. The users set up their agents by e-mail, hence, the web-service, that is also used by both scientists and agents for bidding. Scholar Agent Alpha Rel. 1 is an open system, simple, yet useful, flexible and adaptive enough to become the underlying architecture for further developments. Functional real case uses of this system are shown and discussed in the paper.

  • Albert Trias Mansilla, Silvana Aciar, Josep Lluís de la Rosa i Esteva, Joan Puiggalí Allepuz and Teodor Jové Lagunas, An Agents Approach for Master/Slave Hierarchical Clusters, in Proceedings of the 6th European Workshop on Multi-Agent Systems 2008 (EUMAS 2008), pp. 59-70, Bath, UK, December 18-19, 2008.

    Abstract: This is an agents approach for Master/Slave hierarchical clusters. The optimal assignation of nodes for the execution of a task is complex in a hierarchical structure of clusters. This will be simplified and empowered by using agents. Master Nodes will actively look for slaves accordingly to the load task that was assigned, and compete for slaves. Taskmasters will try to get only the amount of Slaves that it needs. The results show that this approach is more efficient than a static cluster.

  • Josep Lluís de la Rosa and Boleslaw K. Szymanski, A Study on Diverse Scholar Agents Participating in the Second Price Sealed Bid Citation Auction, In proceedings of the 4th International Conference on Semantics, Knowledge and Grid (SKG 2008), pp. 355-358, Beijing, China, December 3-5, 2008.

    Abstract: An objective of this paper is to study how agents in citation auctions behave in terms of their strategies as well as how their perceptions of the Internal Private Values IPVs) impacts those strategies. These issues are studied using several auction mechanisms, such as the Second Price Sealed Bid (SPSB) auction, the Generalized Vickrey Auction (GVA), and the Uniform Price Sealed Bid (UPSB) auction. Using experiments, each auction mechanism is analyzed and its performance in citation auction measured to find their fitness for citation auctions. The results show that optimistic agents perform well in balanced populations of scholar agents biding in a single market. It is also studied how scholar agents decide in which market to bid, given the competing population of scholars with agents in multiple markets. Finally, the need for a global recommender to help agents to decide how to behave when participating in a single market is evaluated.

  • Silvana Aciar, Johan E. Bengtsson, Ann Hagerfors, and Raivo Ruusalepp, Long-Term Digital Preservation using Agent Technology - the PROTAGE Project, In Proceedings of the DLM Forum 2008 Conference, pp. 69-75, Toulouse, France, December 10-12, 2008.

    Abstract: This paper presents a summary of the aims and achievements to date of the FP7 digital preservation project PROTAGE in developing intelligent software agent tools for digital preservation.

  • Josep Lluis de la Rosa, Johan E. Bengtsson, Raivo Ruusalepp, Ann Hagerfors, and Hugo Quisbert, Using Agents for Long-Term Digital Preservation - the PROTAGE Project, in Proceedings of the International Symposium on Distributed Computing and Artificial Intelligence (DCAI 2008), Salamanca, Spain, October 22-24, 2008.

    Abstract: This is a summary of the PROTAGE project and a proposal for creation of agents useful for automation of the vast amount of human interactions and work otherwise needed in digital preservation. The potential of the technology is illustrated with an agent for appraisal of an individualĄ¯s personal files.