Intelligent Query Answering Mechanism in Multi Agent Systems

2011 ◽  
pp. 924-932
Author(s):  
Safiye Turgay ◽  
Fahrettin Yaman
Keyword(s):  
Evaluation Criteria ◽  
Evaluation Process ◽  
Query Answering ◽  
Rule Base ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Outer World ◽  
The Future ◽  
Multi Agent

The query answering system realizes the selection of the data, preparation, pattern discovering, and pattern development processes in an agent-based structure within the multi agent system, and it is designed to ensure communication between agents and an effective operation of agents within the multi agent system. The system is suggested in a way to process and evaluate fuzzy incomplete information by the use of fuzzy SQL query method. The modelled system gains the intelligent feature, thanks to the fuzzy approach and makes predictions about the future with the learning processing approach. The operation mechanism of the system is a process in which the agents within the multi agent system filter and evaluate both the knowledge in databases and the knowledge received externally by the agents, considering certain criteria. The system uses two types of knowledge. The first one is the data existing in agent databases within the system and the latter is the data agents received from the outer world and not included in the evaluation criteria. Upon receiving data from the outer world, the agent primarily evaluates it in knowledgebase, and then evaluates it to be used in rule base and finally employs a certain evaluation process to rule bases in order to store the knowledge in task base. Meanwhile, the agent also completes the learning process. This paper presents an intelligent query answering mechanism, a process in which the agents within the multi-agent system filter and evaluate both the knowledge in databases and the knowledge received externally by the agents. The following sections include some necessary literature review and the query answering approach Then follow the future trends and the conclusion.

scholarly journals Distributed Adaptive Formation Tracking Control under Fixed and Switching Topologies: Application on General Linear Multi-Agent Systems

Symmetry ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 941
Author(s):  
Tianhao Sun ◽  
Huiying Liu ◽  
Yongming Yao ◽  
Tianyu Li ◽  
Zhibo Cheng
Keyword(s):  
Switching Topology ◽  
General Linear ◽  
Time Varying ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Switching Topologies ◽  
Formation Tracking ◽  
Leader Following ◽  
Multi Agent

In this paper, the time-varying formation tracking problem of the general linear multi-agent system is discussed. A distributed formation tracking protocol based on Riccati inequalities with adaptive coupling weights among the follower agents and the leader agent is designed for a leader-following multi-agent system under fixed and switching topologies. The formation configuration involved in this paper is expressed as a bounded piecewise continuously differentiable vector function. The follower agents will achieve the desired formation tracking trajectory of the leader. In traditional static protocols, the coupling weights depend on the communication topology and is a constant. However, in this paper, the coupling weights are updated by the state errors among the neighboring agents. Moreover, the stability analysis of the MAS under switching topology is presented, and proves that the followers also could achieve pre-specified time-varying formation, if the communication graph is jointly connected. Two numerical simulations indicate the capabilities of the algorithms.

A Clustering Approach Based on Cooperative Agents to Improve Decision Support in ERP

2019 ◽  
pp. 1-18
Author(s):  
Nadjib Mesbahi ◽  
Okba Kazar ◽  
Saber Benharzallah ◽  
Merouane Zoubeidi ◽  
Djamil Rezki
Keyword(s):  
Decision Support ◽  
Intelligent Systems ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Cooperative Agents ◽  
Distributed Problem Solving ◽  
Multi Agent ◽  
Complete Set ◽  
Clustering Approach

Multi-agent systems (MAS) are a powerful technology for the design and implementation of autonomous intelligent systems that can handle distributed problem solving in a complex environment. This technology has played an important role in the development of data mining systems in the last decade, the purpose of which is to promote the extraction of information and knowledge from a large database and to make these systems more scalable. In this chapter, the authors present a clustering system based on cooperative agents through a centralized and common ERP database to improve decision support in ERP systems. To achieve this, they use multi-agent system paradigm to distribute the complexity of k-means algorithm in several autonomous entities called agents, whose goal is to group records or observations on similar objects classes. This will help business decision makers to make good decisions and provide a very good response time by the use of the multi-agent system. To implement the proposed architecture, it is more convenient to use the JADE platform while providing a complete set of services and have agents comply with the specifications FIPA.

Evolutionary Computation as a Paradigm for Engineering Emergent Behaviour in Multi-Agent Systems

2011 ◽  
pp. 118-136 ◽  
Author(s):  
Robert E. Smith ◽  
Claudio Bonacina
Keyword(s):  
Evolutionary Computation ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Future Directions ◽  
Agent Based ◽  
Agent Systems ◽  
Emergent Behaviour ◽  
Shaping System ◽  
Multi Agent

In the multi-agent system (MAS) context, the theories and practices of evolutionary computation (EC) have new implications, particularly with regard to engineering and shaping system behaviors. Thus, it is important that we consider the embodiment of EC in “real” agents, that is, agents that involve the real restrictions of time and space within MASs. In this chapter, we address these issues in three ways. First, we relate the foundations of EC theory to MAS and consider how general interactions among agents fit within this theory. Second, we introduce a platform independent agent system to assure that our EC methods work within the generic, but realistic, constraints of agents. Finally, we introduce an agent-based system of EC objects. Concluding sections discuss implications and future directions.

INTENT RECOGNITION IN MULTI-AGENT SYSTEMS: COW HERDING

2014 ◽  
Vol 28 (05) ◽  
pp. 1459006
Author(s):  
NAJLA AHMAD ◽  
ARVIN AGAH
Keyword(s):  
Conceptual Framework ◽  
Recognition System ◽  
Plan Recognition ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Intent Recognition ◽  
Domain Specific ◽  
Novel Approach ◽  
Multi Agent

In a multi-agent system, an agent may utilize its idle time to assist other agents in the system. Intent recognition is proposed to accomplish this with minimal communication. An agent performing recognition observes the tasks other agents are performing and, unlike the much studied field of plan recognition, the overall intent of an agent is recognized instead of a specific plan. The observing agent may use capabilities that it has not observed. A conceptual framework is proposed for intent recognition systems. An implementation of the conceptual framework is tested and evaluated. We hypothesize that using intent recognition in a multi-agent system increases utility (where utility is domain specific) and decreases the amount of communication. We test our hypotheses using the domain of Cow Herding, where agents attempt to herd cow agents into team corrals. A set of metrics, including task time and number of communications, is used to compare the performance of plan recognition and intent recognition. In our results, we find that intent recognition agents communicate fewer times than plan recognition agents. In addition, unlike plan recognition, when agents use the novel approach of intent recognition, they select unobserved actions to perform. Intent recognition agents were also able to outperform plan recognition agents by consistently scoring more points in the Cow Herding domain. This research shows that under certain conditions, an intent recognition system is more efficient than a plan recognition system. The advantage of intent recognition over plan recognition becomes more apparent in complex domains.

Software Metrics for Computing Quality of Software Agents

2020 ◽  
Vol 17 (5) ◽  
pp. 2035-2038
Author(s):  
E. Ajith Jubilson ◽  
Ravi Sankar Sangam
Keyword(s):  
Software Metrics ◽  
Online Shopping ◽  
Software Agents ◽  
Evaluation Process ◽  
Building Blocks ◽  
Software Agent ◽  
Multi Agent System ◽  
Agent System ◽  
Multi Agent

Metrics are the essential building blocks for any evaluation process. They establish specific goals for improvement. Multi agent system (MAS) is complex in nature, due to the increase in complexity of developing a multi agent system, the existing metrics are less sufficient for evaluating the quality of an MAS. This is due to the fact that agent react in an unpredictable manner. Existing metrics for measuring MAS quality fails to addresses potential communication, initiative behaviour and learn-ability. In this work we have proposed additional metrics for measuring the software agent. A software agent for online shopping system is developed and the metrics values are obtained from it and the quality of the multi agent system is analysed.

Bounded consensus tracking control of second-order multi-agent systems with active leader and jointly connected topology

2016 ◽  
Vol 40 (2) ◽  
pp. 504-513 ◽  
Author(s):  
Lei Chen ◽  
Kaiyu Qin ◽  
Jiangping Hu
Keyword(s):  
Tracking Control ◽  
Sufficient Conditions ◽  
Interaction Network ◽  
Second Order ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Agent Systems ◽  
Strongly Connected ◽  
Multi Agent

In this paper, we investigate a tracking control problem for second-order multi-agent systems. Here, the leader is self-active and cannot be completely measured by all the followers. The interaction network associated with the leader–follower multi-agent system is described by a jointly connected topology, where the topology switches over time and is not strongly connected during each time subinterval. We consider a consensus control of the multi-agent system with or without time delay and propose two categories of neighbour-based control rules for every agent to track the leader, then provide sufficient conditions to ensure that all agents follow the leader, and meanwhile, the tracking errors can be estimated. Finally, some simulation results are presented to demonstrate our theoretical results.

VERIFICATION OF THE MOBILE AGENT NETWORK SIMULATOR — A TOOL FOR SIMULATING MULTI-AGENT SYSTEMS

2008 ◽  
Vol 18 (05) ◽  
pp. 651-682 ◽  
Author(s):  
MARIO KUSEK ◽  
KRESIMIR JURASOVIC ◽  
GORDAN JEZIC
Keyword(s):  
Mobile Agent ◽  
Formal Model ◽  
Task Complexity ◽  
Network Simulator ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Network Bandwidth ◽  
Knowledge Based ◽  
Multi Agent

This paper deals with the verification of a multi-agent system simulator. Agents in the simulator are based on the Mobile Agent Network (MAN) formal model. It describes a shared plan representing a process which allows team formation according to task complexity and the characteristics of the distributed environment where these tasks should be performed. In order to verify the simulation results, we compared them with performance characteristics of a real multi-agent system, called the Multi-Agent Remote Maintenance Shell (MA–RMS). MA–RMS is organized as a team-oriented knowledge based system responsible for distributed software management. The results are compared and analyzed for various testing scenarios which differ with respect to network bandwidth as well as task and network complexity.

scholarly journals On Partially Controlled Multi-Agent Systems

1996 ◽  
Vol 4 ◽  
pp. 477-507 ◽  
Author(s):  
R. I. Brafman ◽  
M. Tennenholtz
Keyword(s):  
Expected Utility ◽  
The Other ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Direct Control ◽  
Agent System ◽  
Agent Systems ◽  
Multi Agent ◽  
Game Theoretic

Motivated by the control theoretic distinction between controllable and uncontrollable events, we distinguish between two types of agents within a multi-agent system: controllable agents, which are directly controlled by the system's designer, and uncontrollable agents, which are not under the designer's direct control. We refer to such systems as partially controlled multi-agent systems, and we investigate how one might influence the behavior of the uncontrolled agents through appropriate design of the controlled agents. In particular, we wish to understand which problems are naturally described in these terms, what methods can be applied to influence the uncontrollable agents, the effectiveness of such methods, and whether similar methods work across different domains. Using a game-theoretic framework, this paper studies the design of partially controlled multi-agent systems in two contexts: in one context, the uncontrollable agents are expected utility maximizers, while in the other they are reinforcement learners. We suggest different techniques for controlling agents' behavior in each domain, assess their success, and examine their relationship.

scholarly journals Multi-agent system for computer science and engineering education

2017 ◽  
Vol 58 ◽  
Author(s):  
Jaroslav Meleško ◽  
Eugenijus Kurilovas ◽  
Irina Krikun
Keyword(s):  
Learning Styles ◽  
Intelligent Agents ◽  
Educational Data Mining ◽  
Software Agent ◽  
Multi Agent System ◽  
Multi Agent Systems ◽  
Agent System ◽  
Agent Systems ◽  
Multi Agent ◽  
Identification Software

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