IFMOD: Intuitionistic-Based Fuzzy Multi-Objective Decision in Multi-Agent System

2015 ◽  
Vol 727-728 ◽  
pp. 847-850
Author(s):  
Hui Ying Wang ◽  
Li Na Zhang

Multi-agent system (MAS) contains many intelligent agents, which makes decision for many practical scenarios. However, due to complex decision environment, many data required from sensors are fuzzy. Although a lot of legend solutions address this problem, the decision making result is not very accurate. To solve the problem, we present IFMOD, an algorithm using fuzzy multi-objective decision based on interval-valued intuitionistic fuzzy set. The algorithm adopts iteration way to close the precise value. To make IFMOD algorithm effectively, MAS makes hierarchical structure to complete fuzzy decision. In MAS, most intelligent agents may process the data individually, while other higher intelligent agents make a final decision entirely. The experiment shows that, it is effective for MAS to solve the problem of fuzzy decision in distributed networks.

2019 ◽  
Vol 22 (6) ◽  
pp. 14-26
Author(s):  
Yu. F. Telnov ◽  
A. V. Danilov ◽  
R. I. Diveev ◽  
V. A. Kazakov ◽  
E. V. Yaroshenko

The aim of the researchis to develop a prototype of the intelligent multi-agent system for dynamic interaction of the intelligent agents in the integrated information and educational space to solve the problem of formation of joint educational programs by several educational institutions.Materials and methods.In modern conditions of digital transformation of education the organization of network training of students on dynamically formed educational programs in accordance with the needs of the labor market and the individual requirements of students is becoming increasingly important. It is proposed to develop a software platform based on intelligent multi-agent technology for flexible integration of educational resources and implementation of joint educational programs by several interacting educational institutions. As a basis for the development of the software prototype architecture, the specifications of the developer community for the standardization of agent technologies FIPA (the Foundation for Intelligent Physical Agents), and the software tool environment – JADE framework (Java Agent Development Network) were chosen.Results.The paper presents the architecture of intelligent multi-agent system for network interaction of educational institutions in the integrated information and educational space, which allows to dynamically forming educational programs in accordance with the requested professional competencies. The structure of the ontology of information and educational space, providing the interaction of intelligent agents, is justified, and the mechanism of its display from the OWL format to the format of the tool environment JADE, using the plugin Protege is described. The description of the software prototype, the structure of intelligent agents in the JADE format and the technology of agent interaction, based on the FIPA protocols in the process of educational programs formation is presented.Conclusion.The implementation of the multi-agent system prototype for network interaction of educational institutions allows you to quickly create educational programs in accordance with individual and group learning trajectories under the specific formed professional competence. The presented software prototype with some modification can be used for other subject areas of the digital economy, involving the dynamic formation of network structures of interaction for business partners.


2017 ◽  
Vol 58 ◽  
Author(s):  
Jaroslav Meleško ◽  
Eugenijus Kurilovas ◽  
Irina Krikun

The paper aims to analyse application trends of intelligent multi-agent systems to personalise learning. First of all, systematic literature review was performed. Based on the systematic review analysis, the main trends on applying multi-agent systems to personalise learning were identified. Second, main requirements and components for an educational multi-agent system were formulated. Third, based on these components a model of intelligent personalized system is proposed. The system employs five intelligent agents: (1) learning styles identification software agent, (2) learner profile creation software agent, (3) pedagogical suitability software agent, (4) optimal learning units/scenarios creation software agent, and (5) learning analytics/educational data mining software agent.


Sign in / Sign up

Export Citation Format

Share Document