R&D Projects

Pluggable Platform for Personalised Multilingual Patent Search
Flexible REcommender Systems for Big Data
Multilingual and Multifaceted Interactive Information

Algorithms for Uncooperative Distributed Information Retrieval

Deep Learning Methods in Sentiment Analysis
Semantically Enhanced Browsing for Blind

Model for a European Networked University for e-learning

Competence development in International Oriented Companies

Competence development in International Oriented Companies

Virtual Student Exchanges


Pluggable Platform for Personalised Multilingual Patent Search (PerFedPat)

Position: proposer and Marie Curie Fellow
Funding obtained: approximately 230.000,00 €
Funding organisation: FP7/Research Executive Agency (REA)
Project URL: http://www.perfedpat.eu
Contact person: Prof. Michail Salampasis

The PerFedPat project aims to research into a new generation of advanced patent search systems for the patent related industries and the whole spectrum of patent users by designing a new exciting framework for integrating multiple patent data sources, patent search tools and UIs. The iPerFedPat system, which will be the main result of the project, will have a pluggable architecture, providing core services and operations being able to integrate multiple patent data sources and patent related data streams, thus providing multiple patent search tools and UIs while hiding complexity from the end user. At the core of the system’s architecture lies the idea of Personalised Federated Search. In iPerFedPat federated search is used as a method for retrieving information from distributed data sets into user’s workbench, possibly operate and/or integrate, and finally deliver to the patent users for using them in a parallel, coordinated way. As a result the iPerFedPat system will be able to provide a rich, personalised information seeking experience for different types of patent search types, potentially exploiting techniques from diverse areas such as distributed information retrieval, machine learning  and human-computer interaction.


Position: Leader
Funding : approximately 130.000,00 €
Funding organisation:  
Duration: 7/2018 – 7/2021
Contact person: Prof. Konstantinos Diamantaras

Recommender Systems are a fast-growing field of Information Mining that offers solutions to major marketing and advertising problems such as: finding new products that are likely to appeal to the user,  finding other users who have similar user preferences or could be friends of the user, finding products that probably like in groups of users.

The objectives of the project are divided into two categories, research and commercial. The research objectives include industrial research on the parallel and distributed implementation of a customized recommender system that will satisfy the needs of enterprises with very big volume data.  Commercial objectives include the development of an innovative software package that will implement the results of industrial research and also the implementation, testing and promotion of the product.

MUMIA (Multilingual and Multifaceted Interactive Information Access)

Position: proposer and Action Chair
Funding obtained: approximately 480.000,00 €
Funding organisation: European Cooperation in the field of Scientific and Technical Research/ COST.
Contact person: Prof. Michail Salampasis

The main objective of the Action is to coordinate and support the interaction and harmonization of high quality research at a European level in the field of multilingual and multifaceted interactive information access with a view to contribute to the development of next-generation search systems.

AUDIR (Algorithms for Uncooperative Distributed Information Retrieval)

Position: Scientist in charge
Funding obtained: 70.300,00 €
Funding organisation: General Secretariat of Research &   Technology
Project URL: http://erodios.it.teithe.gr/LCBF/
Contact person: Prof. Michail Salampasis

This research program aimed to investigate algorithms and strategies of source selection and results merging in distributed information retrieval systems and to incorporate these strategies in large scale, highly distributed, uncooperative information retrieval environments.

SeEBrowser (Semantically Enhanced Browsing for Blind People)

Position: Coordinator and Chief Scientist
Funding obtained: 54.000 €
Funding organisation: Greek Ministry of Education
Duration: 1.1.2004 – 31-8-2007
Contact person: Prof. Michail Salampasis

This research program aimed to improve Web accessibility for blind people by rationalising  their information seeking behaviour. The project has developed an open, extensible highly distributed generalised framework based on the Semantic Web which can be used to develop various accessibility applications.

Position: TEI Coordinator
Duration: November 2001 – December 2003
Project URL: http://www.hsh.no/menu
Contact person: Prof. Demosthenis Stamatis

The MENU project sets out to create a model for a European Networked (Virtual) University, providing a variety of e-learning opportunities. The model includes an organisational structure, a quality assurance system, examples of joint courses and study programmes across institutional borders, guidelines and a demonstrator of a practical e-learning environment.

CIOC (Competence development in International Oriented Companies)

Position: TEI Coordinator
Duration: January 2001 – December 2002
Contact person: Prof. Demosthenis Stamatis

The project contributed in the development of models for integration of organizational and competence development in knowledge based companies, having branches across Europe and aiming to train their employees through Open and Distance Learning. Siemens Metering/Norway acted as a specific test bench for adjusting and testing of such models.

DoODL (Dissemination of Open and Distance Learning)

Position: TEI Coordinator
Duration: September 1996- August 1998
Contact person: Prof. Demosthenis Stamatis

The aim of DoODL was to define models for collaboration between European academic institutions so they can function as centres for each other in the field of ODL.

VSX (Virtual Student Exchanges)

Contact person: Prof. Demosthenis Stamatis

Development of ICT based Synchronous and Asynchronous Open and Distance Learning courses in the context of the European program Netd@ys, in collaboration with Hogeschool Gent, Belgium


Duration: 2007-2010
Contact person: Prof. Demosthenis Stamatis

A new approach on different aspects of welfare, environment and food interactions in Central and Southeastern Europe with the use of ICT.The aim of the project is to use E-learning and ICT methods to achieve fast and sufficient training for target groups and end users, Leonardo Da Vinci Comunity Vocational Training Action Project.


Duration: 2004-2006
Contact person: Prof. Demosthenis Stamatis

Promoting quality assurance in animal WELfare – environment – FOOD quality interaction studies through upgraded eLearning


Position: TEI Coordinator
Duration: September 1998 – August 2000
Contact person: Prof. Demosthenis Stamatis

The objective of EuroCompetence was to develop and try out a flexible Open and Distance Learning model for further studies for adult learners. This model covered the need for competence among employees in Industry and Public sector that need to collaborate with other companies and institutions in Europe.)


Position: Leader
Funding: approximately 28.800,00 €
Duration: 4/2014 – 1/2015
Funding organisation: Subcontract from MSENSIS S.A.
Programme: ICT4Growth, Co-funded by the European Regional Development Fund (ERDF) and the Information Society S.A. (ΚΤΠ ΑΕ​)
Project URL: http://www.msensis.com​,​ http://ict4growth.ktpae.gr/​
Contact person: Konstantinos Diamantaras

The project aims are two-fold: (a) the development of a recommendation system for telecommunication service providers based on collaborative filtering techniques augmented with social information (web 2);
(b) the use of machine learning methods for the prediction of customer that may change provider (c​ust​omer churning prediction)

Deep Learning Methods in Sentiment Analysis

Position: Leader
Funding: approximately 49.000,00 €
Duration: 3/2014 – 12/2015
Funding organisation: Subcontract from MSENSIS S.A.
Programme: PAVET 2013, Co-funded by the European Regional Development Fund (ERDF) and the Greek Secretariat of Research and Technology (GSRT)
Project URL: http://www.msensis.com​,​ http://www.gsrt.gr​
Contact person: Konstantinos Diamantaras

The project ​goals are: (a) the analysis and implementation of state-of-the-art Deep Learning methods and Machine Learning methods, in general, for the sentiment analysis/opinion mining from unstructured (free) text. The target languages are Greek and English; (b) the ​optimum parametrization ​of the models, ​the ​vectorial representation of the ​words and the general pre-processing​ of​ the documents to be analyzed.