Filters
cris logo
-
New search Filters
Select from list
Displayed from Show more
You have reached the maximum number of displayed search results.
All results displayed
No results are available for the search performed
Displayed from
You have reached the maximum number of displayed search results.
All results displayed
Loading results
Obtaining statistical data

Projects / Programmes source: ARIS

Predictive analytics based on location-associated context enrichment

Edit
Research activity

Code Science Field Subfield
2.07.00  Engineering sciences and technologies  Computer science and informatics   

Code Science Field
T120  Technological sciences  Systems engineering, computer technology 

Code Science Field
1.02  Natural Sciences  Computer and information sciences 
Keywords
data fusion, context recognition, predictive analytics, geospatial analysis, computer science
Evaluation (rules)
source: COBISS
Evaluation of bibliographic research performance indicators according to ARIS methodology
Citations Citations for bibliographic records in COBIB.SI that are linked to records in citation databases
source: WoS source: Scopus source: COBISS
Researchers (17)
no. Code Name and surname Research area Role Period No. of publications
1.  37956  PhD Marko Bizjak  Computer science and informatics  Researcher  2018 - 2020  42 
2.  37447  PhD David Jesenko  Computer science and informatics  Researcher  2017 - 2019  46 
3.  37672  PhD Simon Jurič  Computer science and informatics  Researcher  2017 - 2020  24 
4.  16259  PhD Simon Kolmanič  Computer science and informatics  Researcher  2017 - 2020  191 
5.  33709  PhD Niko Lukač  Computer science and informatics  Researcher  2017 - 2020  202 
6.  33103  PhD Sebastjan Meža  Civil engineering  Researcher  2017 - 2019  42 
7.  29243  PhD Domen Mongus  Computer science and informatics  Head  2017 - 2020  278 
8.  05892  PhD Dalibor Radovan  Geodesy  Researcher  2017 - 2020  541 
9.  28150  Blaž Repnik  Computer science and informatics  Researcher  2017 - 2020  32 
10.  08638  PhD Krista Rizman Žalik  Computer science and informatics  Researcher  2017 - 2020  186 
11.  52889  Tadej Stošić  Computer science and informatics  Researcher  2019 - 2020  0 
12.  26035  PhD Denis Špelič  Computer science and informatics  Researcher  2017 - 2018  62 
13.  23564  PhD Mihaela Triglav Čekada  Geodesy  Researcher  2017 - 2020  328 
14.  52197  Dino Vlahek  Computer science and informatics  Researcher  2019 - 2020  8 
15.  06671  PhD Borut Žalik  Computer science and informatics  Researcher  2017 - 2020  851 
16.  31475  Denis Žganec  Computer science and informatics  Technical associate  2017 - 2020  18 
17.  33994  PhD Danijel Žlaus  Computer science and informatics  Junior researcher  2017 - 2020  23 
Organisations (2)
no. Code Research organisation City Registration number No. of publications
1.  0246  Geodetic Institute of Slovenia  Ljubljana  5051649000  1,875 
2.  0796  University of Maribor, Faculty of Electrical Engineering and Computer Science  Maribor  5089638003  27,543 
Abstract
With the paradigm shift towards data-driven decision-making, increasingly more investments are being made into data acquisition technologies. Programmes like Copernicus, GEOSS, and Galileo, together with the Internet of Things enabled devices, are daily generating huge amounts of sensory data that are becoming widely accessible through open data initiatives and open interoperability standards. These not only provide us with the opportunity to observe the natural processes at high spatiotemporal resolution, but also enable us to monitor the causal relationships that are driving them. Due to the complexity of interactions within and amongst natural processes and their relations to human activities, extraction of this so-called contextual information has only now become possible. The proposed project addresses contemporary challenges of structured context representation within the fusion of heterogeneous geospatial data sources and streams. Two complementary research directions are foreseen for this purpose, namely Context extraction, where spatiotemporal analytics, based on the concepts of computational geometry, topology, and geospatial statistics, shall be investigated in order to introduce new approaches to the recognition of contextual relations and their structured representation, and Context utilisation for predictive analytics, where new methodologies for the integration of structured contextual information shall be researched in order to advance in the accuracy of the contemporary environmental simulations, regression models and tools for visual analytics. With the key supporting software components already available from our previous projects, additional advances over the current state-of-the-art shall be achieved by the introduction of a new process-centered data fusion model that shall allow for efficient integration of analytics algorithms and their chaining when performing high-level fusion/prediction tasks. In order to concretise the developments, research activities shall be governed by two project pilots: Predictions of microclimate parameters are often predisposed to the context relations between the geospatial entities. The presence of vegetation, for example, influences humidity levels and temperatures in its neighbourhood heavily, while it also requires different turbulence models to be used when simulating the winds. As many environmental services and smart applications rely on these types of predictions, particularly in relation to Smart City concepts, the proposed pilot has the potential to provide several vital, yet currently missing, analytics components. Prediction of geomorphological changes caused by running water and floods, where structured context representation shall be utilised to support the definition of otherwise too complex physical relations to be modelled mathematically. Predicting an increase in water height levels and related soil erosion in regard to a given volume of rainfall, for example, requires complete understanding of the watershed, as well as exact definitions of the physical characteristics of the ground materials. On the other hand, contextual information extracted by assessing geospatial correlations within past events can provide a simplified regression model, the accuracy of which still exceeds our current capabilities. Advances in this field are particularly important for Slovenia, as soil erosion and floods are amongst those climate change related disasters from which Slovenia has suffered greatly in the past. For the reasons given above, the proposed project is well aligned with the Slovenian Smart Specialisation Strategy, where technologies for efficient exploitation of Earth Observation data are exposed explicitly amongst key enablers of Slovenia’s socioeconomic growth and well-being of its citizens.
Significance for science
PLACE addresses one of the key challenges in Geospatial Analytics and Computer Science in general by proposing a new data fusion model with particular focus on context extraction from heterogeneous data sources and streams. While the importance of the context has already been demonstrated by numerous methods, our preliminary analysis of the state-of-the-art showed that there is no systematic approach for dealing with contextual information within data fusion. All up-to-date works related to the discovery of hidden contextual relations and their structuring was done only at the conceptual level or in strictly limited application domains. The proposed research has, therefore, the potential to introduce a new methodological concept that is expected to become increasingly important with recent technological trends and developments. Namely, deployment of global Earth Observation systems (such as Copernicus and GEOSS), Internet-of-Things, and GNSS (such as Galileo) are just some of the global activities that shall drive the demand for predictive analytics in the future by supplying vast amount of geospatial data, rich with contextual information. From a Computer Science perspective, we plan to demonstrate the efficiency of theoretical conceptualisation of context from methodological (e.g. environmental simulations), as well as application perspectives (e.g. water damage assessment). While the former shall be achieved by integrating context into targeted algorithms, the latter shall be demonstrated by concrete geospatial analytics applications. We thus expect that PLACE shall provide a referential foundation (i.e. data fusion model, capable of extracting and utilising context in different application domains, ranging from prediction of climate change parameters to assessment of geomorphological changes), motivating researchers to adapt these algorithms further, develop new ones and utilise the PLACE data fusion model to improve accuracy, efficiency, and generality of the contextually enriched location-associated predictive analytics, for instance, probabilistic and assemble forecasting. Furthermore, the developed pilot applications shall provide researchers with the opportunity to conduct their own in-depth environmental studies. Amongst others, the following key research collaborations outside of the primary scope of the project have already been identified: A propagation of dust particles in an urban environment based on environmental simulations shall be conducted with the National Laboratory of Health, Environment and Food, and An assessment of rock glaciers on regression models in collaboration with the Research Centre of the Slovenian Academy of Sciences and Arts, Anton Melik Geographical Institute. In accordance with the dissemination strategy, we shall seek for new research collaboration opportunities for PLACE utilisation. Prediction of energy production and consumption needs could be one attractive extension.
Significance for the country
PLACE data fusion services shall be delivered by extending a well-established open source platform for accessing and processing geographic data (e.g. Geoserver). This will ensure full scalability, extendibility, and interoperability of the proposed project’s deliverables and their compliance with the OGC (Open Geospatial Consortium) Standards, as well as the EU INSPIRE Directive, thus, allowing their straightforward integration. In order to ensure long-term exploitation of deliverables, the PLACE concept is aligned with relevant national research and innovation policies. Slovenia’s Smart Specialisation Strategy S4 is the main driving force behind the PLACE concept. PLACE relates directly to one of the key enabling technologies on which Slovenia intends to build its economic growth and wellbeing of citizens in future, i.e. Geographic Information Systems and Technologies (GIS-T). The Project Leader coordinates the GIS-T activities of the S4 priority area - Smart Cities and Communities within the National Strategic Development and Innovation Partnership (SRIP).  SRIP joins all relevant Slovenian research organisations, policy makers and over 160 Slovenian companies. Through this partnership, the PLACE team intends to bring about the following impacts: Contributions to the GIS-T sector by addressing those currently missing analytical components that, as recognised by the community, have the potential to extend the sectorial market. PILOT 1 is designed for this purpose, where accurate predictive analytics of microclimate parameters are essential in support of many Smart City services. Energy management systems that require prediction of user needs (e.g. as a consequence of micro-level changes in temperatures) and production capacities (e.g. photovoltaic electricity) in order to balance energy flows efficiently within the city is just one of many examples. Contributions to the public administration are targeted by PILOT 2. As recognised by the Administration for Civil Protection and Disaster Relief (a partner in SRIP), Slovenia is particularly vulnerable to floods. Only in the last 10 years, flood related damage in Slovenia exceeded €850M. By the assessment of geomorphological changes caused by the water streams and floods, new information layers shall be generated, offering analytics support in design of solutions within the decision- making process. Contribution to the public infrastructure shall be achieved by installing a prototype PLACE platform within the public collaborative research infrastructure of SRIP with the intention to enable start-ups, spin-offs and other SME’s to conduct their innovation experiments and build new services. For the above given reasons, over 20 SMEs in GIS-T have already expressed their interest in PLACE data products and analytics services for development of new smart applications. We commit ourselves further to search for new partnership by appointing a Knowledge Transfer Manager.
Most important scientific results Interim report, final report
Most important socioeconomically and culturally relevant results Interim report, final report
Confirmation required
Views history
Favourite