Skip to main content

Über dieses Buch

This book constitutes the refereed proceedings of the Workshop on Collaborative Agents, Research and Development, CARE 2014, and the Workshop on Agents, Virtual Societies and Analytics, AVSC 2014, held as Part of AAMAS 2014 in Paris, France, in May 2014. The 10 revised full papers presented were carefully reviewed and selected from more than 40 submissions. The papers deal with the following topics: an ubiquitous service-oriented architecture for urban sensing; geo-fencing based disaster management service; applying ontologies and agent technologies to generate ambient intelligence applications; VIRTUAL-ME: a library for smart autonomous agents in multiple virtual environments; shared message boards for smart enterprises; an improved learning automata approach for the route choice problem; urban context detection and context-aware recommendation via networks of humans as sensors; mining social interaction data in virtual worlds; a multi-agent architecture to support ubiquitous applications in smart environments; caring for my neighborhood: a platform for public oversight.



An Ubiquitous Service-Oriented Architecture for Urban Sensing

In the transformation from traditional to smart cities, there is an increasing trend around the world towards intelligent dynamic infrastructures that provide citizens with new services that can improve their quality of life and fulfill the criteria of energy efficiency and sustainability. In the light of this, an important challenge is how to enable citizens and cities to promote the sensing of data with regard to a number of different factors. This paper outlines the early stages of our research which is concerned with an ubiquitous service-oriented architecture for urban sensing called UrboSenti. The proposed approach differs from other sensing plat-forms since it provides a set of services to collect data from several sources and assists in the development of new sensing applications. In addition, our model encompasses all the sensing activities, ranging from the collection of data to the generation of reports about events in the city.
Carlos O. Rolim, Anubis G. Rossetto, Valderi R. Q. Leithardt, Guilherme A. Borges, Tatiana F. M. dos Santos, Adriano M. Souza, Cláudio F. R. Geyer

Geo-fencing Based Disaster Management Service

The success of disaster handling often depends on the efficient flow of information. The social media and networks receive a growing attention as potential source of valuable data in disaster scenarios. The social network based information flow is real-time, direct, two-directional and often geo-tagged. Unfortunately, besides these obvious advantages, social network data suffers from drawbacks: it is unstructured, dispersed and lacks reliability. This paper proposes an approach based on combining a geo-fencing technology with social network platform to combat this problem and deliver a novel service for disaster management. The service groups users ad-hoc based on their location. Social network features allow users to exchange real-time information, coordinate rescue efforts, issue and report tasks. The geo-fences are visualized to provide a good overview of the disaster zone. The service was evaluated by disaster management experts, with an encouraging feedback.
Piotr Szczytowski

Applying Ontologies and Agent Technologies to Generate Ambient Intelligence Applications

The specification of agent systems comprises different dimensions normally defined using distinct formalisms. Since this lack of a uniform representation makes harder to express how each level affects the others, we propose an ontology to integrate the formalisms that originally cover a single multi-agent system dimension. In doing this, we align semantic technologies and knowledge representation for agents, environments, and organisations providing agent-oriented designers with a unified approach for developing complex systems. In our approach, we represent the abstractions typical of each multi-agent system dimension as an ontology, and we exemplify both the use of such ontologies to model an eldercare application in the context of ambient intelligence and smart cities, as well as how the ontology concepts support coding in agent platforms. We discuss the implications of such integrated view for designing agents, and highlight its advantages for agent-based software development.
Artur Freitas, Daniela Schmidt, Alison Panisson, Rafael H. Bordini, Felipe Meneguzzi, Renata Vieira

VIRTUAL-ME: A Library for Smart Autonomous Agents in Multiple Virtual Environments

Emulating human behaviour is a very desirable characteristic for virtual agents. There is plenty of literature that focuses on a single specific aspect of human behaviour emulation, but it is quite rare to find a collection of implementations encompassing several aspects of the problem. In this work we present VIRTUAL-ME (VIRTUal Agent Library for Multiple Environments), a library that provides programmers with a complete set of classes that assembles various human characteristics and makes it possible to build smart agents. The assessment of the library capabilities to populate a generic virtual environment is also discussed through the analysis of different case studies.
Roberta Castano, Giada Dotto, Rossella Suma, Andrea Martina, Andrea Bottino

Shared Message Boards for Smart Enterprises

Shared Message Boards foster communication practices within restricted groups that typically do not emerge in traditional social networks. In this article, we describe an experiment in which a Shared Message Board technology was employed to support carpooling activities in a large company in Brazil. Based on the results extracted from the platform and from two user studies, we identified important elements influencing the adoption of this technology as well as other activities where it can be effectively used in order to promote the development of smart enterprises.
Kelly Shigeno, Carlos Cardonha, Nicole Sultanum, Rodrigo L. Guimarães, Mateus Molinaro, Ricardo Herrmann, Sergio Borger, Fernando Koch

An Improved Learning Automata Approach for the Route Choice Problem

Urban mobility is a major challenge in modern societies. Increasing the infrastructure’s physical capacity has proven to be unsustainable from a socio-economical perspective. Intelligent transportation systems (ITS) emerge in this context, aiming to make a more efficient use of existing road networks by means of new technologies. In this paper we address the route choice problem, in which drivers need to decide which route to take to reach their destinations. In this respect, we model the problem as a multiagent system where each driver is represented by a learning automaton, and learns to choose routes based on past experiences. In order to improve the learning process, we also propose a mechanism that updates the drivers’ set of routes, allowing faster routes to be learned. We show that our approach provides reasonably good solutions, and is able to mitigate congestion levels in main roads.
Gabriel de O. Ramos, Ricardo Grunitzki

Urban Context Detection and Context-Aware Recommendation via Networks of Humans as Sensors

The wide adoption of smart mobile devices makes the concept of human as a sensor possible, opening the door to new ways of solving recurrent problems that occur in everyday life by taking advantage of the information these devices can produce. In the case of this paper, we present part of the work done in the EU project SUPERHUB and introduce how geolocated positioning coming from such devices can be used to infer the current context of the city, e.g., disruptive events, and how this information can be used to provide services to the end-users.
Sergio Alvarez-Napagao, Arturo Tejeda-Gómez, Luis Oliva-Felipe, Dario Garcia-Gasulla, Victor Codina, Ignasi Gómez-Sebàstia, Javier Vázquez-Salceda

Mining Social Interaction Data in Virtual Worlds

Virtual worlds and massively multi-player online games are rich sources of information about large-scale teams and groups, offering the tantalizing possibility of harvesting data about group formation, social networks, and network evolution. However these environments lack many of the cues that facilitate natural language processing in other conversational settings and different types of social media. Public chat data often features players who speak simultaneously, use jargon and emoticons, and only erratically adhere to conversational norms. This chapter presents techniques for inferring the existence of social links from unstructured conversational data collected from groups of participants in the Second Life virtual world.
Syed Fahad Allam Shah, Gita Sukthankar

A Multi-agent Architecture to Support Ubiquitous Applications in Smart Environments

The implementation of Ambient Intelligence (AmI) requires the support of tools and technologies capable of interpreting large quantities of data collected from different sources comprising sensors networks, mobile devices, social networks and other systems. The agent-oriented paradigm is particularly appropriate for such a scenario, because agents offer some important features, like proactive and reactive reasoning, autonomy, social abilities and learning. In this work we propose a middleware architecture to support the development of applications in the scope of Smart Cities, describing its main characteristics and requirements. The Devices, Environments and Social networks Integration Architecture (DESIA) proposal includes emerging technologies such as social networks, cloud computing and digital ecosystems, emphasizing security and privacy, key aspects not always covered by other architectures.
Cristiano Maciel, Patricia Cristiane de Souza, José Viterbo, Fabiana Freitas Mendes, Amal El Fallah Seghrouchni

Caring for My Neighborhood: A Platform for Public Oversight

Social participation is one of the strong claims that have been done about benefits derived from open government data, but to achieve this goal there are many social, technical and congnitive barriers to discuss. Regarding the specific example of budget transparency, despite there is data supply on governments portals, it is not understandable yet for a broader audience. In order to address this challenge we present in this paper Cuidando do Meu Bairro (Caring for My Neighborhood), a tool that was adopted in São Paulo city to promote citizen engagement and better visualization of public budget expenditures. From unstructured and semi structured information about public spending, some expenditures are geocoded and exhibited on the city map. The color code used in their pins reflects the real time spending status, which delivers budgetary content in a more accessible form to the public. We also discuss some challenges faced, the initial users demands and others ideas to discuss in our ongoing work, the Project Cuidando do Meu Bairro. A broader picture of this project is presented in order to give an idea of potential for linking government information about budget actions, budget amendments from the municipal legislative, and the citizen participation in the budgetary process.
Gisele S. Craveiro, Andrés M. R. Martano


Weitere Informationen

Premium Partner