UPRC (University of Piraeus Research Center) has been actively engaged and coordinated plenty of EU funded R&D projects as well as National R&D projects funded by the Greek Ministry of Development and the General Secretariat of Research and Technology. Due to the involvement of numerous research projects, UPRC team brings significant expertise and knowledge in data management, IoT and cloud services as well as machine learning engineering and applications.
UPRC consists of members with diverse and multidisciplinary expertise. More specifically DaC (Data & Cloud research group) members innovate by addressing research challenges across several data and cloud computing domains. UPRC research activities and outcomes are reflected in several respective publications with a respectable number of citations.
DaC members collaborate with universities, distinguished IT companies, and research centers inside and outside Greece for the creation and implementation of innovative information systems and software mechanisms. With an extensive scientific background in Data Management and analytics, the UPRC members deliver innovations through cutting-edge data management approaches across the data path and through advanced machine and deep learning techniques.
In iHelp project, the UPRC team has been involved in research and development activities in the field of eHealth with a special focus on (i) project management and coordination (ii) electronic health records homogenization, cleaning, standardization, and qualification, and (iii) explainability of machine learning-based outcomes and recommendation that will be served to the users of the platform through visual analytics dashboards.
“Diversity and variety of data, their huge volume, and thus processing and analysis of these data become more and more complex and difficult procedures. Collection, quality estimation, as well as the interpretation and the harmonization of the data, that derive from the existing huge amounts of heterogeneous medical devices and data sources, face a dramatic increase of interest in the healthcare domain. We seek to assure the incoming data accuracy, integrity, and quality, as well as to provide an automated structure mapping mechanism between various data resources.” George Manias, Associate Researcher
“Large collections of electronic health record (EHR) data and technical advances in machine learning (ML) have aroused the growth of research interest in developing ML-based clinical decision support systems. Despite the recognition of the importance of machine learning in healthcare, obstacles to further adoption in real healthcare settings remain due to the black-box nature of ML. Therefore, there is an emerging need for explainable AI (XAI) frameworks, which allow end-users to evaluate the ML model’s decision-making. We intend to enhance iHelp decision support tool with XAI functionality in order to enhance transparency and trustworthiness in machine learning-based predictions.” George Marinos, Associate Researcher