The Systemics
and Informatics World Network
SIWN Abstracts
Index
Editorial for Special Issue on Agent Based Systems for Human Learning
Debbie Richards
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 1-2
sai: itssa.2008.03.029
Forming and Scaffolding Human Coalitions: A Framework and An Implementation For Computer-Supported Collaborative Learning Environment
Nobel Khandaker and Leen-Kiat Soh
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 3-22
Abstract: Computer-supported collaborative learning (CSCL) environments are used today as a platform for deli-vering distance education and as a tool to improve student understanding via collaborative learning methods. The suc-cess of a CSCL environment in improving the knowledge of a student depends on the quality of group work of its partici-pants. However, forming human user groups that allow all the users collaborate effectively is difficult because of the dynamic nature of the human users and the complex interplay of human factors (e.g., comfort level, proficiency, etc.). Fur-thermore, human behaviors change over time due to their ability to learn new skills. Thus, a framework that accom-modates the unique nature of human behavior and uses it to improve the outcome of the coalitions is needed. In this pa-per, we present iHUCOFS – a multiagent framework for forming and scaffolding human coalitions. We also discuss an implementation of the iHUCOFS framework (VALCAM) in a CSCL environment called I-MINDS. Preliminary results indicate that VALCAM can make a positive impact on the learner coalitions formed in I-MINDS.
Keywords: computer-supported collaborative learning, mul-tiagent system, human coalition formation, scaffolding.
sai: itssa.2008.03.030
Dynamic Experience Management in Virtual Worlds for Entertainment, Education, and Training
Mark O. Riedl, Andrew Stern, Don M. Dini and Jason M. Alderman
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 23-42
Abstract: Modern computer systems have the ability to make the storytelling experience interactive by involving a participant or learner as a character in the narrative itself. We present a framework for creating interactive narratives for entertainment, educational, and training purposes based on a type of agent called an experience manager. An experience manager (a generalization of a drama manager) is an intelligent computer agent that manipulates a virtual world to coerce a participant’s experience to conform to a set of provided properties. Our realization of the experience manager automatically generates narrative content in order to adapt to the user’s actions in the virtual world. The experience management framework has been used to develop an interactive version of Little Red Riding Hood and an interactive practice environment called IN-TALE for educating and training cognitive skills such as situation awareness, cultural awareness, leadership, and decisionmaking.
Keywords: interactive narrative; storytelling in education and training; drama management; experience management; intelligent tutoring systems
sai: itssa.2008.03.031
Impacts of Visualisation, Interaction and Immersion on Learning Using an Agent-Based Training Simulation
Debbie Richards, Nicolas Szilas, Manolya Kavakli and Mark Dras
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 43-60
Abstract: Simulations offer a safe, repeatable and controlled way of providing training to humans and for evaluating the value of the training. This paper describes a simulation system that we are developing for the purposes of training customs officers to identify risk situations. The work brings together research from virtual environments; narrative intelligence; language technology and knowledge acquisition to develop a training system we are using to evaluate the effect of factors on our architecture and implementation such as visualization, interaction, and immersion on engagement and learning.
Keywords: agent based systems, engines and storytelling, knowledge acquisition, language technology, narrative intelligence, simulations, training, virtual environments.
sai: itssa.2008.03.032
A Survey and Qualitative Analysis of Recent Advances in Drama Management
David L. Roberts and Charles L. Isbell
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 61-75
Abstract: In recent years, there has been a growing interest in constructing rich interactive entertainment and training experiences. As these experiences have grown in complexity, there has been a corresponding growing need for the development of robust technologies to shape and modify those experiences in reaction to the actions of human participants. One popular mechanism for addressing this need is through the use of a drama manager. A drama manager is a coordinator that tracks narrative progress in the environment and directs the roles and/or responses of objects and agents to achieve a specific narrative or training goal. In this paper, we provide a survey of recent advances in drama management technologies for interactive entertainment, and describe a set of desiderata for the qualitative analysis of such systems.
Keywords: agent coordination, desiderata, drama management, interactive drama, interactive narrative, narrative learning.
sai: itssa.2008.03.033
Using Simulation to Model and Understand Group Learning
Maartje Spoelstra and Elizabeth Sklar
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 76-88
Abstract: In this research, simulation is used to model individuals participating in various group learning scenarios. By reviewing the pedagogical literature for key themes found in studies of skill acquisition, the design of learning environments and their effects on individual learners, a set of characteristic factors are identified that can describe a human learner. These characteristics are used to construct computational models that act as controllers for agents acting in a simulated learning environment. Varying parameter values can change the learning environment, as well as control some of the “human” factors that describe the population of agent learners instantiated in the simulation. The simulation can emulate the expected effects based on empirical and experimental results of education and developmental psychology research, and also gives a simple environment in which to conduct low-cost, non-invasive experiments on the design of learning environments.
Keywords: multi-agent simulation, education, group learning
sai: itssa.2008.03.034
e-Advisor: A Web-based Intelligent System for Academic Advising
Fuhua Lin, Kinshuk, Rory McGreal, Steve Leung, Dunwei Wen, Frank Zhang, Qin Li and Xiaofeng Liang
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 89-98
Abstract: This paper describes the design and development of a Web-based intelligent system, e-Advisor, for facilitating academic advising. The system supports three types of users: students, advisors, and program administrators. The paper focuses on the multi-agent architecture and various types of agents in e-Advisor. A preference-driven planning algorithm used by the advisor agent is explained in detail. Empirical results show that the architecture and algorithm are effective.
Keywords: academic advising, intelligent systems, knowledge modeling, multi-agent systems
sai: itssa.2008.03.035
Creating Pedagogical Agents as Social Models in an Online Learning Environment MathGirls
Yanghee Kim, Beijie Xu and Abbass Al Sharif
International Transactions on Systems Science and Applications, Vol. 3, No. 1, March 2008, pp. 99-106
Abstract: This paper introduces the learning environment MathGirls for high school girls learning fundamentals of algebra. Grounded in social cognitive theories of learning, MathGirls utilizes pedagogical agents to create a girl-friendly virtual learning environment. The design constituents of pedagogical agents are reviewed. These constituents are likely to influence building agent/learner relations. The agent design and system architecture of the MathGirls environment are developed to integrate some of the design constituents. Empirical findings from MathGirls deployment in classrooms support the efficacy of the presence of pedagogical agents in shaping affective and cognitive characteristics of the learner. The paper concludes with the discussions of future recommendations for the effective design of and research in pedagogical agent systems.
Keywords: learning companions, math learning, motivation, online learning, pedagogical agents, social interaction
Introduction to Special Section on Agent Based System Challenges for Ubiquitous and Pervasive Computing
Guest Editor: J. Gaber
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 107
sai: itssa.2008.05.030
Facilitating the Ambient Intelligent Vision: A Theorem, Representation and Solution for Instability in Rule-Based Multi-Agent Systems
Victor Zamudio and Vic Callaghan
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 108-121
Abstract: Multi-agent systems underpin the vision for ambient intelligence. However, developing multi-agent systems is a complex and challenging process. For example, pervasive computing has been found susceptible to instability, due to unwanted behaviour arising from unplanned interaction between rule based agents. This instability is impossible to predict, as it depends on the rules of interaction, the initial state of the system, the user interaction, and in the time delay of the system (due to network traffic, different speed of processing, etc). In this paper we present a theoretical framework, an Interaction Network (IN), together with a communication locking strategy that we call INPRES (Instability Prevention System) that can be used to identify and eliminate this problem. In addition we describe a Multi-Dimensional Model (MDM) to represent the agents and the state of each agent over time. A theorem showing the role of delays in an unstable system is presented. We present experimental results based on simulations and a physical emulation that demonstrate the effectiveness of these methods.
Keywords: agent challenges, pervasive computing, instability, periodic behaviour, multi-agents.
sai: itssa.2008.05.031
Enhancing Natural Interaction with Circumstantial Knowledge
Dolores Cuadra, Jessica Rivero, David del Valle and Francisco Javier Calle
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 122-129
Abstract: This work focuses the circumstantial knowledge management for a specific need: the achievement of Natural Interaction (NI). In first place, a cognitive approach to NI is glanced as the framework for such knowledge management. This approach reflects some certain requirements for the whole interaction system, which are met by a multi-agent system implementation. Finally, a Situation Modeling is proposed for a first approach to the interaction circumstances management.
Keywords: natural interaction, situation models, spatiotemporal databases, multi-agent based interaction.
sai: itssa.2008.05.032
Agentφ: A Tool for Modeling Composite Self-Adaptive Agents
Sébastien Leriche and Jean-Paul Arcangeli
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 130-138
Abstract: In this paper, we propose a flexible agent model, and a tool called AGENTφ for modeling safe composite agents. Agents are assembled from fine-grained reusable components, called micro-components, which implement non-functional mechanisms (interaction capabilities, mobility, adaptation skills...). Agents are self-adaptive : when running, an agent can autonomously replace some of its micro-components in order to adapt to runtime conditions. Here, the micro-component level behaves like an adaptable container which hosts the agent's behavior. Static modeling of agents and dynamic self-adaptation features allow developers to deal with flexibility requirements in the context of open distributed computing, and specially of ubiquitous and pervasive computing. An embedded communicating agent (with a GPS component) is developed in order to illustrate our proposal. Experiments show that complexity involved by flexibility constraints is limited due to separation of concerns and levels, and to reuse, still with good performances.
Keywords: agents, software components, software architecture, dynamic adaptation, middleware, open distributed systems.
sai: itssa.2008.05.033
Toward Dynamic Generation of Computational Agents by Means of Logical Descriptions
Roman Neruda and Gerd Beuster
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 139-144
Abstract: A formalism for the logical description of computational agents and multi-agent systems is given. It is explained how it such a formal description can be used to configure and reason about multi-agent systems realizing computational intelligence models. A usage within a real software system Bang 3 is demonstrated. A way to extend the system toward dynamic environments with migrating agents is discussed.
Keywords: Multi-agent systems, formal description, computational intelligence.
sai: itssa.2008.05.034
A Survey on Graph Based Service Discovery Approaches for Ad hoc Networks
Mohammed Haddad and Hamamache Kheddouci
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 145-152
Abstract: The concept of service is frequently used as an abstraction of software and hardware resources. Service oriented architectures should offer mechanisms of service discovery, advertisement and location. So, it represents a key problem in very dynamic networks like ad hoc networks. Various research treating the communication in these networks carried an unquestionable interest to use virtual dynamic topologies to get a better network organization. In this paper, we give a classification and discuss the different virtual topologies in ad hoc networks and their advantages in implementing service oriented applications.
Keywords: Service discovery, ad hoc networks, graphs.
sai: itssa.2008.05.035
P2MP VPLS Using Mobile Agents Approach
Mohamed El Hachimi and Maria Bennani
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 153-157
Abstract: Ethernet is the most widely deployed and ubiquitous Local Area Network technology. Recently, there has been more interest to extend Ethernet physical reach to be used as a suitable solution for wide area networks known as Metro Ethernet. Services offered in this kind of networks are often point to point connections between multiple sites. Virtual Private LAN Service (VPLS) was developed to go beyond point to point connectivity and provide point to multi-point or multipoint to multipoint connectivity.
In the other hand, the increasing adoption of MPLS was soon adapted to scale Ethernet networks and offer VPN services. Consequently, VPLS leverage the foundation and the power of MPLS to offer multi-point connectivity. VPLS sites are connected in fully meshed topology over MPLS using multiple P2P Label switching paths (LSP). The multiple point to point connections leads to wastage of bandwidth that is why Multicast has been proposed to be a suitable solution for VPLS service over MPLS. MPLSs TE support is provided over using Point-to-Point (P2P) LSPs however, the functionality and signaling of Point to Multipoint (P2MP) LSPs are not supported in existing MPLS Architecture. In this paper we propose a solution for point-to-multipoint tree establishment by the mean of mobile agent paradigm, while taking into account, resource management and quality of service requirements.
Keywords: VPLS, MPLS, Mobile agents, VPN, Multicast.
sai: itssa.2008.05.036
A Hybrid Resource Access Approach for Ubiquitous Grid
Imran Ahmad, Sunbal Faheem, Maqbool-uddin-Shaikh and Ghulam Qasim
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 158-161
Abstract: The main objective of the pervasive/ubiquitous computing is the reduction of learning needs of the users. This objective is achieved by making the deduction about the users’ requirements. Flow of services and propagation of pervasive devices produce a large amount of data. The pervasive devices process this data. These devices have limitations on hardware and software capabilities. These devices are also heterogeneous. These features of the pervasive devices make them impractical for complex and data intensive functions. To process complex and data intensive functions need to be dynamically transferred to the infrastructure that should be capable for doing this processing. The Grid infrastructure is best candidate for data intensive functions. The complex and data intensive functions can be transferred to the grid nodes for processing. The resources can be selected based on client location, price and QoS requirements. Critical applications such as homeland security, crisis management, optimizing business processes etc require quick and fast results. In this paper, an algorithm is proposed for task scheduling with time-cost minimization and with maximum resource utilization. The experiments show the performance enhancement for applications and improved resource utilization by this algorithm.
Keywords: ubiquitous computing, grid computing, ubiquitous grid computing, computational grid computing, resource scheduling, OD (On Demand), BLBD (Based on Load Balancing and Demand).
sai: itssa.2008.05.037
Location Models for Pervasive Road Networks
A. Roxin and M. Wack
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 162-166
Abstract: Context-aware mobile computing aims at designing applications that automatically adapt their behaviors to the available location information and the available nearby sensors and devices. This is done in order to fulfill tasks in a way that suits users’ current context best. To achieve this, context representation and manipulation are important issues, so as to establish formal context models. In this paper, basic elements of context-aware systems are described with an emphasis on location information representations. Space models for location-based applications are presented. Considered realistic applications concern intelligent vehicles and pervasive road networks.
Keywords: context-aware systems, pervasive computing, ubiquitous computing, location information modeling, location-aware applications, intelligent vehicle, road network
model.
sai: itssa.2008.05.038
Urban Transport Planning for Ubiquitous Environments
Mahjoub Dridi, Amir Hajjam and Abdellah EL-Moudni
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 167-172
Abstract: The main objective of Ubiquitous Computing (UC) is to provide users information and service accesses anytime and irrespective to their location. In transportation functionning, many approaches based on optimization algorithms are being employed in the development of intelligent transport systems. In particular in public transport, to guarantee a high quality of intelligent transportation planning, timetable must be optimized in order to reduce the transit time of passengers in connections and to provide users real-time and appropriate information that suits their locations and contexts. In this paper, we consider public transportation planning and especially tranfer optimization problem where the goal is to minimize the total expected waiting time of riders by coordinating transfers in the network. The methodology adopted in this work is structured in two phases: the first one consists on optimizing the transit durations in connections with consideration of fixed duration trip between consecutives stations and illimited vehicle capacity. In the second phase, we prove that the considered problem becomes difficult to solve and give a resolution approach based on genetic algorithms.
Keywords: ubiquitous environments, combinatorial optimization, genetic algorithms assignment.
sai: itssa.2008.05.039
A Secure Approach Based on Contract Negotiation for Service Discovery in Ubiquitous Computing Environments
A.Nait-Sidi-Moh, M. Bakhouya and M. Wack
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 173-180
Abstract: Ubiquitous computing deals with providing users accesses to a wide range of services at any time, every where, and from a variety of devices. The monitoring and controlling accesses to these services are one of the fundamental issues that must be faced in the context of ubiquitous computing environments. To address this issue, an access control must be granted to services in order to regulate their usage. In this paper, a secure approach based on contract negotiation and electronic signature for monitoring and controlling accesses to services in ubiquitous environments is presented. In this approach, client agents and server agents are bounded by contracts: the server agent expects that the client agent will not attempt to access other services than those it required, and the client agent expects that the server agent will provide the required service. The specification and modeling of electronic signature process using Petri net together with the validation of its properties are presented.
Keywords: ubiquitous and pervasive computing, service discovery, contract negotiation, electronic signature, specification, modeling and control, petri nets.
sai: itssa.2008.05.040
A Reinforcement Learning-Based Approach for Spontaneous Service Emergence in Pervasive Computing Environments
M. Bakhouya
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 181-187
Abstract: In this paper, a reinforcement learning approach based on the creation of affinity relationships between users having similar preferences and interests is presented. This approach suits pervasive environments to promote computerbased human interactions for spontaneous service emergence. By mimicking the human immune system behavior for the implementation of pervasive applications, services or user interests are represented by agents that can establish relationships based on affinities. Affinity corresponds to the adequacy with which two services could bind to share common interest attributes. These affinities are adjusted or reinforced by users’ satisfaction regarding their interaction and dynamic network condition changes.
Keywords: pervasive computing, spontaneous service emergence paradigm, propitient multi-agent systems, reinforcement learning.
sai: itssa.2008.05.041
TUGrid Portal: A Secure and User-Friendly Interface
Anju Sharma and Seema Bawa
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 188-193
Abstract: Grid computing aims to integrate large number of heterogeneous, geographically distributed resources and services to create the illusion of simple and powerful virtual supercomputers. Grids provide us a common set of services and capabilities that are deployed across the resources. For the deployment of different services and capabilities, grid portals are designed. Grid portals are the essential tools in automotive companies, for managing compute intensive resources, for virtual engineering and designing. This paper presents the motivation for, development and implementation of Grid-enabled computational portal for data processing and integration of various middleware for the interoperability. Along with this implementation details, testbed for the portal, simulation results for the portal, features of the TUGrid Portal and future directions are also presented. The portal can be extended in a number of directions -additional supports for grid administrators, greater number of application-specific interfaces, interoperability between grid infrastructures, and interfaces for programming support.
Keywords: grid computing, grid portals, TUGrid portal, SLA, N1GE6, Globus, Condor, Alchemi
sai: itssa.2008.05.042
Stable Coalitions Under Different Demand Conditions in Iterative Request for Proposal Environments
Carlos Merida-Campos and Steven Willmott
International Transactions on Systems Science and Applications, Vol. 4, No. 2, May 2008, pp. 194-204
Abstract: This paper explores a general model of economic exchange between heterogeneous agents representing firms, traders or other socioeconomic entities, that self-organize into coalitions to fulfil specific tasks. In particular, the work addresses coalition formation problems in which one or many different tasks are directed at the same population over time in an iterative fashion – giving the agents the possibility to organize themselves for specific tasks. The purpose of the paper is to describe the necessary elements that lead the system to an equilibrium state and asses the impact of two different factors on the type of collaboration patterns established between agents. The two factors studied are coalition size constraints and the specificity of the requested tasks. By using a novel data mining technique called collaboration graphs it is possible to see that stable states can be reached using a simple iterative protocol, and that self interested populations adapt to the specific requirements of the task, creating more dynamism when specific task requirements change over time, and increasing in stability when more generic tasks are required. It is also shown that the number of stable states increases as the coalition size limit decreases, and that using a different optimization based on immediate payoff maximization, stability can be compromised.
Keywords: multi-agent systems, coalition formation, request for proposal, distributed problem solving, electronic markets
-------------------------------------------------------------------------------------
Copyright © 2008 SIWN