Innovation through applied research and development

We currently work on applied research and development projects not only to serve our customers but also to develop our own product lines. Our goal is to apply AI in different fields and provide value in the world.

Decision support system

The main target of our decision support system is the timely support on decisions to the identified situations that will reason about the appropriate reactions to the situations at hand. It also provides an automated adaptation of response processes depending on contextual factors. AI decisions have remained a black-box for a long time. The main focus in our decision support system is the use of explainability in the core (XAI). One of our research projects INCISIVE is focused on classifying cancer images and explaining the patterns found to the user for better understanding. In addition, credit reports produced in one of our solutions provide a holistic assessment explained to risk officers.

Data curation and annotation platform

Data curation is one of the most important parts, in order to organize and integrate data collected from various sources. Data used for training of models need to be unbiased and result to robust results. Our data curation platform includes semi and auto annotation mechanisms for text and images in order to help in the annotation process. In our reserach projects some of the fields we are currently using this technology are cancer image annotation and classification at INCISIVE, crime scene and object classification at LAW-GAME and soil assessment at DRYADS.

Early warning system

We have developed a prototype of an early warning system to analyze incoming data and trigger warnings and alerts through a continous monitoring process. Through an automated procedure for anomaly detection, the system can use pre-trained data combined with specified rules to give robust results in real-time. Currently, a part of this system is used at STAMINA and DRYADS.

Digital twins tools

We are currently investigating the path of digital twins and how innovative technologies can move this domain further. As robotics expands in parallel with AI, there is a need for obtaining enhanced knowledge from a digital twin system. Optimization is an important aspect. A prediction coming from an AI model in combination with a digital twin can lead to understanding the effects of using different components in a system or replacing the existing ones.

Graph financial analytics

Big data has been a very interesting topic the last few years. Linking all this data with a scalable manner is now a challenge. We research new ways of connecting all the data together in order to find relations, patterns and conclude to results. The graph data science techniques are used on financial data to provide insights. Through these techniques we investigate fraud detection and bank transactions’ classification. We also have implemented our scoring system.

Web and social analytics platform

Our web and social analytics platform is based on AI. We use the part of sentiment analysis from our natural language classification engine in order to create our analytics. This results in contextually understanding data and providing accurate, actionable insights that are explainable to the end-user. Currently, we research for new features and improvements of this platform through STAMINA.

_ Cancer research

INCISIVE - An AI-powered cancer image repository for diagnosis, prediction and follow-up

INCISIVE aims to address three major open challenges in order to explore the full potential of AI solutions in cancer imaging: AI challenges unique to medical imaging, image labelling and annotation and data availability and sharing. In order to do that INCISIVE partners will develop an automated-ML based annotation mechanism to rapidly produce training data for machine learning research and and a pan-European federated repository of medical images, that will enable the secure donation of data in compliance with ethical, legal and privacy demands. This will increase accessibility to datasets and enabling experimentation of AI-based solutions.

_ Pandemics

STAMINA - Intelligent decision support for pandemics through linked data

STAMINA develops an intelligent decision support toolset for pandemic prediction and management. STAMINA enables national planners and first responders to anticipate and respond to the the “known-unknowns” in their daily effort to enhance health security. Main functionality of the toolset includes, among others: Real-time web and social media analytics aiming at public trust monitoring and flagging possible disease outbreak. Predictive modeling of pandemic outbreak and its impact, along with decision-making support in implementing mitigation strategies. Early warning system for first responders.

_ Fight against criminality

LAW-GAME - An Interactive, Collaborative Digital Gamification Approach to Effective Experiential Training and Prediction of Criminal Actions

The aim of LAW-GAME is to train police officers’ on the procedure, through gamification technologies in a safe and controlled virtual environment. Essential tasks during the creation of LAW-GAME serious game are to virtualise and accurately recreate the real world. In this project, core competencies will be developed performing intelligence analysis, through a series of AI-assisted procedures for crime analysis and prediction of illegal acts.

_ Fight against threats to the Environment

DRYADS - A Holistic Fire Management Ecosystem for Prevention, Detection and Restoration of Environmental Disasters

DRYADS aims to build upon state-of-the-art high TRL products and unite them in a holistic Fire Management platform that optimizes and reuses the available Socio-technological Resources in all three main phases of Wildfires. For the prevention and preparedness, DRYADS proposes the use of a real-time risk evaluation tool, that can receive multiple classification inputs and work with a new proposed neural network-powered Risk factor indicator. Many different methods, materials and technological equipment will be used, such as alkali activated construction materials (AAM), integrating post-wildfires wood ashes (PWA), Copernicus infrastructure, a swarm of small drones, wearables for the protective equipment, UAV (drones), UAG and airships. Last but not least, DRYADS will build a new innovative land and field-based restoration initiative.

_ Financial literacy and sustainability

PLOUTOS - Cooperation for achieving third country nationals' financial independence through financial literacy tools and entrepreneurship bootcamps

PLOUTOS aims to improve TCN's access to financial services via different training and practical prospects. The training prospect is based on two training courses. The first one is financial literacy and sustainability, supported by a relevant language course. The second one is a training course on community interpreting offered to people already offering this service without having had any professional training. The practice prospect is based on a business program enabling practical training of TCNs in applying their financial literacy skills on the job. Finally, a Multi-lingual one-stop-shop platform will be developed, offering TCNs access to microfinance in any European country through the 96 members of the European Microfinance Network, lifting language, cultural and administrative burdens.

Use the form below to send us a message