Wyniki wyszukiwania - BazTech

1

Modeling of passengers’ choice using intelligent agents with reinforcement learning in shared interests systems; A basic approach

Vikharev Sergey, Lyapustin Maxim, Mironov Danil, Nizovtseva Irina, Sinitsyn Vladimir

Transport Problems

|

2019

|

T. 14, z. 2

43--53

EN

The purpose of this paper is to build a model for assessing the satisfaction of passenger service by the public transport system. The system is constructed using intelligent agents, whose action is based on self-learning principles. The agents are passengers who depend on transport and can choose between two modes: a car or a bus wherein their choice of transport mode for the next day is based on their level of satisfaction and their neighbors’ satisfaction with the mode they used the day before. The paper considers several algorithms of agent behavior, one of which is based on reinforcement learning. Overall, the algorithms take into account the history of the agents’ previous trips and the quality of transport services. The outcomes could be applied in assessing the quality of the transport system from the point of view of passengers.

2

Multi-agent system to assure the logical security of data in distributed information system

Poniszewska-Marańda A.

Journal of Applied Computer Science

|

2013

|

Vol. 21, nr 1

119--133

EN

The increased availability of information as a whole became an important problem and threat for its security, especially security of sensitive and confidential information and that is why the necessity to assure the security of such data became undeniable. The developers of applications an information systems put more and more stress on the aspect of their security and safety. Development of information systems has to answer more and more to problems connected to federated data sources and problems of heterogeneous distributed information systems. It is necessary to propose the architecture for secure cooperation of such systems. The paper presents the practical application of concepts of multi-agent systems in domain of logical security of data in distributed information systems. The purpose of presented solution is to support the process management of IT project realization based on the software creation methodologies.

3

Evolving adaptive recurrent networks with Developmental Symbolic Encoding

Suchorzewski M.

Metody Informatyki Stosowanej

|

2010

|

nr 1 (22)

175-187

EN

In this paper we are concerned with evolutionary synthesis of recurrent networks capable of learning in the environment. First, we define the model of network we aim to evolve, which is weightless recurrent network of basic arithmetic nodes. Next, we propose a developmental genetic representation for the network, along with some genetic operators for it. The representation bears some important characteristics such as closure and completeness. Most notably, however, it features modularity and scalability, which we demonstrate on a parity problem. Finally, we evolve the network capable of successful learning in some narrow problem domain. The result shows, that for a given problem domain, evolutionary approach may produce networks performing better than generic neural networks.