Ioannis Athanasiadis | Γιάννης Αθανασιάδης
Environmental Modelling & Software
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In 5th Int’l Exhibition and Conference on Environmental Technology (HELECO 2005), pp. 213, Athens, Greece, 2005.
Abstract In an effort to support Environmental Monitoring and Surveillance Centers (EMSC) to fuse, manage and diffuse environmental data in a more efficient manner, we developed a distributed system for managing and diffusing environmental information. The developed system, called AISLE, is an adaptive, intelligent tool for supporting advanced information management services. Its main characteristic is the provision of decision support and information diffusion abilities through electronic services to several users with diverse needs. Specifically, software agents are in charge of integrating and managing environmental data recorded by field sensors or other monitoring devices, along with their diffusion to a wide range of end-user applications, such as environmental databases, terminal applications, or public information services over the internet. The system has been demonstrated in two pilot cases. In the first case, AISLE has been applied for assessing and reporting ambient air quality in Valencia, Spain. In the second case, AISLE was used for monitoring weather conditions in Cyprus.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In Sixth Int’l Symposium on Environmental Software Systems (ISESS-05), (A. Jakeman and D. A. Swayne, ed.), Sesimbra, Portugal, 2005.
Abstract The Meteorological Service of Cyprus operates a Doppler radar at the mountainous region of the island. Data-streams recorded by the radar are used for weather forecasting and, especially, for identifying oncoming precipitation incidents and issuing (potential) warnings. However, the continuous processing and evaluation of radar data requires significant efforts by the meteorologists, both for data processing, storage, and maintenance, as well as for data interpretation and visualization. To assist meteorologists and to automate a large part of these tasks, we have developed Abacus, a multi-agent system for managing radar data and providing decision support. Abacus’ agents undertake data-management and visualization tasks, while they are also responsible for extracting statistical indicators and assessing current weather conditions. In addition, Abacus’ agents can identify potentially hazardous incidents, disseminate preprocessed information over the web, and enable warning services are provided via email. In this paper, Abacus’ agent architecture is detailed and agent communication for information diffusion is discussed. Focus is also given on the fully customizable logical rule-bases used for agent reasoning required in decision-support. The platform has been tested with real-world data from the Meteorological Service of Cyprus.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In Sh@ring (Proc. 18th Int’l Conference on Informatics for Environmental Protection: EnviroInfo 2004), pp. 303-305, Geneva, Switzerland, 2004.
Abstract The last decades, there has been a remarkable change in modern societies. Environmental values are appreciated to a greater extent, as it has become evident that they are highly correlated with our quality of life. The aftermath of the growing societal interest in the environment and sustainable development was the emerging need for providing environmental information to the public. The challenge for Environmental Management and Assessment Information Systems is to provide efficient, accurate and timely electronic services to the public. In this work, we examine the applicability of software agent technology for automating the environmental quality assessment process. Software agents are best suited in systems that are modular, decentralized, changeable, ill-structured and complex, according to Van Dyke Parunak (1999). Environmental management and assessment systems are of this kind, and employing software agents to realize them makes possible the provision of advanced features. However, certain limitations may arise. Both advantages and limitations of agent-based applications for environmental monitoring and assessment systems are connected with real-world functionality.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In Concurrent Engineering: The Vision for the Future Generation in Research and Applications, (R. Jardim-Goncalves, J. Cha and A. Steiger-Garcao, ed.), pp. 11-18, Madeira, Portugal, 2003.
Abstract Software agent technology has matured enough to produce intelligent agents, which can be used to control a large number of concurrent engineering tasks. Multi-agent systems are communities of agents that exchange information and data in the form of messages. The agents’ intelligence can range from rudimentary sensor monitoring and data reporting to more advanced forms of decision making and autonomous behavior. The behavior and intelligence of each agent in the community can be obtained by performing data mining on available application data and the respected knowledge domain. We have developed Agent Academy, a software platform for the design, creation, and deployment of multi-agent systems, which combines the power of knowledge discovery algorithms with the versatility of agents. Using this platform, we show how agents, equipped with a data-driven inference engine, can be dynamically and continuously trained. We also discuss a few prototype multi-agent systems developed with Agent Academy.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In IEEE Int’l Conference on Integration of Knowledge Intensive Multi-Agent Systems (KIMAS-05), (C. Thomson and H. Hexmoor, ed.), pp. 422-428, Waltham, Massachusetts, USA, 2005.
Abstract Data mining has proven a successful gateway for discovering useful knowledge and for enhancing business intelligence in a range of application fields. Incorporating this knowledge into already deployed applications, though, is highly impractical, since it requires reconfigurable software architectures, as well as human expert consulting. In an attempt to overcome this deficiency, we have developed Agent Academy, an integrated development framework that supports both design and control of multi-agent systems (MAS), as well as agent training. We define agent training as the automated incorporation of logic structures generated through data mining into the agents of the system. The increased flexibility and cooperation primitives of MAS, augmented with the training and retraining capabilities of Agent Academy, provide a powerful means for the dynamic exploitation of data mining extracted knowledge. In this paper, we present the methodology and tools for agent retraining. Through experimental results with the Agent Academy platform, we demonstrate how the extracted knowledge can be formulated and how retraining can lead to the improvement – in the long run – of agent intelligence.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In Third Biennial Meeting of the Int’l Environmental Modelling and Software Society, (A. Voinov, A. Jakeman and A. E. Rizzoli, ed.), Burlington, Vermont, USA, 2006.
Abstract Common practice has proven that software implementations of environmental models are seldom reused by broader communities or in different modelling frameworks. One of the reasons for this situation is the poor semantics of model interfaces. Model interfaces describe a critical amount of the modellers’ knowledge, but their software implementations fail to represent the complexity of model assumptions in software terms. In this paper, we present an ontology-driven approach that aims to enrich software model interfaces with advanced semantics. A generic ontology for defining environmental model variables has been developed along with two families of tools for supporting the modellers’ community to share their knowledge and software codes in an easy, efficient and sound way. The first family of tools consists of a web-based ontology editor for sharing knowledge related to environmental model components and their interface variables. The second set of tools exploits the knowledge stored in the ontology by generating source code in an automated fashion. Thus, it is shown how ontologies, accompanied by a set of supporting tools, can be used for promoting the reuse of environmental models.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In 5th Int’l Exhibition and Conference on Environmental Technology (HELECO 2005), pp. 64, Athens, Greece, 2005.
Abstract This paper presents DAWN, a decision support system that uses software agents for simulating the water demand-supply chain in urban environments. Specifically, a community of software agents is assigned to represent residential water consumers, while another agent simulates the Water Utility. The system incorporates: (a) an econometric model for estimating future water demands, and (b) a social model for simulating the influence that permeates among consumers as a result of an information and education campaign. The hybrid combination of the two models is the novelty of the approach that attempts to incorporate both the economical and the social dimension of water value. DAWN use has been demonstrated in the residential area of Thessaloniki, for exploring the responsiveness of water consumers to an information and education campaign.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In First European Workshop on Multi-Agent Systems (EUMAS 2003), (M. d’Inverno, C. Sierra and F. Zambonelli, ed.), Oxford, UK, 2003.
Abstract In this paper we present Agent Academy, a framework that enables software developers to quickly develop multi-agent applications, when prior historical data relevant to a desired rule-based behaviour are available. Agent Academy is implemented itself as a multi-agent system, that supports, in a single tool, the design of agent behaviours and reusable agent types, the definition of ontologies, and the instantiation of single agents or multi-agent communities. Once an agent has been designed within the framework, the agent developer can create a specific ontology that describes the historical data. In this way, agents become capable of having embedded rule-based reasoning. We call this procedure `agent training’ and it is realized by the application of data mining and knowledge discovery techniques on the application-specific historical data. From this point of view, Agent Academy provides a tool for both creating multi-agent systems and embedding rule-based decision structures into one or more of the participating agents.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In MODSIM 2005 Int’l Congress on Modelling and Simulation, (A. Zerger and R. M. Argent, ed.), pp. 732-737, Melbourne, Australia, 2005.
Abstract As researchers we are often faced with the difficult and demanding task of preparing models, and their computer implementations, for decision making, or, more recently, for integrated assessment. Such assessment often involves large scale problems, where the decisions to be made can deeply affect the environment, the social context and the economic background of regions and even nations. Yet, we face the grim reality that a model is a focused representation of the world, and it is always a result of several compromises in terms of details and structure, leading to trade-offs in terms of complexity, flexibility and performance. This trade-off becomes an essential design property. We often wish our models to be as simple as possible, balancing transparency, understandability and level of detail. Now, we are involved in the SEAMLESS project, an EU FP6 Integrated Project, aims at generating an integrated framework of computer models. This framework can be used for assessment of how future alternative agricultural and environmental polices affect sustainable development in Europe. Thus, we are designing a cross disciplinary software system to deal with different simulation domains. In this, we need to take care of many differences between the different modeling societies.In this article we describe all the risks we have identified as associated to our architecture centric approach and how we dealt with them. This article describes the design of the modeling framework for SEAMLESS.
Read also:
Filed Under (Conference papers) by I N Athanasiadis on 31-05-2006
In Agent-Oriented Software Engineering at Autonomous Agents and Multi-Agent Systems (AAMAS 2003), (P. Giorgini, J. P. Mueller and J. Odell, ed.), pp. 1-15, Melbourne, Australia, 2003.
Abstract As agent-oriented paradigm is reaching a significant level of acceptance by software developers, there is a lack of integrated high-level abstraction tools for the design and development of agent-based applications. In an effort to mitigate this deficiency, we introduce Agent Academy, an integrated development framework, implemented itself as a multi-agent system, that supports, in a single tool, the design of agent behaviours and reusable agent types, the definition of ontologies, and the instantiation of single agents or multi-agent communities. In addition to these characteristics, our framework goes deeper into agents, by implementing a mechanism for embedding rule-based reasoning into them. We call this procedure `agent training’ and it is realized by the application of AI techniques for knowledge discovery on application-specific data, which may be available to the agent developer. In this respect, Agent Academy provides an easy-to-use facility that encourages the substitution of existing, traditionally developed applications by new ones, which follow the agent-orientation paradigm.
Read also:
Books edited
Find me elsewhere
