By Topic

Intelligent Agent & Multi-Agent Systems, 2009. IAMA 2009. International Conference on

Date 22-24 July 2009

Filter Results

Displaying Results 1 - 25 of 87
  • Authors index

    Publication Year: 2009 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | PDF file iconPDF (247 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2009 , Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (84 KB)  
    Freely Available from IEEE
  • Introduction

    Publication Year: 2009 , Page(s): 1 - 9
    Save to Project icon | Request Permissions | PDF file iconPDF (478 KB)  
    Freely Available from IEEE
  • Enhanced communication scheme for mobile agents

    Publication Year: 2009 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (844 KB) |  | HTML iconHTML  

    Mobile agent technology is a promising field which has a great scope in the areas of networking, distributed systems and grid systems. The frequent movement of the agents poses challenges for the design of an efficient communication protocol for mobile agents. In this paper we propose an improved communication scheme for mobile agents which overcomes the following issues. First, the problem of overloading of the agent is solved by provision for generating a twin agent when required. Also urgent messages are given priority by using a message queue which sorts the messages according to priority frequently. Our scheme also provides a mechanism for the mobile agent to automatically update itself according to the environmental changes in a predictable and visible manner. Also it reduces the resource overhead over the network dynamically by temporarily destroying the idle agents and reconstructing them when needed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Agent-based autonomous Examination Systems

    Publication Year: 2009 , Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5344 KB) |  | HTML iconHTML  

    Online computerized examination systems is developed using software agent technology. Multi-agent system containing main agent, mobile agent and stationery agent is developed to support the functionality of examination systems in Aglet environment. All these agents in the system communicate with each other to process the operations requested by the user. Authentication of the examinee for valid user name and password is done by the stationary agents at user authentication module and database with the help of mobile agent. After successful authentication and selection of subject by examinee, mobile agent collects questions, their alternatives and correct answer retrieved by stationary agent from the database. These questions are displayed to the examinee. As examinee goes on answering these questions, main agent stores the answer given by examinee in database and updates the score. When the examination gets over, the main agent processes the result and displays result. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance measurement analysis for multi-agent systems

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3735 KB) |  | HTML iconHTML  

    A multi agent system (MAS) consists of number of software agents working together for an application. Agent communication, co-ordination and agent management are the important modules of any MAS, which makes MAS a very complex system. These complex systems require lot of analysis for keeping up the good performance. In this paper number of parameters associated with a multiagent system is discussed for performance analysis. Various categories of MAS communication models are also discussed. A profiling technique is also suggested for a multi agent system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic home agent assignment in WLAN with cellular networks

    Publication Year: 2009 , Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (25471 KB) |  | HTML iconHTML  

    Wireless local area networks (WLANs) are providing the most economical means of Internet access. However, their access is very much limited. They can be deployed in a large scale by integrating them with cellular networks such as universal mobile telecommunication system (UMTS), general packet radio services (GPRS) etc. A seamless roaming between these two hetero networks can be ensured through mobile IP. But the two networks don't have support towards mobile IP which requires the deployment of home agents and a protocol between the mobile nodes, home agents and foreign agents. Hence seamless roaming can be provided by incorporating Mobile IP support in 802.11 (WLAN) networks. The cellular networks require the home agent placement to be placed and the appropriate home agents to be assigned. The home agent placement and home address assignment are the issues for supporting Mobile IP for heterogeneous roaming. If the mobiles use a home agent (HA) that is deployed in a UMTS network when roaming in a WLAN network, the UMTS network may get overloaded with WLAN traffic. The solution to this problem is to dynamically assign an HA in the WLAN domain. Different architectures can be obtained by placing HA at different positions each having its own shortcomings, in which HA is placed between border router and GGSN that requires HA performing very high speed routing as fast as GPRS gateway signaling node (GGSN) which is practically not possible occurring in the existing architecture. To overcome these difficulties different architectures are proposed in this paper. In the first architecture the HA and GGSN is connected to the border router instead of tightly coupling the HA to the GGSN, and the second architecture is HA can be collocated with one of the GGSN in UMTS network and in the third architecture, GGSN is the default router of the mobile nodes (MN) under its coverage area, the foreign agent (FA) is best collocated with the GGSN. Based on the observation of proposed arch- itectures through performance metrics on packet overhead an attempt towards dynamic home agent assignment has been proposed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Identification of emotion stress agents in Hindi and English sentences

    Publication Year: 2009 , Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (325 KB) |  | HTML iconHTML  

    Identification of emotion plays a significant role in human machine interaction. Our research focuses on identifying the emotion stress agent in a spoken sentence in Hindi and English. These agents help us in quickly identifying the emotion in speech. It greatly increases the capability of machine by just analyze the stress agent. We consider the emotions ldquoHappyrdquo, ldquoAngerrdquo, ldquoSurpriserdquo and ldquoSadrdquo along with ldquoNeutralrdquo in speech and examine the difference between the agents. At the end we come up with a table showing the comparison between various stress agents. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge management in education

    Publication Year: 2009 , Page(s): 1 - 3
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1205 KB) |  | HTML iconHTML  

    Institutional effectiveness, synonymous with assessment of learning, but perhaps larger is having sweeping impact on education. Education today is subject to the same pressures of the marketplace to spur innovation, improve customer service, or achieve operational excellence. Modalities of delivering learning have changed from ldquoonly game in townrdquo to ldquoanywhere, anytimerdquo. Knowledge management is the process of transforming information and intellectual assets into enduring value. It connects people with the knowledge that they need to take action, when they need it. There is tremendous value to educational institutions that develop initiatives to share knowledge to achieve business objectives. If done effectively, it can lead to better decision-making capabilities, reduced ldquoproductrdquo development cycle time (for example, curriculum development and research), improved academic and administrative services, and reduced costs. The challenge is to convert the information that currently resides in the individuals of the institution widely and easily available to any faculty member, staff person, or other constituent. This paper outlines the basic concepts of knowledge management as and considers trends, and explores how it might be applied in educational institutes and whether educational institutes are ready to embrace it. All institutions inherently store, access, and deliver knowledge in some manner. It is with KM that institutions will be better able to increase student retention and graduation rates; retain a technology workforce in the face of severe employee shortages; expand new Web based offerings; work to analyze the cost effective use of technology to meet more enrollment; transform existing transaction-based systems to provide information, not just data, for management; and compete in an environment where institutions cross state and national borders to meet student needs anytime/anywhere. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Content based email classification system by applying conceptual maps

    Publication Year: 2009 , Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (413 KB) |  | HTML iconHTML  

    This paper discusses the possibility of adopting the concept of knowledge based systems [KBS], in general, and conceptual maps, in particular, in email classification system. Needless to say that email has the potential to improve efficiency and reduce costs involved in communication. Even after the advent of newer technologies such as instant messaging and VoIP, email remains the top most application of the Internet, intranets and extranets. Though the email system is popular, powerful, cost-effective and efficient, it has some shortcomings viz., [a] it remains an unmanaged medium and [b] it is a vast store of unstructured information. Hence, email database will effectively be used by the knowledge workers only if: [a] it enables classification within stringent legitimate frame work [b] it can be searched/sorted and mined in ways that make it useful. Email classification, a technique for adding metadata and visual labels to email, offers an effective strategy for managing and controlling email. Most of the existing systems are based on term-based classification schemes. To achieve better accuracy, semantic information must be made use of. This proposed system could be an add-on application of existing computational as well as term-based methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generic architecture for agent based E-learning system

    Publication Year: 2009 , Page(s): 1 - 5
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1560 KB) |  | HTML iconHTML  

    E-learning refers to the way by which the learning content is provided by means of electronic technology. E-learning system is classified as either synchronous or asynchronous. It is the effective learning process so that the Web-based learning system has become a promising paradigm in education. Agent based E-learning can manage the information overload, serve as academic experts, and create programming environments for the learners. There are several characteristics specific to E-learning system such as Interaction, Personalization, Adaptation, Intelligence, Interoperability, Accessibility and Security. Agent based architecture for E-learning system provides the above mentioned features to support instructional design, to retrieve relevant learning materials, to process and analyze data to enable meaningful E-learning recommendations to instructors and learners. But most of the existing E-learning architectures doesn't consider all the features in a single system. So there is a need for a generic architecture that should support all the features to make the E-learning system more efficient. In this paper, we provide a generic architecture for E-learning system. This architecture considers interactivity, personalization, adaptation, interoperability, collaboration, security to enhance the quality of learning process. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multi-agent system (MAS) based scheme for health care and medical diagnosis system

    Publication Year: 2009 , Page(s): 1 - 3
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (870 KB) |  | HTML iconHTML  

    In recent era, health care professionals truly belief that the better health care can be provided by developing computerized intelligent health care system. In this paper, we attempted to propose an advanced scheme of agent-based health care and medical diagnosis system using the knowledge base and collaborative as well as co-operative intelligent agents residing on a multi-agent platform, which provides a communicative task-sharing environment. A user-friendly interface of this system will provide high performance, reliability and functionality. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation of dialogue management for learning dialogue strategy using learning automata

    Publication Year: 2009 , Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1442 KB) |  | HTML iconHTML  

    Modeling the behavior of the dialogue management in the design of a spoken dialogue system using statistical methodologies is currently a growing research area. This paper presents a work on developing an adaptive learning approach to optimize dialogue strategy. The problem of dialogue management can be formalized as a sequential decision making under uncertainty whose underlying probabilistic structure has a Markov chain. A variety of data driven algorithms for finding the optimal dialogue strategy is available within Markov decision process which is based on reinforcement learning. However the local reward function is typically set as static and there exist a dilemma in engaging the type of exploration versus exploitation. Hence we present an online policy learning algorithm using learning automata for optimizing dialogue strategy which improves the naturalness of human-computer interaction that combines fast and accurate convergence with low computational complexity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An efficient multi-agent patient scheduling using market based coordination mechanism

    Publication Year: 2009 , Page(s): 1 - 4
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2995 KB) |  | HTML iconHTML  

    An increase in specialization and technology, especially in the health care department has invariably resulted in a need for efficient management of the resources and more timely treatment for the patients. Agents are deployed to solve the patient scheduling problem in the hospitals because they work well in a distributed, decentralized and dynamic environment. Each patient and resource in the hospital is represented by an agent. A combinatorial auction is a specialized form of market based coordination mechanism used to coordinate the allocation of timeslots of the resource. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Agent based models of social systems and collective intelligence

    Publication Year: 2009 , Page(s): 1 - 7
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3142 KB) |  | HTML iconHTML  

    Agent-based modeling and simulation techniques have now become a suitable and popularly used approach to build useful models of social systems, which not only helps to get better understanding of various social phenomena but also enriches the agent-based computing paradigm in return. Agent-based models allow simulating social units such as individuals, households, organizations or nations and their direct or indirect interactions. These models demonstrate how global order and collective intelligence can emerge from relatively simple local interactions and can explain the dynamics of the emergent behaviour. The agent-based modeling approach has provided the bridging link between psychological & sociological analysis of individual and social behaviours respectively, which was otherwise missing. This generative, proof-by-construction approach has also complemented the individual-centered research in cognitive science by showing that individual alone is not the crucial unit of cognition but is affected by environment and society besides affecting them as well. In this paper, we have given an analytical account of agent-based modeling of emergent collective social behaviours, on these lines, along with relevant theoretical & experimental outcomes and their implications for multi-agent systems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-agent based models of social contagion and emergent collective behavior

    Publication Year: 2009 , Page(s): 1 - 5
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2427 KB) |  | HTML iconHTML  

    A deeper understanding of emergence of global patterns in social systems such as diffusion of ideas, emergence of norms & conventions, higher organizations, collective wisdom and evolution of culture; through simple and predictable local interactions of individuals, has been a long quest for sociologists. Agent-based modeling is the latest approach which has virtually replaced the use of traditional techniques of equation based models & micro simulations for social systems analysis. This new paradigm, in addition to being applied to model & analyze various social systems, is also finding widespread application in diverse domains such as economics, business organizations and computational systems. The findings of agent-based models of social systems not only help obtaining a better understanding of the investigated phenomenon but also provide valuable inputs for design of agent-based computational formulations for solving different problems in varied domains. In this paper, we have tried to characterize the use of multi-agent based modeling approach of social contagion and emergent collective behavior along with our experimental work on neighbourhood aggregation model. The paper concludes with a short discussion of the relevant implications for multi-agent systems design. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extension of the Goal-Decision-Information approach to ensure quality in data warehouse development using software agent

    Publication Year: 2009 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2789 KB) |  | HTML iconHTML  

    Data warehouses are complex systems that have to deliver highly-aggregated data from heterogeneous sources to decision makers. It is essential that we can assure the quality data warehouse in terms of data as well as the services provided by it. But the requirements and the environment of data warehouse systems is dynamic in nature. To handle these changes efficiently, data warehouses depend largely on the meta databases. In this paper, the proposal is to extend the Goal-Decision-Information approach to model the quality of the data warehouse. In order to fulfill the specific quality goals, dependencies among the various quality factors is exploited in this model. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved search technique using wildcards or truncation

    Publication Year: 2009 , Page(s): 1 - 4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (639 KB) |  | HTML iconHTML  

    Search engine technology plays an important role in web information retrieval. However, with Internet information explosion, traditional searching techniques cannot provide satisfactory result due to problems such as huge number of result Web pages, unintuitive ranking etc. Therefore, the reorganization and post-processing of Web search results have been extensively studied to help user effectively obtain useful information. This paper has basically three parts. First part is the review study on how the keyword is expanded through truncation or wildcards (which is a little known feature but one of the most powerful one) by using various symbols like * or! .The primary goal in designing this is to restrict ourselves by just mentioning the keyword using the truncation or wildcard symbols rather than expanding the keyword into sentential form. Second part consists of the review on subdivision based on wildcards. It is based on the observation that documents are often found to contain terms with high information content which summarize their subject matter. The third part consists of a proposed algorithm based on the above two. The main goal of this paper is to develop a very efficient search technique by which the information retrieval will be very fast, reducing the amount of extra labor needed on expanding the query. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive content for personalized E-learning using web service and semantic web

    Publication Year: 2009 , Page(s): 1 - 4
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (841 KB) |  | HTML iconHTML  

    E-learning refers to learning that is delivered or enabled via electronic technology. Learning is a cognitive activity that differs from student to student. Personalization is the process of tailoring pages to individual user's characteristics or preferences. E-learning system provides a set of personalization functionalities such as personalizing learning plans, learning materials, test and necessary instant messages etc., to online learners. The problem in the existing system is the lack of personalization due to weak-semantic learning resources. The possibilities of personalized searching for information will be improved, with the advance of the semantic web and available web services. This paper present an approach to e-learning personalization based on ontology and information exchange is maintained by web services based on Service-oriented architecture. Therefore the learning process is enhanced by providing personalized learning content to the learners in an effective and dynamic intelligent way. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-agent based reconfigurable architecture for future wireless networks

    Publication Year: 2009 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2234 KB) |  | HTML iconHTML  

    The key behind successful resolution of all possible communication challenges in future wireless systems is in the interoperability. The concept of interoperability will yield the necessity of reconfigurability and cooperativeness in various communications systems paving the road towards the 4G paradigms. In this paper, the analysis is conducted for the design of reconfigurable architectures for emerging wireless communication systems. This paper also proposes an innovative multi-agent based reconfigurable system approach by which a unified hardware/software co-design methodology is accomplished to improve the system performance in terms of adaptability, efficiency and reliability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Web browser architecture proposal with local agent

    Publication Year: 2009 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2849 KB) |  | HTML iconHTML  

    The Web browser has become the centerfold application to the Internet. It has evolved from being an application for rendering static Web pages to a host of a variety of applications. The growing requirements for a Web browser have lead to code additions, vendor specific add-ons but not much change in its base design. Hence in this paper we are proposing new Web browser architecture based on local computing which will ensure improvement in quality of service (QOS). This can be achieved by adding a generic extensible local agent on client end which will interact with Web browser. This new local agent will support some generic functionality like compression. Additionally this agent can also have an additional security layer specifically designed for Add-ons, authentication, data upload and download. By separating out specific security features from the Web browser to a separate component will help to reduce the code size of a Web browser. Security patch-ups for newly found vulnerabilities related to Web-browser can be made available easily without the reinstallation of complete Web browser. In case of multimedia data upload, compression will ensure tremendous reduction in data transfer over network. In case of image uploads using compression; our POC proves the best case reduction in data transfer by 80 times and average case data transfer reduction by 12 times. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Central Anti-Money Laundering control system using agents technology

    Publication Year: 2009 , Page(s): 1 - 3
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (662 KB) |  | HTML iconHTML  

    The criminal individuals and organizations in today's world including terrorists have taken advantage of the available financial systems, to launder money from illegal proceeds and for their illegal activities. India is particularly under threat from terrorists and it also has been difficult to track down the finance of criminal elements. There have been some proposals in the past for anti money laundering [AML] solutions. However none of them were able to be very effective in India, as our country's vastness, and lack of AML compliance by banks was not taken to consideration. In our approach, after considering the fact that the government in India plays a significant role in regulating the economy and financial practices, we propose a system in which there is central monitoring system, controlled by an independent central agency, which in turn is connected to many regional centres throughout the country, using agents technology. Each of these regional centres will be connected to banks within their given areas. The regional centres will monitor the transactions of all the different banks in a given area and report the suspicious customers back to the central monitoring system. Then central monitoring system reports to the officials concerned and it is investigated into. This is novel agent based approach for a national framework, which is India specific, will ensure the enforcement of AML laws in our country, as every bank will be required to register themselves with a regional monitoring system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent Agents for source decision making process in MANET

    Publication Year: 2009 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2828 KB) |  | HTML iconHTML  

    In this paper, we propose a new intelligent agent based multipath routing protocol for ad hoc wireless networks, which is based on the DSR (dynamic source routing)-on demand routing protocol. Congestion is the main reason for packet loss in mobile ad hoc networks. If the workload is distributed among the nodes in the system, based on the congestion of the paths, the average execution time can be minimized and the lifetime of the nodes can be maximized. We propose a scheme to distribute load between multiple paths according to the congestion status of the path. This protocol uses intelligent agent to obtain the congestion status of the nodes. Our simulation results confirm that the proposed protocol-IASR improves the throughput and reduces the number of collisions in the network. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intrusion Detection System using Self Organizing Maps

    Publication Year: 2009 , Page(s): 1 - 5
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1622 KB) |  | HTML iconHTML  

    With the rapid expansion of computer usage and computer network the security of the computer system has became very important. Every day new kind of attacks are being faced by industries. Many methods have been proposed for the development of intrusion detection system using artificial intelligence technique. In this paper we will have a look at an algorithm based on neural networks that are suitable for Intrusion Detection Systems (IDS). The name of this algorithm is "Self Organizing Maps" (SOM). Neural networks method is a promising technique which has been used in many classification problems. The neural network component will implement the neural approach, which is based on the assumption that each user is unique and leaves a unique footprint on a computer system when using it. If a user's footprint does not match his/her reference footprint based on normal system activities, the system administrator or security officer can be alerted to a possible security breach. At the end of the paper we will figure out the advantages and disadvantages of Self Organizing Maps and explain how it is useful for building an Intrusion Detection System. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Role of ontology in automatic construction of stories for kids

    Publication Year: 2009 , Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2848 KB) |  | HTML iconHTML  

    Story is a description of a chain of events told or written in prose or verse. It gives an excitement for the people in the world irrespective of their age and it is an interesting way of transferring knowledge from one person to other in the form of narrated sequence of events arranged in a chronological order to convey the message. In the artificial intelligence era, construction of stories by the system has the significant role in natural language process. Constructing the stories automatically by the system is significant in the artificial intelligence era. Most of the story generation models have concentrated on syntactic level rather than semantics. Syntactically constructed story may lose their interestingness. To provide the semantics for the constructed story, ontology has significant role. Ontology is a formal explicit shared conceptualization, which is used to provide the domain knowledge. This paper focuses on reasoning the sentences to check the semanticness of the constructed story using ontology. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.