Intelligent Applications

Expert Systems

The goal is to develop intelligent applications for solving non-trivial problems using the expertise knowledge acquired by human experts. The group has been involved in the development of various expert systems, such as:

  • Expert system for software evaluation (ESSE).
  • Distributed expert system for managing a national network (ExperNet).
  • Various intelligent systems for searching in a database using incomplete, insufficient and/or incorrect information.
  • Expert system for land evaluation.
  • Expert system for detecting problems in a Novell LAN.
  • Expert system for drug consultation.
  • Expert system for first aid support.
  • Expert system for the interpretation of fundus fluorescein angiograms.

Decision Support Systems

The group has developed several systems for assisting humans on taking decisions on various non-trivial problems, focussing on the following decision making methodologies:

  • Expert Systems (see above)
  • Multi-criteria methodology
  • Decision trees
  • Neural networks

Logistics

The goal is to develop a real time, general-purpose logistics tool for the management of natural and human resources. The system must exhibit real time behavior and be able to scale up in order to be applied in large and complex environments. The aim of this research is also to bring together common AI technologies like Planning, Scheduling and Optimization, among with other research directions like Operational Research.

e-Commerce, e-Business

e-Commerce (Electronic Commerce) is a general concept covering any for of business transaction or information exchange executed using information communication technology, between companies, between companies and their customers, or between companies anApril 16, 2005g of goods, services and electronic (digital) material. The development and use of e-commerce is growing at a rapid rate not only in business but also in cultural, governmental and educational environments. e-Commerce is one of today’s buzzwords and as such our research team couldn’t ignore it. Evaluation, testing and development of prototype e-commerce sites using widespread commercial products are our main concerns.

e-Learning

The great interest on using the WWW as a universal medium for accessing educational resources, gave birth to various coordinated efforts for the standardization of the various aspects related to education. The two most important of these efforts are related to the definition of metadata describing educational resources and metadata describing the learner. Under the light of these emerging efforts, we investigate knowledge based approaches on organizing and accessing educational resources. We aim at advanced tools that facilitate client-side learners to access educational resources in a way tailored to their individual profile and educational needs, and dynamic course generation based on fine grained educational resources.

Intelligent Web Information Systems

The goal is to develop Web information systems with content that is dynamically computed using declarative, logic-based query languages. In order to achieve this traditional Web content must be represented using AI knowledge representation formalisms such as conceptual graphs, objects, or frames.

Intelligent Geographical Information Systems (GIS)

The goal is to develop Intelligent Geographical Information Systems that combine intelligent knowledge-based, data mining and planning techniques with the visualization power of digital maps. Some of the projects that the group has been involved led to the development of an Intelligent GIS for Land Evaluation and an Intelligent GIS for Logistics.

Ambient Intelligence

Research in this area is focused on smart environments, which are equipped with a sensor network that monitors environmental parameters (luminance, temperature, humidity, CO2 emmisions, smoke presence e.t..c. ), power consumption (electric power, oil consumption) and other parameters (e.g. presence of humans, computer usage e.t.c.). The data that is collected is then analyzed by a monitoring agent, deploying AI planning techniques, that automatically controls a number of devices (lighting, heating, e.t.c.), in order to provide the habitants of the environment with personalized settings, automate every day proccesses and minimize the total power consumption of the environment. More details about this initiative can be found in the Smart IHU web page