Ioannis N. Athanasiadis

ThinkLab/ThinkCap
(Collaboration with the Ecoinformatics Collaboratoty, University of Vermont, 2005-today)
ThinkCap is a web application that provides user interfaces over a remote, multi-ontology knowledge base. It is designed to meet the needs of non-technical as well as technical users. Users can search for concepts using a sophisticated text search that indexes concept descriptions as well as related web resources or documents. ThinkCap will eventually become a knowledge portal toolkit that will allow extensive customization. By modifying or creating new thinkcap templates and/or extension plug-ins, sophisticated knowledge-based applications can be developed.

System for Environmental and Agricultural Modeling - Linking European Science and Society
(EU-SUSTDEV-FP6 Integrated Project, 2005-2008)

SEAMLESS Integrated Project aims at the generation of an integrated framework with computer models and approaches for ex-ante assessment of alternative agricultural and environmental policy options for sustainable development in Europe. The project has been set up in response to a research and policy need formulated by the European Commission.
SEAMLESS proposes an integrated and operational framework, SEAMLESS-IF. This computer system will include quantitative models that simulate effects of the biophysical environment and economic developments, next to procedures that enable assessment of the qualitative aspects such as quality of life and visual landscape quality.
The latest developments in Information Technology (IT) will facilitate the integration of models from a wide range of scientific domains. Interactive identification of the key indicators (e.g. for environmental pollution, economic performance or social acceptability) that can capture the relevant information associated with specific policy questions will be crucial.

Network on Governance, Science and Technology for Sustainable Water Resource Management in the Mediterranean. The Role of DSS Tools
(EU-FP6,INCO-MPC, Coordination Action, 2004-2007)

This Coordination Action aims to contribute to the achievement of improved governance and planning in the field of sustainable water management, by establishing a network between the science, policy, and civil society spheres, by fostering active involvement of the relevant stakeholders, and through the development and dissemination of Best Practices Guidelines for the design and implementation of Dss tools for Integrated Water Resources Management (IWRM) in the Mediterranean Area.
The key objectives of this Co-ordination Action are:
a) to establish durable links between scientific institutions, governments, NGOs, SMEs and other stakeholders and improve public awareness on water management;
b) to improve scientific knowledge and applied methodologies in IWRM;
c) to promote the development of suitable Dss tools built upon real needs of policy making in IWRM.

DAWN: Distributed Agent-based Water Demand Simulator
(Collaboration with the Hydraulics Div. of the Civil Engineering Dept, Aristotle University, Thessaloniki, 2004-2005)

Design and evaluation of a water-pricing policy is a complex task, as economic, social and political constraints have to be incorporated. In order to support policy makers in their tasks, we developed DAWN, a software tool for evaluating water-pricing policies, implemented as a multi-agent system. DAWN simulates the residential water demand-supply chain and enables the design, creation, modification and execution of different scenarios. Software agents behave as water consumers, while econometric and social models are incorporated into them for estimating future consumptions. Scenarios and models can be parameterized through a friendly graphical user interface and software agents are instantiated at runtime. DAWN’s main advantage is that it supports social interaction between consumers, which is activated using agent communication. Thus, variables affecting water consumption and associated with consumer’s social behavior can be included into DAWN scenarios.
DAWN platform is available at SourceForge.

FLR Classifier: A knowledge representation and learning environment using Fuzzy Lattices
(Collaboration with Prof. V.G. Kaburlasos, 2003-present)

The Fuzzy Lattice Reasoning (FLR) classifier for rule induction (learning) and fuzzy reasoning (generalization) have been introduced in a mathematical lattice data domain. The inherent capacity of lattice theory to accommodate jointly disparate lattices implies a capacity for unified knowledge representation. The FLR classifier carries out learning "on-line" by computing join-lattice intervals, which correspond to hyperboxes in the eucleidian space, whereas generalization is affected by a tunable logical disjunction of lattice interval conjunctions.

Classifier implementation has been contributed to the Waikato Environment for Knowledge Analysis (WEKA).

Agent Academy: A Data-Mining Framework for Training Intelligent Agents
(EU-FP6-IST, Targeted Research Project, 2001-2004)

The overall objective of the project was the development of Agent Academy (AA), an integrated environment for embedding and improving intelligence in newly created agents through the use of Data Mining techniques. The AA platform functions, as its name suggests, as a training facility and it supports:
a) the creation of Intelligent Agents with limited initial referencing capabilities, and
b) the training of these Agents in order to augment their intelligence efficiently, according to user specifications and preferences.
The training process is based on Data Mining technologies that enable the Knowledge Discovery from a substantial set of data derived from monitoring agent behaviour.