Search

The goal of the paper is to identify and confirm the existence of the synergetic effect produced by agents solving together instances of the Euclidean planar travelling salesman problem. The research included the computational experiment in which computation results produced by six implemented A-Teams are analyzed. The reported A-Teams have been built using the JABAT environment. Combinations of five local search procedures, each encoded as an optimizing agent, have been used. The experiment involved instances of the Euclidean planar travelling salesman problem of different sizes. Problem instances have been solved by different A-Teams with different numbers of individuals in the population of solutions stored in the common memory. The research has confirmed that constructing an A-Team from heterogeneous optimizing agents might result in achieving a synergetic effect and thus increasing a quality of the computation results. [ABSTRACT FROM AUTHOR]

JABAT (Jade-based A-Team) is a middleware that allows to design and implement multiagent architectures for solving combinatorial optimization problem. So far JABAT has been implemented in environments of local/global networks, in which the users were able to adjoin computer to the system for the work of the system΄s agents. The paper describes implementation of the middleware called JABAT (JADE-based A-Team) on a cluster of computers at the TASK Academic Computer Centre. It also presents the results of first tests carried out in this new environment. [ABSTRACT FROM AUTHOR]

The chapter proposes a middleware called JABAT (JADE-Based A-Team). JABAT allows to design and implement A-Team architectures for solving combinatorial and selected non-linear optimization problems. The JABAT is intended to become a first step towards next generation A-Teams which are fully Internet accessible, portable, scalable and in conformity with the FIPA standards. From the user point of view JABAT is the web-based application, in the paper refereed to as the e-JABAT. [ABSTRACT FROM AUTHOR]

Distributed data mining is an important research area. The task of the distributed data mining is to analyze data from different sources. Solving such tasks requires a special approach and tools, different from those dedicated to learning from data located in a single database. This paper presents an approach to learning classifiers from distributed data based on data reduction (the prototype selection) at a local level. The problem is solved through applying the A-Team concept implemented using the JABAT environment, which supports implementation of multiple-agent teams. The paper includes a general overview of the JABAT, the problem formulation and some technical details of the proposed implementation. Finally, the computational experiment results validating the approach are shown. [ABSTRACT FROM AUTHOR]

The paper proposes a middleware called JABAT (Jade-based A-Team). JABAT allows to design and implement A-Team architectures for solving combinatorial optimization problem. JABAT is intended to become the first step towards next generation A-Teams which are fully Internet accessible, portable, scalable and in conformity with the FIPA standards. [ABSTRACT FROM AUTHOR]

The paper proposes a JADE-based A-Team environment (JADE-A-Team) as a middleware supporting the construction of the dedicated A-Team architectures used for solving variety of computationally hard optimization problems. The paper includes a general overview of the functionality and structure of the proposed environment and a more detailed description of optimization agents including their standard functions, ontology, construction requirements and activation procedure. Further sections explain how to create and activate an A-Team agent and how the communication between agents is handled. Conclusions focus on advantages of the JADE-A-Team environment and on suggestions for further research. [ABSTRACT FROM AUTHOR]