Digital repository of Slovenian research organisations

Search the repository
A+ | A- | Help | SLO | ENG

Query: search in
search in
search in
search in

Options:
  Reset


Query: "author" (Pi��kur Mitja) .

11 - 20 / 286
First pagePrevious page12345678910Next pageLast page
11.
Building a Citizen science network in Slovenia : 2. stručni skup Suradnja, izgradnja, nadogradnja s međunarodnim sudjelovanjem – Volonteri u knjižnicama, Virovitica, 29. 9. 2023
Mitja Vovk Iskrić, 2023, unpublished conference contribution

Published in DiRROS: 13.02.2024; Views: 120; Downloads: 82
.pdf Full text (410,37 KB)
This document has many files! More...

12.
13.
14.
15.
16.
Simultaneous determination of free biliverdin and free bilirubin in serum : a comprehensive LC-MS approach
Alen Albreht, Mitja Martelanc, Lovro Žiberna, 2024, original scientific article

Published in DiRROS: 18.12.2023; Views: 159; Downloads: 72
.pdf Full text (1,74 MB)
This document has many files! More...

17.
SONAR, a nursing activity dataset with inertial sensors
Orhan Konak, Lucas Liebe, Kirill Postnov, Franz Sauerwald, Hristijan Gjoreski, Mitja Luštrek, Bert Arnrich, 2023, short scientific article

Abstract: Accurate and comprehensive nursing documentation is essential to ensure quality patient care. To streamline this process, we present SONAR, a publicly available dataset of nursing activities recorded using inertial sensors in a nursing home. The dataset includes 14 sensor streams, such as acceleration and angular velocity, and 23 activities recorded by 14 caregivers using five sensors for 61.7 hours. The caregivers wore the sensors as they performed their daily tasks, allowing for continuous monitoring of their activities. We additionally provide machine learning models that recognize the nursing activities given the sensor data. In particular, we present benchmarks for three deep learning model architectures and evaluate their performance using different metrics and sensor locations. Our dataset, which can be used for research on sensor-based human activity recognition in real-world settings, has the potential to improve nursing care by providing valuable insights that can identify areas for improvement, facilitate accurate documentation, and tailor care to specific patient conditions.
Keywords: nursing documentation, nursing activities, SONAR, sensors
Published in DiRROS: 11.12.2023; Views: 200; Downloads: 102
.pdf Full text (1,62 MB)
This document has many files! More...

18.
HARE : unifying the human activity recognition engineering workflow
Orhan Konak, Lucas Liebe, Kirill Postnov, Franz Sauerwald, Hristijan Gjoreski, Mitja Luštrek, Bert Arnrich, 2023, original scientific article

Abstract: Sensor-based human activity recognition is becoming ever more prevalent. The increasing importance of distinguishing human movements, particularly in healthcare, coincides with the advent of increasingly compact sensors. A complex sequence of individual steps currently characterizes the activity recognition pipeline. It involves separate data collection, preparation, and processing steps, resulting in a heterogeneous and fragmented process. To address these challenges, we present a comprehensive framework, HARE, which seamlessly integrates all necessary steps. HARE offers synchronized data collection and labeling, integrated pose estimation for data anonymization, a multimodal classification approach, and a novel method for determining optimal sensor placement to enhance classification results. Additionally, our framework incorporates real-time activity recognition with on-device model adaptation capabilities. To validate the effectiveness of our framework, we conducted extensive evaluations using diverse datasets, including our own collected dataset focusing on nursing activities. Our results show that HARE’s multimodal and on-device trained model outperforms conventional single-modal and offline variants. Furthermore, our vision-based approach for optimal sensor placement yields comparable results to the trained model. Our work advances the field of sensor-based human activity recognition by introducing a comprehensive framework that streamlines data collection and classification while offering a novel method for determining optimal sensor placement.
Keywords: human activity recognition, multimodal classification, privacy preservation, real-time classification, sensor placement
Published in DiRROS: 11.12.2023; Views: 190; Downloads: 73
.pdf Full text (6,40 MB)
This document has many files! More...

19.
20.
The LANDSUPPORT geospatial decision support system (S-DSS) vision : operational tools to implement sustainability policies in land planning and management
Fabio Terribile, Marco Acutis, Antonella Agrillo, Erlisiana Anzalone, Sayed Azam-Ali, Marialaura Bancheri, Peter Baumann, Barbara Birli, Antonello Bonfante, Marco Botta, Mitja Ferlan, Jernej Jevšenak, Primož Simončič, Mitja Skudnik, 2023, original scientific article

Abstract: Nowadays, there is contrasting evidence between the ongoing continuing and widespread environmental degradation and the many means to implement environmental sustainability actions starting from good policies (e.g. EU New Green Deal, CAP), powerful technologies (e.g. new satellites, drones, IoT sensors), large databases and large stakeholder engagement (e.g. EIP-AGRI, living labs). Here, we argue that to tackle the above contrasting issues dealing with land degradation, it is very much required to develop and use friendly and freely available web-based operational tools to support both the implementation of environmental and agriculture policies and enable to take positive environmental sustainability actions by all stakeholders. Our solution is the S-DSS LANDSUPPORT platform, consisting of a free web-based smart Geospatial CyberInfrastructure containing 15 macro-tools (and more than 100 elementary tools), co-designed with different types of stakeholders and their different needs, dealing with sustainability in agriculture, forestry and spatial planning. LANDSUPPORT condenses many features into one system, the main ones of which were (i) Web-GIS facilities, connection with (ii) satellite data, (iii) Earth Critical Zone data and (iv) climate datasets including climate change and weather forecast data, (v) data cube technology enabling us to read/write when dealing with very large datasets (e.g. daily climatic data obtained in real time for any region in Europe), (vi) a large set of static and dynamic modelling engines (e.g. crop growth, water balance, rural integrity, etc.) allowing uncertainty analysis and what if modelling and (vii) HPC (both CPU and GPU) to run simulation modelling ‘on-the-fly’ in real time. Two case studies (a third case is reported in the Supplementary materials), with their results and stats, covering different regions and spatial extents and using three distinct operational tools all connected to lower land degradation processes (Crop growth, Machine Learning Forest Simulator and GeOC), are featured in this paper to highlight the platform's functioning. Landsupport is used by a large community of stakeholders and will remain operational, open and free long after the project ends. This position is rooted in the evidence showing that we need to leave these tools as open as possible and engage as much as possible with a large community of users to protect soils and land.
Keywords: land degradation, land management, soil, spatial decision support system, sustainability
Published in DiRROS: 13.11.2023; Views: 313; Downloads: 155
.pdf Full text (4,42 MB)
This document has many files! More...

Search done in 0.38 sec.
Back to top