156 research outputs found
Um sistema de ensino inteligente via sociedade de multi-agentes aplicado ao diagnostico de epilepsia
No full textPlaying with Cases: Rendering Expressive Music with Case-Based Reasoning
No full textThis paper surveys significant research on the problem of rendering expressive music by means of AI techniques with an emphasis on Case-Based Reasoning. Following a brief overview discussing why we prefer listening to expressive music instead of lifeless synthesized music, we examine a representative selection of well-known approaches to expressive computer music performance with an emphasis on AI-related approaches. In the main part of the paper we focus on the existing CBR approaches to the problem of synthesizing expressive music, and particularly on TempoExpress, a case-based reasoning system developed at our Institute, for applying musically acceptable tempo transformations to monophonic audio recordings of musical performances. Finally we briefly describe an ongoing extension of our previous work consisting on complementing audio information with information of the gestures of the musician. Music is played through our bodies, therefore capturing the gesture of the performer is a fundamental aspect that has to be taken into account in future expressive music renderings. This paper is based on the “2011 Robert S. Engelmore Memorial Lecture” given by the first author at AAAI/IAAI 2011.</jats:p
An Agent-based Approach to Health Care Management
No full textThe provision of medical care typically involves a number of individuals, located in a number of different institutions, whose decisions and actions need to be coordinated if the care is to be effective and efficient. To facilitate this decision making and to ensure the coordination process runs smoothly, the use of software support is becoming increasingly widespread. To this end, this paper describes an agent-based system which was developed to help manage the care process in real world settings. The agents themselves are implemented using a layered architecture, called AADCare, which combines a number of AI and agent techniques: a symbolic decision procedure for decision making with incomplete and conflicting information, a concept of accountability for task allocation, the notions of commitments and conventions for managing coherent cooperation, and a set of communication primitives for interagent interaction. The utility of this approach is demonstrated through the development of an application prototype for the clinical process of cancer treatment
Cooperation in Industrial Systems
No full textARCHON is an ongoing ESPRIT II project (P-2256) which is approximately half way through its five year duration. It is concerned with defining and applying techniques from the area of Distributed Artificial Intelligence to the development of real-size industrial applications. Such techniques enable multiple problem solvers (e.g. expert systems, databases and conventional numerical software systems) to communicate and cooperate with each other to improve both their individual problem solving behavior and the behavior of the community as a whole. This paper outlines the niche of ARCHON in the Distributed AI world and provides an overview of the philosophy and architecture of our approach the essence of which is to be both general (applicable to the domain of industrial process control) and powerful enough to handle real-world problems
An Agent Architecture for Distributed Medical Care
No full textAbstract. This paper describes the design and implementation of a layered agent architecture for decision support applications in general and for distributed medical care in particular. Three important characteristics which shaped the agent design are identified: distribution of data and control, information uncertainty, and environment dynamism. To provide appropriate decision support in these circumstances the architecture combines a number of AI and agent techniques: a symbolic decision procedure for decision making with incomplete and contradictory information, a concept of accountability for task allocation, commitments and conventions for managing coherent cooperation, and a set of communication primitives for inter-agent interaction
High p(T) direct photon and pi(0) triggered azimuthal jet correlations and measurement of k(T) for isolated direct photons in p plus p collisions at root s=200 GeV
No full textCorrelations of charged hadrons of 1< p(T) < 10 Gev/c with high pT direct photons and pi(0) mesons in the range 5< p(T) < 15 Gev/c are used to study jet fragmentation in the gamma + jet and dijet channels, respectively. The magnitude of the partonic transverse momentum, k(T), is obtained by comparing to a model incorporating a Gaussian kT smearing. The sensitivity of the associated charged hadron spectra to the underlying fragmentation function is tested and the data are compared to calculations using recent global fit results. The shape of the direct photon-associated hadron spectrum as well as its charge asymmetry are found to be consistent with a sample dominated by quark-gluon Compton scattering. No significant evidence of fragmentation photon correlated production is observed within experimental uncertainties.Office of Nuclear Physics in the Office of Science of the Department of Energy (DOE
An agent-based architecture for software tool coordination
No full textThis paper presents a practical multi-agent architecture for assisting users to coordinate the use of both special and general purpose software tools for performing tasks in a given problem domain. The architecture is open and extensible being based on the techniques of agent-based software interoperability (ABSI), where each tool is encapsulated by a KQML-speaking agent. The work reported here adds additional facilities for the user to describe the problem domain, the tasks that are commonly performed in that domain and the ways in which various software tools are commonly used by the user. Together, these features provide the computer with a degree of autonomy in the user's problem domain in order to help the user achieve tasks through the coordinated use of disparate software tools.
This research focuses on the representational and planning capabilities required to extend the existing benefits of the ABSI architecture to include domain-level problem-solving skills. In particular, the paper proposes a number of standard ontologies that are required for this type of problem, and discusses a number of issues related to planning the coordinated use of agent-encapsulated tools.Unpublished[1] N. Singh. A Common Lisp API and facilitator for ABSI: version 2.0.3. Technical Report Logic-93-4, Logic Group, Computer Science Department, Stanford University, 1993.
[2] M. R. Genesereth and S. P. Ketchpel. Software agents. Communications of the ACM, 37(7):48–53, July 1994.
[3] M. R. Cutkosky, R. S. Engelmore, R. E. Fikes, M. R. Genesereth, and T. R. Gruber. PACT: An experiment in integrating engineering systems. Computer, 26(1):28–37, 1993.
[4] T. Khedro and M. Genesereth. The federation architecture for interoperable agent-based concurrent engineering systems. International Journal on Concurrent Engineering, Research and Applications, 2:125–131, 1994.
[5] W. Wong and A. Keller. Developing an Internet presence with online electronic catalogs. Stanford Center for Information Technology, http://www-db.stanford.edu/pub/keller/1994/cnet-online-cat.ps.
[6] T. Nishida and H. Takeda. Towards the knowledgeable community. In Proceedings of the International Conference on the Building and Sharing of Very Large Scale Knowledge Bases, pages 157–166, 1993. http://ai-www.aist-nara.ac.jp/doc/people/takeda/doc/ps/kbks.ps.
[7] S. J. S. Cranefield and M. K. Purvis. Agent-based integration of general-purpose tools. In Proceedings of the Workshop on Intelligent Information Agents, Fourth International Conference on Information and Knowledge Management, December 1995. http://www.cs.umbc.edu/~cikm/iia/proc.html.
[8] Stanford Knowledge Systems Laboratory. Ontology Server Web page. http://www-ksl-svc.stanford.edu:5915/.
[9] K. Erol, J. Hendler, and D. S. Nau. UMCP: A sound and complete procedure for hierarchical task-network planning. In K. Hammond, editor, Proceedings of the 2nd International Conference on AI Planning Systems, pages 249–254, 1994.
[10] P. R. Cohen, A. Cheyer, M. Wang, and S. C. Baeg. An open agent architecture. In Proceedings of the Spring Symposium on Software Agents, Technical Report SS-94-03. AAAI Press, 1994. ftp://ftp.ai.sri.com/pub/papers/cheyer-aaai94.ps.gz.
[11] C. A. Knoblock and J. L. Ambite. Agents for information gathering. In J. Bradshaw, editor, Software Agents. AAAI/MIT Press, 1996. forthcoming. Also http://www.isi.edu/sims/papers/95-agents-book.ps.
[12] O. Etzioni, N. Lesh, and R. Segal. Building softbots for UNIX. Unpublished technical report, 1992. ftp://june.cs.washington.edu/pub/etzioni/softbots/softbots-tr.ps.Z.
[13] S. S. Ali and S. Haller. Interpreting spreadsheet data for human-agent interactions. In Proceedings of the Workshop on Intelligent Information Agents, Fourth International Conference on Information and Knowledge Management, December 1995. http://www.cs.umbc.edu/~cikm/iia/proc.html
Um framework para simulação econômica baseado em um modelo de agente adaptativo antecipatório com racionalidade limitada
No full textDissertação (Mestrado) - Universidade Federal de Santa Catarina, Centro Tecnológico
A semantic description framework for web services descriptions and matchmaking
No full textIn the M.Sc thesis, the project focuses on the problems of semantic-based representing and retrieving Web services based on the capabilities of services. Service description is critical to application development in Web service environments. There are a number of motivated research developed for representing Web services by different research organisations such as WSDL and UDDI. Both of them are existing standards for Web services. WSDL is designed to provide descriptions of message transport and interface used by each service. UDDI provides a registration structure for businesses and services, and describes businesses and services using their physical attributes in terms of names, addresses, human-understandable business descriptions and service descriptions. Both WSDL and UDDI lack semantic-based description information and a number of essential factors of service capabilities are out of the current description frameworks such as the degrees of service capabilities, relationships between users and services. Moreover, the discovery mechanism provided by UDDI is "exact match” search on the business or service names and descriptions. Actually, service providers and service consumers may have very different background and knowledge, so they do not usually share the same description information for the same item in their minds. It is difficult to locate the proper Web services if users do not express their requirements exactly same with the service provider advertisements. With the consideration of above problems, the development of techniques to semantically represent Web services is necessary for the Web service description and matchmaking. To address the above problems, we identify several requirements and essential factors that a Web service description framework should have and propose a semantic rich modelling framework to integrate these factors to describe Web services capabilities in unambiguous and computer-understandable forms with ontology. The novel description framework is the Business-Service-User (BSU) framework which provides a semantic based description information for business, service and user. Another important goal for the BSU framework is to integrate with current Semantic Web markup languages so that the framework can be easily accessed and understood by the computer. In this thesis, we use the semantic web language OWL to represent the BSU framework and the new semantic description language is called OWL-BSU, which is a computer-interpretable description of the business, service and user. Moreover, a simple and effective matching algorithm is designed to calculate the semantic relationships between service consumers requirements and service descriptions. To make our approach work in the real world, we develop a semantic Web services search engine, which integrates OWL-BSU and the matching algorithm on the top of UDDI registry. The evaluation experimental results have shown that our approach can achieve a great improvement on retrieval performance in terms of recall and precision, comparable to the existing UDDI registry
- …
