Abstract

The amount of data generated by Earth Observation Systems is in general huge compared with the capacities of the data management and processing technologies. Currently, complex data acquisition infrastructures maintained by public administrations are complemented with initiatives based on the collaboration of citizens at large scale (mobile crowdsensing, social media, etc.). Apart from their volume, main characteristics of the generated data are their heterogeneity and the lack of appropriate metadata. Those characteristics hinder data integration processes, data reuse in applications with non-expert users and the development of general-purpose components that might be reused in many domains. In this talk, we will: i) introduce uses cases with environmental data sources that arise in the scope of different projects, ii) briefly review solutions related to the management of the geospatial and temporal dimensions, and to the semantics commonly present in environmental datasets, iii) describe solutions and future plans related to the integration of environmental datasets, both in mediation and data warehouse architectures and iv) outline future research directions related to the searching and interactive exploration of very large integrated and smart environmental datasets.

Bio

José R.R. Viqueira is Associate Professor at the Department of Electronics and Computer Science of the USC. Besides, he is founding member of the COGRADE (Computer Graphics and Data Engineering) research group of the USC and he is member of the research staff of the Centro Singular de Investigación en Tecnoloxías Intelixentes (CITIUS). His current research lines are related to the management of very large scientific data sets, with special emphasis on spatio-temporal and sensor data. He obtained a master (1998) and a PhD (2003) in Computer Science at the University of A Coruña. Since 1998 has been involved in research works related to spatial and spatio-temporal data management, with special relevance in GIS applications and also in sensor data management. He is author of many research papers in journals and conferences related to data management and geosciences. He has participated and leaded competitive research projects of regional, national, and international scope and he participated and leaded technology transfer activities with both companies and public administration, including the creation of a Spin-off that is active since 2003.

Abstract

With the standardization of Electronic Health Records in hospitals and mandatory requirement for data preservation, healthcare data reached unprecedented scale and scope, offering both opportunities and challenges to practitioners, regulators and researchers. Community network analysis emerged as a promising trend and technology for mining large scale health dataset. In its simple form, social network analysis aims to identify communities of nodes that are similar to each other according to some similarity criteria. Nevertheless, the research gets widen when considering the various entities that can be assigned to nodes, ranging from named-entities (e.g., patients, organization, locations) to abstract structures inferred from original data, as well as the potentially high number of attributes associated to a single node (i.e., age, gender, interest), which builds a bridge to the concept of “attributed community” that balances network topology with attribute similarity. This talk reviews the state-of-the art in this field of community-based mining in healthcare, highlighting the state-of-the-art, challenges and promising directions in the field. At the same time some ongoing works in the field as part of DigiHealth Oulu, will be scrutinized. Growing issues of explainability and computational affordability will be investigated.

Bio

Dr. Mourad Oussalah is a Research Professor in University of Oulu, Faculty of Information Technology and Electrical Engineering, Centre for Machine Vision and Signal Analysis, where he leads the Social Mining Research Group. He is also affiliated with Medical Imaging, Physics and Technology Unit of the Faculty of Medicine as part of Academy of Finland DigiHealth Project. Prior joining University of Oulu, he was with the University of Birmingham, UK from 2003-2016. He also held research positions at City University of London and KU Leuven in Belgium, and Visiting Professor position in University of Evry Val Essonnes of France (summer 2006), New Mexico of USA (summer 2009) and Xian University of China (Fall 2018).

Dr. Oussalah research has concentrated mainly on information and data fusion, text mining, information retrieval and uncertainty handling where he published more than 250 international publications and supervised a dozen of PhD students and more than 40 Msc students, provided more than 20 keynote talks at international conferences and served as PC members of more than 60 international conferences. He is a Fellow of Royal Statistical Society and Senior member of IEEE and acted as executive of IEEE SMC UK & Ireland Chapter from 2002 till 2016.

Dr. Oussalah is also leading and participating into several EU projects including YoungRes (#823701) (2019-2021) on Youth polarization, WaterLine (2021-2024) on Soil Moixture Analysis, Prince (#815362) (2019-2022) on CBRNE incidents, Cutler (#770469) on Coastal Urban development, IPaWa (2019-2022) on smart parking, CBC Karelia (Finland-Russia) on IoT Business Creation (2018-2020), Grage –Marie Skłodowska-Curie action (ID:645706) (2016-2018) on active ageing and elderly living in urban settings, COST Action on Linked Data. Academy of Finland DigiHealth (2020-2024). He also secured funding from several foundations (e.g., Finnish Cancer Research, Nokia and Nuffield foundations).