nach oben

2013 | Buch

Trends in Practical Applications of Agents and Multiagent Systems

11th International Conference on Practical Applications of Agents and Multi-Agent Systems

herausgegeben von: Javier Bajo Pérez, Juan M. Corchado Rodríguez, Johannes Fähndrich, Philippe Mathieu, Andrew Campbell, Mari Carmen Suarez-Figueroa, Alfonso Ortega, Emmanuel Adam, Elena Navarro, Ramon Hermoso, María N. Moreno

Verlag: Springer International Publishing

Buchreihe : Advances in Intelligent Systems and Computing

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Inhaltsverzeichnis

Über dieses Buch

Research on Agents and Multi-agent Systems has matured during the last decade and many effective applications of this technology are now deployed. PAAMS provides an international forum to presents and discuss the latest scientific developments and their effective applications, to assess the impact of the approach, and to facilitate technology transfer. PAAMS started as a local initiative, but since grown to become the international yearly platform to present, to discuss, and to disseminate the latest developments and the most important outcomes related to real-world applications. It provides a unique opportunity to bring multi-disciplinary experts, academics and practitioners together to Exchange their experience in the development and deployment of Agents and Multi-agents systems. PAAMS intends to bring together researchers and developers from industry and the academic world to report on the latest scientific and technical advances on the application of multi-agent systems, to discuss and debate the major issues, and to showcase the latest systems using agent based technology. It will promote a forum for discussion on how agent based techniques, methods and tools help system designers to accomplish the mapping between available agent technology and application needs. Other stakeholders should be rewarded with a better understanding of the potential and challenges of the agent-oriented approach.

This edition of PAAMS special sessions is organized by the Bioinformatics, Intelligent System and Educational Technology Research Group (http://bisite.usal.es) of the University of Salamanca. The present edition was held in Salamanca, Spain, from 22nd to 24th May 2013.

Inhaltsverzeichnis

Frontmatter

A Stylized Software Model to Explore the Free Market Equality/Efficiency Tradeoff

Abstract

This paper provides an agent-based software exploration of the well-known free market efficiency/equality trade-off. Our study simulates the interaction of agents producing, trading and consuming goods within different market structures, and looks at how efficient the producers/consumers mapping turn out to be as well as the resulting distribution of welfare among agents at the end of an arbitrarily large number of iterations. A competitive market is compared with a random one. Our results confirm that the superior efficiency of the competitive market (an effective producers/consumers mapping and a superior aggregative welfare) comes at a very high price in terms of inequality (above all when severe budget constraints are in play).

Hugues Bersini, Nicolas van Zeebroeck

Towards a Dynamic Negotiation Mechanism for QoS-Aware Service Markets

Abstract

The market value of commercial Service-Based Applications (SBAs) will depend not only on their functionality, but also on the value of QoS parameters referring to its not functional properties. These parameters are not static properties since they may vary according to the provision strategies of providers as well as the demand of users having their own preferences on the application’s QoS values. In this paper we propose a negotiation-based mechanism among service providers and a user requesting a QoS-aware SBA to select services with suitable QoS values, i.e. values that once aggregated satisfy the user’s requirements. The proposed mechanism simulates a market-based provision mechanism that allows to take into account the variability of service QoS attribute values typical of the future market of services, as well as to dynamically set the length of the negotiation process that is usually very time consuming.

Claudia Di Napoli, Paolo Pisa, Silvia Rossi

D3S – A Distributed Storage Service

Abstract

The Internet growth allowed an explosion of service provision in the cloud. The cloud paradigm dictates the users’ information migration from the desktop into the network allowing access everywhere, anytime. This paradigm provided a adequate environment to the emergence of online storage services, such as Amazon S3. This kind of service allows storing digital data in a transparent way, in a pay-as-you-go model. This paper describes an implementation of an S3 compatible cloud storage service based on peer-to-peer networks, in particular, through the Bit-Torrent protocol. This approach allows taking advantage of the intrinsic features of this kind of networks, in particular the possibility for simultaneous downloading of pieces from different locations and the fault tolerance.

Rui Pedro Lopes, Pedro Sernadela

Evaluation of the Color-Based Image Segmentation Capabilities of a Compact Mobile Robot Agent Based on Google Android Smartphone

Abstract

This paper presents the evaluation of the image segmentation capabilities of a mobile robot agent based on a Google Android Smartphone. The mobile agent was designed to operate autonomously in an environment inspired in a soccer game. The pixel-based color image segmentation capabilities was performed by testing different two-dimensional look up tables created from two-dimensional color histograms of the objects appearing in the scenario. The best segmentation alternative was obtained when using of a two-dimensional look up table based on the H (hue) and V (value) color image description. The final conclusion is that a Google Android Smartphone has enough potential to define an autonomous mobile robot agent and play a game that requires color-based image segmentation capabilities.

Dani Martínez, Javier Moreno, Davinia Font, Marcel Tresanchez, Tomàs Pallejà, Mercè Teixidó, Jordi Palacín

Distributed and Specialized Agent Communities

Abstract

SCODA (Distributed and Specialized Agent COmmunities) is presented, like a new modular architecture for multi-agent systems development. By means of SCODA, multi-agent systems development is allowed under specialized modular philosophy, through it, the functionalities of the system can be extended in scaled form, according to the objectives. SCODA is composed by small subsystems of agents called, Specialized Intelligent Communities (CIE), which provide the necessary functionalities to solve the objectives needed across distributed services. By means of these CIE, scalability of the systems is allowed, so that they could be re-used in different developments, independently of his purpose.

Jesús Ángel Román, Sara Rodríguez, Juan Manuel Corchado

A Gateway Protocol Based on FIPA-ACL for the New Agent Platform PANGEA

Abstract

Communication is one of the cornerstones of the intelligent agents paradigm. There are different forms of communication between agents, just as there are many platforms for creating them. However, one of the problems we encountered when using the agent paradigm is the actual communication between platforms. That is, to have a gateway of communication between different types of agents regardless of the platform has been used to create them. To this end, a new way of communication between PANGEA and other multiagent platforms is presented in this paper. In this communication process the FIPA-ACL standards are used.

Alejandro Sánchez, Gabriel Villarrubia, Carolina Zato, Sara Rodríguez, Pablo Chamoso

Applying Classifiers in Indoor Location System

Abstract

Research in indoor location has acquired a growing importance during the recent years. The main objective is to obtain functional systems able of providing the most precise location, identification and guidance in real time. Currently, none of the existing indoor solutions have obtained location or navigation results as precise as the ones provided by the analog systems used outdoor, such as GPS. This paper presents an indoor location system based on Wi-Fi technology which, from the use of intensity maps and classifiers, allows effective and precise indoor location.

Gabriel Villarubia, Francisco Rubio, Juan F. De Paz, Javier Bajo, Carolina Zato

Geo-localization System for People with Cognitive Disabilities

Abstract

Technology is present in almost every simple aspect of the people’s daily life. As an instance, let us refer to the smartphone. This device is usually equipped with a GPS modulewhich may be used as an orientation system, if it carries the right functionalities. The problem is that these applications may be complex to operate and may not be within the bounds of everybody.

Therefore, the main goal here is to develop an orientation system that may help people with cognitive disabilities in their day-to-day journeys, when the caregivers are absent. On the other hand, to keep paid helpers aware of the current location of the disable people, it will be also considered a localization system. Knowing their current locations, caregiversmay engage in others activities without neglecting their prime work, and, at the same time, turning people with cognitive disabilities more independent.

João Ramos, Ricardo Anacleto, Paulo Novais, Lino Figueiredo, Ana Almeida, José Neves

Adding Sense to Patent Ontologies: A Representation of Concepts and Reasoning

Abstract

At present, information regarding patents is usually represented and stored in large databases. Information from these databases is commonly retrieved in the form of files with a CSV- or XML-based codification but with little semantics that enable the inference of further relationships among patents. In these databases, each patent is associated with a technological field by a code for a hierarchical classification. Although the codes assume a hierarchical classification approach, inclusion/subsumption relationships are not explicitly specified such that computers can process them automatically. This paper presents an approach to automatically translate the hierarchies found in the patent classification codes into ontologies of concept hi-erarchies. This proposal also enables the automatic inference of implicit knowledge of patent information. A case study is presented to illustrate the applicability of the proposal.

Maria Bermudez-Edo, Manuel Noguera, Nuria Hurtado-Torres, María Visitación Hurtado, José Luis Garrido

Representation of Clinical Practice Guideline Components in OWL

Abstract

The objective of clinical decision support systems is to improve the quality of care and, if possible, help to reduce the occurrence of clinical malpractice cases such as medical errors and defensive medicine. To do so they need a machine-readable support to integrate the recommendations of Clinical Practice Guidelines. CompGuide is a Computer-Interpretable Guideline model developed in Ontology Web Language that offers support for administrative information concerning a guideline, workflow procedures, and the definition of clinical and temporal constraints. When compared to other models of the same type, besides having a comprehensive task network model, it introduces new temporal representations and the possibility of reusing pre-existing knowledge and integrating it in a guideline.

Tiago Oliveira, Paulo Novais, José Neves

Dynamically Maintaining Standards Using Incentives

Abstract

Standards have had much importance in different fields of research in order to assure a certain quality of service in bilateral contracts. More specifically, in multi-agent systems performance standards may be used in order to articulate contracts among partners in environments dealing with uncertainty. However, little effort has been made on how to ensure standards compliance over time. In this work we put forward a learning-based mechanism that attempts to maintain performance standards by applying incentives and/or punishments to agents identified as specialised for certain tasks. We present some empirical results supporting our approach.

Ramón Hermoso, Henrique Lopes Cardoso

Self-organizing Prediction in Smart Grids through Delegate Multi-Agent Systems

Abstract

This paper discusses a contribution to software and system engineering for smart grids, which comprises multi-agent application domain modeling and delegate multi-agent systems. In this contribution, domain models are software components – agents offering executable services – that become part of the multi-agent software as it will be deployed. These domain models crystalize relevant power engineering knowhow and expertise, thus building bridges between the power engineering and the software engineering communities. The longevity of the real-world counterparts of these domain models ensures their technical feasibility and economic value. By mirroring real-world counterparts throughout their full life cycle, re-configurability is ensured and, in combination with the evaporate-and-refresh mechanisms of the delegate multi-agent systems, even becomes business-as-usual. The paper’s main contribution originates from research addressing self-organizing prediction of smart grid operations.

Leo Rutten, Paul Valckenaers

Holonic Recursiveness with Multi-Agent System Technologies

Abstract

Recursive Systems are often needed or recommended for automatically deploy or build a software system composed of multiple entities on a large network, or on distributed locations, without a central control. We use the recursive definitions proposed in holonic systems, as the recursiveness is an elemental structural property of their structure. Holonic systems are used to be implemented usingMAS technologies (platforms) on the basis of the shared functional properties of autonomy and cooperation of agents and holons. This paper discusses the adequacy of the actualMAS technologies for holonic recursiveness implementation. A comparison of MAS platforms is done through a framework that will guide the decisions of designers and developers.

Sonia Suárez, Paulo Leitao, Emmanuel Adam

Intelligent Energy Management System for the Optimization of Power Consumption

Abstract

This paper describes a Smart Storage System capable of managing energy and smart home devices to optimize the local power consumption of a house. The proposed model consists of two main systems; the Local Energy Management Unit (LEMU) and the Central Energy Management and Intelligent System (CEMIS). On the one hand, the LEMU is able to maintain the power consumption under a maximum reference value and to switch on/off the devices by using domotic protocols. On the other hand, the CEMIS receives operation data remotely from several devices, analyzes them using intelligent techniques and determines the best operation strategy for each LEMU, communicating the operation references back to them.

Vicente Botón-Fernández, Máximo Pérez Romero, Adolfo Lozano-Tello, Enrique Romero Cadaval

Find It – An Assistant Home Agent

Abstract

Cognitive impaired population face with innumerable problems in their daily life. Surprisingly, they are not provided with any help to perform those tasks for which they have difficulties. As a consequence, it is necessary to develop systems that allow those people to live independently and autonomously. Living in a technological era, people could take advantage of the available technology, being provided with some solutions to their needs. This paper presents a platform that assists users with remembering where their possessions are. Mainly, an object recognition process together with an intelligent scheduling applications are integrated in an Ambient Assisted Living (AAL) environment.

Ângelo Costa, Ester Martinez-Martin, Angel P. del Pobil, Ricardo Simoes, Paulo Novais

Efficient People Counting from Indoor Overhead Video Camera

Abstract

This article introduces a system for real-time people counting. People counting is a challenging topic in the surveillance domain. The proposed system is built from INT³-Horus, a multi-agent based framework for intelligent monitoring and activity interpretation. The system uses an indoor overhead video camera that detects people moving freely in a hall or room. The people counting system is flexible in detecting individuals as well as groups. Counting is independent of the trajectories and possible occlusions of the humans present in the scene. The initial results offered by the system are very promising in terms of specificity, sensitivity and F-score.

Juan Serrano-Cuerda, José Carlos Castillo, Marina V. Sokolova, Antonio Fernández-Caballero

Modeling Intelligent Agents to Integrate a Patient Monitoring System

Abstract

ICU units are a good environment for the application of intelligent systems in the healthcare arena, due to its critical environment that require diagnose, monitor and treatment of patients with serious illnesses. An intelligent decision support system - INTCare, was developed and tested in CHP, a hospital in Oporto, Portugal. The need to detect the presence or absence of the patient in bed, in order to stop the collection of redundant data concerning about the patient vital status led to the development of an RFID locating and monitoring system - PaLMS, able to uniquely and unambiguously identify a patient and perceive its presence in bed in an ubiquitous manner, making the process of data collection and alert event more accurate. An intelligent multi-agent system for integration of PaLMS in the hospital’s platform for interoperability (AIDA) was also developed, using the characteristics of intelligent agents for the communication process between the RFID equipment, the INTCare module and the Patient Management System, using the HL7 standard embedded in agent behaviours.

Gabriel Pontes, Carlos Filipe Portela, Rui Rodrigues, Manuel Filipe Santos, José Neves, António Abelha, José Machado

Towards Self-Explaining Agents

Abstract

We advocate Self-Explanation as the foundation for the Self-* properties. Arguing that for system component to have such properties the underlining foundation is a awareness of them selfs and their environment. In the research area of adaptive software, self-* properties have shifted into focus pushing ever more design decisions to a applications runtime. Thus fostering new paradigms for system development like intelligent agents. This work surveys the state of the art methods of self-explanation in software systems and distills a definition of self-explanation.

Johannes Fähndrich, Sebastian Ahrndt, Sahin Albayrak

Semi-automated Generation of Semantic Service Descriptions

Abstract

The increasing complexity and dynamics of distributed systems make the management and integration of new services more and more difficult. Automation processes for the definition, selection and composition of services for goal achievement can produce reliefs. However, a high degree of self-explanation of the services is obligatory for this. Today’s multi-agent frameworks only provide insufficient solutions to this. Within this paper we will outline an approach, which enables the integration of semantic service descriptions into multi-agent systems with reasonable effort.

Nils Masuch, Philipp Brock, Sahin Albayrak

Patience in Group Decision-Making with Emotional Agents

Abstract

Intense and usually stressful group decision-making has become a daily activity in the modern business environments which caused the emergence of interest in systems that allow simulation of group decision-making with agents as human representatives (surrogates). Development of representative agents is significantly enhanced through the use of methods that allow mapping of some of the most important human traits in the world of agents. These traits are emotions, personality and mood which gain importance by their direct effect on the process of individual and group decision-making. This paper presents the research results of applying the concept of patience to the emotional agents which should provide more stable and efficient group decision-making.

Denis Mušić

Analysis of Web Usage Data for Clustering Based Recommender System

Abstract

Implicit web usage data is sparse and noisy and cannot be used for usage clustering unless passed through a sophisticated pre-processing phase. In this paper we propose a systematic way to analyze and preprocess the web usage data so that data clustering can be applied effectively to extract similar groups of user. We split the entire process into analysis, preprocessing and outlier detection and show the effect of each phase on Java Application Programming Interface (API) documentation usage data that is collected from our server logs. We use the extracted clusters for web based recommender systems and present the accuracy of the recommendations.

Shafiq Alam, Gillian Dobbie, Patricia Riddle, Yun Sing Koh

Multi-label Classification for Recommender Systems

Abstract

Multi-label classification groups a set of supervised learning methods producing models capable of classifying examples in more than one class. These methods have been applied in diverse fields; however, the field of recommender systems has been hardly explored. In this work, books’ recommendation data are used to evaluate the behavior of the main multi-label classification methods in this application domain. The experiments carried out demonstrated their suitability to provide reliable recommendations and to avoid the grey sheep problem.

Dolly Carrillo, Vivian F. López, María N. Moreno

If It’s on Web It’s Yours!

Abstract

The large amount of information available on web is difficult for machine processing until or unless it is readily available in certain forms. To make it convenient for different processes and in standard pattern, it is often required that the information is available locally and as a dataset. On the web it’s mostly for human use and scattered in different forms and on different locations. In this paper, we have described a method by which one can easily transform scattered information into large datasets and able to process it with different tools to get more meaningful insights.

Abdul Mateen Rajput

User Assistance Tool for a WebService ERP

Abstract

Companies are increasingly complex requiring increasingly complex software management systems. For that reason, they resort to ERP systems, which are becoming wildly complex in an attempt to cover all the needs of the companies. They tend to have extensive menus with endless options to anticipate and try to satisfy all the information management situations. However, this software complexity taxes the human resources in the company. Complex ERP require that employees of these companies receive intensive training, and extensive further support is required of the ERP tool manufacturer.

Israel Carlos Rebollo Ruiz, Manuel Graña Romay

TV-SeriesRec: A Recommender System Based on Fuzzy Associative Classification and Semantic Information

Abstract

Recommender systems have become essential in many web sites, especially in the e-commerce area; however, they are not extended enough in some domains. In this work, a recommender system for TV series is presented due to the increasing interest for this kind of products. The system implements a methodology that deals with the most important problems of recommender systems.

Diego Sánchez-Moreno, Ana Belén Gil, María N. Moreno

Backmatter

Titel: Trends in Practical Applications of Agents and Multiagent Systems
herausgegeben von: Javier Bajo Pérez
Juan M. Corchado Rodríguez
Johannes Fähndrich
Philippe Mathieu
Andrew Campbell
Mari Carmen Suarez-Figueroa
Alfonso Ortega
Emmanuel Adam
Elena Navarro
Ramon Hermoso
María N. Moreno
Verlag: Springer International Publishing
Electronic ISBN: 978-3-319-00563-8
Print ISBN: 978-3-319-00562-1
DOI: https://doi.org/10.1007/978-3-319-00563-8