We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the application of this novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspaces need to be deconflicted, reconciled, and managed automatically. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Furthermore, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.

Task computing ([R. Masuoka et al., (2003)]) enables a user to compose and execute complex tasks in application-, device- and service-rich environments. Task computing is possible through the availability of semantically described services that, can be composed on-the-fly by end-users into executable tasks. Through the use of a task computing client, users can not only compose tasks from available semantically described services, but discover, create, manage and manipulate services as well. The focus of this paper is the technologies used for dynamic service discovery, and creation, management and manipulation of semantically described services.

The Task Computing framework is designed to operate in dynamic ubiquitous environments in which a mobile computing user dynamically discovers the current set of available semantically defined services. Task Computing allows the end-user to easily and seamlessly integrate and manipulate services found on their own computer, the nearby devices and relevant remote web services. The user can create, execute and monitor complex tasks resulting from compositions of these services. In this paper, how Task Computing addresses some issues in mobile and ubiquitous multimedia applications and some of the multimedia related semantic services currently implemented in this framework are described.

Article Free Access Share on MOCHA: a database middleware system featuring automatic deployment of application-specific functionality Authors: Manuel Rodríguez-Martínez Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile , Nick Roussopoulos Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile , John M. McGann Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile , Stephen Kelley Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile , Vadim Katz Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile , Zhexuan Song Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile , Joseph JáJá Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College Park Institute for Advanced Computer Studies and Department of Computer Science, University of Maryland, College ParkView Profile Authors Info & Claims SIGMOD '00: Proceedings of the 2000 ACM SIGMOD international conference on Management of dataMay 2000 https://doi.org/10.1145/342009.336575Published:16 May 2000Publication History 5citation34DownloadsMetricsTotal Citations5Total Downloads34Last 12 Months11Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF