Distributed scheduling to support a call center: A cooperative multiagent approach

This article describes a multiagent system architecture to increase the value of 24-hour-a day call center service. This system supports call centers in making appointments with clients on the basis ofknowledge ofemployees and their schedules. Relevant activities are scheduled for employees in preparation ofsuch appointments. The multiagent system architecture is based on principled design, using the compositional development method for multiagent systems DESIRE. To schedule procedures in which more than one employee is involved, each employee is represented by its own personal assistant agent, and a work manager agent coordinates the schedules of the personal assistant agents and clients through the call center. The multiagent system architecture has been applied to the banking domain, in cooperation with and partially funded by the Rabobank.     

Zeus: A toolkit for building distributed multiagent systems

The multiagent systems approach of knowledge- level cooperation between autonomous agents promises significant benefits to distributed systems engineering, such as enhanced interoperability, scalability, and reconfigurability. However, thus far, because of the innate difficulty of constructing multiagent systems, this promise has been largely unrealized. Hence there is an emerging desire among agent developers to move away from developing point solutions to point problems in favor of developing methodologies and toolkits for building distributed multiagent systems. This philosophy led to the development of the ZEUS Agent Building Toolkit, which facilitates the rapid development of collaborative agent applications through the provision of a library of agent- level components and an environment to support the agent-building process. The ZEUS toolkit is a synthesis of established agent technologies with some novel solutions to provide an integrated collaborative agent-building environment.     

Dynamic workforce allocation in a constrained flow shop with multi-agent system

The present work addresses the problem of real time workforce scheduling in assembly lines where the number of operators is less to the number of workstations.The problem is faced developing a two-steps procedure made of (i) a centralized scheduling based on a constraint optimization problem (COP) for initial operator scheduling, and (ii) a decentralized algorithm performed by a multiagent system (MAS) to manage workers in case of unforeseen events.In the proposed MAS architecture, Agents represent the operators trying to find local assignments for themselves. The system is validated with a simulation model and implemented with a hardware infrastructure in a real assembly line of electromechanical components. The main original contribution of the paper consists in proving – by means of both validation through a simulation model and test in a real assembly line of electromechanical components – that (1) multi-agent systems could be successfully adopted to solve a workforce scheduling problem, and (2) a combined approach consisting of centralized + distributed approach would provide better results compared with the application of one of the two approaches alone.     

Implementing agent teams in dynamic multiagent environments

Teamwork is becoming increasingly critical in multiagent environments ranging from virtual environments for training and education, to information integration on the internet, to potential multirobotic space missions. Teamwork in such complex, dynamic environments is more than a simple union of simultaneous individual activity, even if supplemented with preplanned coordination. Indeed, in these dynamic environments, unanticipated events can easily cause a breakdown in such preplanned coordination. The central hypothesis in this article is that for effective teamwork, agents should be provided explicit representation of team goals and plans, as well as an explicit representation of a model of teamwork to support the execution of team plans. In our work, this model of teamwork takes the form of a set of domain independent rules that clearly outline an agent's commitments and responsibilities as a participant in team activities, and thus guide the agent's social activities while executing team plans. This article describes two implementations of agent-teams based on the above principles, one for a realworld helicopter combat simulation, and one for the RoboCup soccer simulation. The article also provides a preliminary comparison of the two agent-teams to illustrate some of the strengths and weaknesses of RoboCup as a common test bed for multiagent systems.     

Layered approach to learning client behaviors in the robocup soccer server

In the past few years, multiagent systems (MAS) have emerged as an active subfield of artificial intelligence (AI). Because of the inherent complexity of MAS, there is much interest in using machine learning (ML) techniques to help build multiagent systems. Robotic soccer is a particularly good domain for studying MAS and multiagent learning. Our approach to using ML as a tool for building Soccer Server clients involves layering increasingly complex learned behaviors. In this article, we describe two levels of learned behaviors. First, the clients learn a low-level individual skill that allows them to control the ball effectively. Then, using this learned skill, they learn a higher level skill that involves multiple players. For both skills, we describe the learning method in detail and report on our extensive empirical testing. We also verify empirically that the learned skills are applicable to game situations.     

Teamwork in research

Abstract

A doorless assembly system (the Nagamachi System) was first implemented at Nissan Motor's Zama Plant and has since spread throughout Japan and the rest of the world. With this system all doors are taken off a car body in the first process of a car assembly line and assembled in a separate door assembly line. This system aims to obtain an ergonomic profit from the reduction of a worker's workload. The implementation of the system results in such a reduction in workload, as well as an increase in work efficiency, and higher productivity.     

Negotiation in a multi-agent system for construction claims negotiation

Negotiation is an important approach for agents to co-operate and reach agreement in multiagent systems (MAS). Different negotiation theories and models have been deployed in a variety of applications. This paper is concerned with the applicability of these theories to the domain of agent-based construction claims negotiation. The peculiarities of this domain are highlighted and the approach adopted in the development of a multi-agent system for construction claims negotiation (MASCOT) described. Of particular interest is the integration of Zeuthen's bargaining model with a Bayesian learning mechanism, which addresses the characeristics of the construction claims negotiation. Examples are presented to demonstrate the impact of various negotiation approaches on the conduct and outcome of construction claims negotiations.     

Une nouvelle analyse multi-temporelle d'images satellitales,les résidus de l'Analyse en Composantes Principales. Un cas d'étude: une série d'images Landsat Thematic Mapper de la Camargue,France

Résumé. Les méthodes d'analyses de séries temporelles d'images satellitales sont nombreuses. Après une brève revue de ces méthodes, une nouvelle approche est proposée. Elle consiste à calculer les résidus de l'ACP (Analyse en Composantes Principales) du tableau des NDVI par la procédure suivante: calculer les variables NDVI à chacune des dates; construire le tableau de données espace × temps, par accolement des variables NDVI; réaliser l'ACP de ce tableau; déterminer le nombre, k, de facteurs de l'ACP explicatifs des structures stables au cours du temps du paysage; et calculer les résidus entre le tableau NDVI et celui reconstruit à partir des k facteurs. Cette méthode appliquée à l'analyse d'une série de trois scènes Landsat TM acquises en 1983, 1984 and 1993 sur la Camargue (France) a permis de séparer les structures permanentes d'occupation du sol de leurs variations annuelles. La spécificité de cette région, appelée ‘île Camargue’, qui est totalement sous le contrôle des systèmes d'irrigation mis en place par l'homme, apparaît ainsi nettement.

Abstract. Numerous methods exist for the analysis of changes applied to time series of satellite images. After a quick review of these methods, a new approach is proposed. This approach is based on residuals computed from PCA (Principal Component Analysis) on a NDVI table. It consists of: computing the NDVI variable for each date; building a space × time table which joins NDVI variables; carrying out a PCA on this table; choosing the number, k, of factors of PCA which explain time invariant landscape structures; and computing residuals between NDVI table and the table computed from the k factors. This method applied to the analysis of a series of three Landsat TM scenes acquired in 1983, 1984 and 1993 on the Camargue region (France) allows separation of the permanent land use structure from its annual variations. The specificity of the so called ‘island Camargue’ is clearly shown; control of water exchanges by man alters the land use every year.     

Approximately adaptive neural cooperative control for nonlinear multiagent systems with performance guarantee

This paper studies the cooperative control problem for a class of multiagent dynamical systems with partially unknown nonlinear system dynamics. In particular, the control objective is to solve the state consensus problem for multiagent systems based on the minimisation of certain cost functions for individual agents. Under the assumption that there exist admissible cooperative controls for such class of multiagent systems, the formulated problem is solved through finding the optimal cooperative control using the approximate dynamic programming and reinforcement learning approach. With the aid of neural network parameterisation and online adaptive learning, our method renders a practically implementable approximately adaptive neural cooperative control for multiagent systems. Specifically, based on the Bellman's principle of optimality, the Hamilton–Jacobi–Bellman (HJB) equation for multiagent systems is first derived. We then propose an approximately adaptive policy iteration algorithm for multiagent cooperative control based on neural network approximation of the value functions. The convergence of the proposed algorithm is rigorously proved using the contraction mapping method. The simulation results are included to validate the effectiveness of the proposed algorithm.     

A study on effects of market systems in an artificial market

In an artificial market approach with multi-agent systems, the static equilibrium concept is often used in market systems to approximate continuous market auctions. However, differences between the static equilibrium concept and continuous auctions have not been discussed in the context of an artificial market study. In this paper, we construct an artificial market model with both of them, namely, the Itayose and Zaraba method, and show simple characteristic differences between these methods based on computer simulations. The result indicates the further need to model the market system by studying artificial markets. Hidenori Kawamura, Ph.D.: He received Ph.D. degree from Division of Systems and Information Engineering, Graduate School of Engineering, Hokkaido University, Japan in 2000. He is currently an instructor in Graduate School of Information Science and Technology, Hokkaido University, Japan. His research interests include multiagent systems, mass user support, artificial intelligence, complex systems, and tourism informatics. He is a member of IPSJ, JSAI, IEICE, ORSJ, JSTI and AAAI. Yasushi Okada, Ph.D.: He is a master course student in Graduate School of Engineering, Hokkaido University, Japan. He studies multiagent systems. Azuma Ohuchi, Ph.D.: He received his Ph.D. degree in 1974 from Hokkaido University. He is currently the professor in Graduate School of Information Science and Technology, Hokkaido University Japan. His research interstes include systems information engineering, artificial intelligence, complex systems, tourism informatics and medical systems. He is a member of the IPSJ, JSAI, IEEJ, ORSJ, Soc. Contr. Eng., Jap. OR Soc., Soc. Med. Informatics, Hosp. Manag., JSTI and IEEE-SMC. Koichi Kurumatani, Ph.D.: He received his Ph.D. Degree in 1989 from The University of Tokyo. He is currently a leader of Multiagent Research Team in Cyber Assist Research Center (CARC), National Institute of Advanced Industrial Science and Technology (AIST), Japan. His research interests include multiagent systems and mass user support. He is a member of JSAI, IPSJ, JSTI and AAAI.     

Proplant: Multiagent system for production planning

The so-called ''tribase'' acquaintance model of the agent's behavior is presented in this paper. This represents an extension of the twin-base model (Cao et al., 1997). Based on practical experience, the new model tries to cope with parallel processing, precedence constraints, and sparse resources. The idea of substituting the interagent negotiation processes by the periodical internal planning activity of the agents is stressed. A multiagent system, ProPlanT, as an application of the tribase model for the project-oriented production planning developed for TESLA TV company is described in detail. Three types of agents production planning agent (PPA), production management agent (PMA), and production agent (PA) are distinguished. The corresponding tribase models and potential role of metaagents are discussed.     

Environment as a first class abstraction in multiagent systems

The current practice in multiagent systems typically associates the environment with resources that are external to agents and their communication infrastructure. Advanced uses of the environment include infrastructures for indirect coordination, such as digital pheromones, or support for governed interaction in electronic institutions. Yet, in general, the notion of environment is not well defined. Functionalities of the environment are often dealt with implicitly or in an ad hoc manner. This is not only poor engineering practice, it also hinders engineers to exploit the full potential of the environment in multiagent systems. In this paper, we put forward the environment as an explicit part of multiagent systems.We give a definition stating that the environment in a multiagent system is a first-class abstraction with dual roles: (1) the environment provides the surrounding conditions for agents to exist, which implies that the environment is an essential part of every multiagent system, and (2) the environment provides an exploitable design abstraction for building multiagent system applications. We discuss the responsibilities of such an environment in multiagent systems and we present a reference model for the environment that can serve as a basis for environment engineering. To illustrate the power of the environment as a design abstraction, we show how the environment is successfully exploited in a real world application. Considering the environment as a first-class abstraction in multiagent systems opens up new horizons for research and development in multiagent systems.     

Classification automatique assistée par une analyse de texture,des paysages de la Pointe d'Arçay d'après des données Thematic Mapper

Abstract

Cet article présente une classification automatique des unités de paysages de la Pointe d'Arçay d'aprés des données Thematic Mapper (TM), avec un algorithme de classification non supervisée d'agrégation autour de centres mobiles, en utilisant non seulement des informations radiométriques du TM mais aussi un certain nombre de caractéristiques texturales des paysages. La qualité de la classification multispectrale est améliorée par l'introduction d'une analyse de texture

An approach to automatic classification of landscape using LANDSAT-5 Thematic Mapper (TM) data is presented with an example of application for the Arçay spit (Véndee, France). First of all, using unsupervised classification of aggregation round mobile centres (the dynamic-cluster algorithm), a multispectral classification is realized withTM bands 1,2,3,4, 5 and 7, and then a texture analysis is introduced to eliminate classification confusion between certain classes. The classification quality is improved owing to the texture analysis.     

MetrIntPair—A Novel Accurate Metric for the Comparison of Two Cooperative Multiagent Systems Intelligence Based on Paired Intelligence Measurements

In this paper, we propose a novel metric called MetrIntPair (Metric for Pairwise Intelligence Comparison of Agent‐Based Systems) for comparison of two cooperative multiagent systems problem‐solving intelligence. MetrIntPair is able to make an accurate comparison by taking into consideration the variability in intelligence in problem‐solving. The metric could treat the outlier intelligence indicators, intelligence measures that are statistically different from those others. For evaluation of the proposed metric, we realized a case study for two cooperative multiagent systems applied for solving a class of NP‐hard problems. The results of the case study proved that the small difference in the measured intelligence of the multiagent systems is the consequence of the variability. There is no statistical difference between the intelligence quotients/level of the multiagent systems. Both multiagent systems should be classified in the same intelligence class.     

Le programme spatial francais pour I'Observation de la Terre

Résumé.

Abstract

Après avoir mentionn´ les programmes d'observation des oc´ans et de I'atmosph`ere, les autcurs présentent les premi`res expérimentations francaises de télédétection des ressources terrestres dans le cadre des programmes américains (Landsat, Seasat, etc). L'accent est ensuite mis sur le programme SPOT (Systèeme Pour I'Observation de la Terre) concu entre 1972 et 1977, approuvé par le gouvernement francais en 1978 et dont le lancement du premier satellite SPOT 1 a eu lieu le 22 février 1986. Avec ses capteurs à haute résolution (10 ou 20 m) et ses possibilités de visée latérale, SPOT fournit des images dont I'utilisation opérationnelle se développe dans de nombreux domaines (cartographie, ressources renouvelables, etc).

After a short presentation of the ocean and atmosphere observation programmes, the authors describe the first French experiments on earth resources remote sensing with the American satellites Landsat, Seasat, etc. Subsequently the SPOT programme (Système Pour I'Observation de la Terre) is reviewed. This project was studied between 1972 and 1977 and approved by the French government in 1978. The first satellite. SPOT I, was launched on 22 February 1986. With its high resolution sensors (10-20 m) and side-looking capabilities, SPOT gives images for many operational applications (cartography, renewable resources, etc.)     

A multiagent telemedicine system

In this paper we propose a telemedicine sytem model based on multiagent systems. Then, we develop a simulator based on this model. The system is composed of seven agents, such as: a medical database management agent, an application agent, and a planning agent. Some simulations are presented to evaluate the performance of our system. The simulator was developed using JAFMAS (Java-based Agent Framework for Multiagent Systems).     

Télédétection des formations géomorphologiques et de la végétation dans un territoire du Haut Atlas oriental marocain a partir des donnees du satellite SPOT

Abstract

L' étude vise á déterminr les possibilités d'identifier sur 1'imagerie SPOT certains éléments géomorphologiques et du couvert végétal en milieu aride. Les réponses spectrales des types de végétation steppique étant proches de celles des sols nus, leur caracterisation doit passer par une cartographie géomorphologique complétés par une recherche sur les relations vegetation-geomorphologie. Ces possibilités sont illustrées à partir des données SPOT images en couleurs composees (canaux bruts ou combinaisons de canaux) et de classifications supervisées appliquées à un territoire test d'environ 42000 ha du Haut Atlas oriental marocain.

The aim of the study is the evaluation of SPOT imagery for the identification of some geomorphological features and vegetation cover in arid areas. The spectral responses of steppe-type vegetation being close to the ones obtained for bare soils types, their characterization must be obtained through a geomorphological mapping, in addition to research on vegetation-geomorphology interrelations. These possibilities are illustrated from SPOT data colour composite images (raw channels or spectral indices) and from supervised classifications applied to a lest area of about 42 000 ha in the oriental High Atlas Mountains of Morocco.     

Visualization and debugging of distributed multiagent systems

Visualizing the behavior of systems with distributed data, control, and process is a notoriously difficult task. Each component in the distributed system has only a local view of the whole setup, and the onus is on the user to integrate, into a coherent whole, the large amounts of limited information they provide. In this article, we describe an architecture and an implemented system for visualizing and controlling distributed multiagent applications. The system comprises a suite of tools, with each tool providing a different perspective of the application being visualized . Each tool interrogates the components of the distributed application, collates the returned information, and presents this information to users in an appropriate manner. This in essence, shifts the burden ofinference from the user to the visualizer. Our visualizer has been evaluated on four distributed multiagent systems: a travel management application, a telecommunications network management application, a business process management demonstrator, and an electronic commerce application. Lastly, we briefly show how the suite of tools can be used together for debugging multiagent applications - a process we refer to as debugging via corroboration.     

Using bayesian networks to model agent relationships

An agent-society of the future is envisioned to be as complex as a human society. Just like human societies, such multiagent systems (MAS) deserve an in-depth study of the dynamics, relationships, and interactions of the constituent agents. An agent in a MAS may have only approximate a priori estimates of the trustworthiness of another agent. But it can learn from interactions with other agents, resulting in more accurate models of these agents and their dependencies together with the influences of other environmental factors. Such models are proposed to be represented as Bayesian or belief networks. An objective mechanism is presented to enable an agent elicit crucial information from the environment regarding the true nature of the other agents. This mechanism allows the modeling agent to choose actions that will produce guaranteed minimal improvement of the model accuracy. The working of the proposed maxim in entropy procedure is demonstrated in a multiagent scenario.     

Agent-based approach for manufacturing integration: The ciimplex experience

The production management system used by most manufacturers today consists of disconnected planning and execution processes and lacks the support for interoperability and collaboration needed for enterprise-wide integration. This situation often prevents the manufacturer from fully exploring market opportunities in a timely fashion. To address this problem, we are exploring an agent-based approach to intelligent enterprise integration. In this approach, a set of agents with specialized expertise can be quickly assembled to help with the gathering of relevant information and knowledge, to cooperate with each other and with other parts of the production management system and humans to arrive at timely decisions in dealing with various enterprise scenarios. The proposed multiagent system, including its architecture and implementation, is presented and demonstrated through an example integration scenario involving real planning and execution software systems.