1661. |
1662. Preverjanje verjetnostne napovedi sanitarnega poseka smreke zaradi podlubnikov v Sloveniji v 2023Nikica Ogris, Maarten De Groot, 2023, drugi znanstveni članki Povzetek: Preverili smo zanesljivost verjetnostne napovedi sanitarnega poseka smreke zaradi podlubnikov v Sloveniji v 2023. Verjetnostni model za napoved sanitarnega poseka smreke zaradi podlubnikov je potrdil visoko zanesljivost (AUC modela = 0,89, AUC napovedi = 0,84). Ugotovili smo optimalni prag za verjetnost sanitarnega poseka, ki ga bomo lahko uporabili pri naslednjih napovedih za bolj jasno določitev območij, kjer se bodo potencialno pojavila žarišča smrekovih podlubnikov. Napoved za leto 2023 smo naredili s pragom 0,30, ki pa se je izkazal za prenizkega, saj je bila kar tretjina modelskih celic lažno pozitivnih. Optimalen prag za verjetnostni model v letu 2023 je bil 0,40. Povprečen optimalen prag v obdobju 2020–2023 je bil 0,45, ki ga predlagamo za izdelavo verjetnostne napovedi v naslednjem letu. Ključne besede: gozdovi, varstvo gozdov, navadna smreka, Picea abies, sanitarni posek, napoved, ogroženost, model, validacija, zmogljivost, zanesljivost, točnost, natančnost, AUC, občutljivost, specifičnost Objavljeno v DiRROS: 11.12.2023; Ogledov: 442; Prenosov: 164
Celotno besedilo (791,14 KB) Gradivo ima več datotek! Več... |
1663. |
1664. Usposabljanje BTSF: Izbruhi škodljivih organizmov – načrti izrednih ukrepov za prednostne škodljive organizme, Bratislava, oktober 2023Simon Zidar, Eva Groznik, 2023, poljudni članek Ključne besede: gozdovi, Varstvo gozdov, zdravje rastlin, načrt izrednih ukrepov, simulacijska vaja, prednostni škodljiv organizem, BTSF Objavljeno v DiRROS: 11.12.2023; Ogledov: 408; Prenosov: 182
Celotno besedilo (531,83 KB) Gradivo ima več datotek! Več... |
1665. Using the IUCN environmental impact classification for alien taxa to inform decision-makingSabrina Kumschick, Sandro Bertolino, Tim M. Blackburn, Giuseppe Brundu, Katie E. Costello, Maarten De Groot, Thomas Evans, Belinda Gallardo, Piero Genovesi, Tanushri Govender, 2023, izvirni znanstveni članek Povzetek: The Environmental Impact Classification for Alien Taxa (EICAT) is an important tool for biological invasion policy and management and has been adopted as an International Union for Conservation of Nature (IUCN) standard to measure the severity of environmental impacts caused by organisms living outside their native ranges. EICAT has already been incorporated into some national and local decision-making procedures, making it a particularly relevant resource for addressing the impact of non-native species. Recently, some of the underlying conceptual principles of EICAT, particularly those related to the use of the precautionary approach, have been challenged. Although still relatively new, guidelines for the application and interpretation of EICAT will be periodically revisited by the IUCN community, based on scientific evidence, to improve the process. Some of the criticisms recently raised are based on subjectively selected assumptions that cannot be generalized and may harm global efforts to manage biological invasions. EICAT adopts a precautionary principle by considering a species’ impact history elsewhere because some taxa have traits that can make them inherently more harmful. Furthermore, non-native species are often important drivers of biodiversity loss even in the presence of other pressures. Ignoring the precautionary principle when tackling the impacts of non-native species has led to devastating consequences for human well-being, biodiversity, and ecosystems, as well as poor management outcomes, and thus to significant economic costs. EICAT is a relevant tool because it supports prioritization and management of non-native species and meeting and monitoring progress toward the Kunming–Montreal Global Biodiversity Framework (GBF) Target 6. Ključne besede: biological invasions, evidence synthesis, impact assessment, managing invasive species, precautionary principle Objavljeno v DiRROS: 11.12.2023; Ogledov: 467; Prenosov: 278
Celotno besedilo (537,44 KB) Gradivo ima več datotek! Več... |
1666. PS-AAS : portfolio selection for automated algorithm selection in black-box optimizationAna Kostovska, Gjorgjina Cenikj, Diederick Vermetten, Anja Janković, Ana Nikolikj, Urban Škvorc, Peter Korošec, Carola Doerr, Tome Eftimov, 2023, objavljeni znanstveni prispevek na konferenci Ključne besede: automated algorithm selection, portfolio selection, black box optimization Objavljeno v DiRROS: 11.12.2023; Ogledov: 464; Prenosov: 185
Celotno besedilo (1,90 MB) Gradivo ima več datotek! Več... |
1667. SONAR, a nursing activity dataset with inertial sensorsOrhan Konak, Lucas Liebe, Kirill Postnov, Franz Sauerwald, Hristijan Gjoreski, Mitja Luštrek, Bert Arnrich, 2023, drugi znanstveni članki Povzetek: 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. Ključne besede: nursing documentation, nursing activities, SONAR, sensors Objavljeno v DiRROS: 11.12.2023; Ogledov: 323; Prenosov: 172
Celotno besedilo (1,62 MB) Gradivo ima več datotek! Več... |
1668. HARE : unifying the human activity recognition engineering workflowOrhan Konak, Lucas Liebe, Kirill Postnov, Franz Sauerwald, Hristijan Gjoreski, Mitja Luštrek, Bert Arnrich, 2023, izvirni znanstveni članek Povzetek: 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. Ključne besede: human activity recognition, multimodal classification, privacy preservation, real-time classification, sensor placement Objavljeno v DiRROS: 11.12.2023; Ogledov: 411; Prenosov: 133
Celotno besedilo (6,40 MB) Gradivo ima več datotek! Več... |
1669. Evaluation of ash pozzolanic activity by means of the strength activity index test, frattini test and DTA/TG analysisSabina Dolenec, Vilma Ducman, 2018, izvirni znanstveni članek Povzetek: The pozzolanic activity of five different types of ash was studied using various direct and indirect methods. In addition to strength activity index (SAI) determination and the Frattini test, ash pozzolanicity was assessed via differential thermal and thermogravimetric analyses (DTA/TG) after curing for 7, 28 and 90 days. The results showed that, due to their respective mineralogical, chemical and physical characteristics, the ashes exhibited different levels of pozzolanic activity in terms of the amount of lime with which they could chemically bind, as well as reaction kinetics. Although SAI and Frattini test results were not in agreement in the case of some of the ashes, DTA/TG analysis revealed that a certain amount of portlandite was consumed, thus confirming the occurrence of a pozzolanic reaction. The results also showed that ashes with higher amounts of reactive SiO2 were more reactive, while those with higher BET surface areas displayed a faster pozzolanic reaction rate. Ključne besede: biomass ash, DTA/TG, fly ash, Frattini test, pozzolanic activity, SAI Objavljeno v DiRROS: 11.12.2023; Ogledov: 306; Prenosov: 151
Celotno besedilo (1,05 MB) Gradivo ima več datotek! Več... |
1670. Revitalised geotourism mining heritage potentials in the Posavje FoldsMateja Golež, 2018, izvirni znanstveni članek Povzetek: The territory of the Posavje Folds offers many geotourism potentials reflecting in particular in rich mining heritage. For a long time, local communities have considered them mainly in the context of local problems, but nowadays we may see individual examples of successful revitalization of cave chambers and mining structures. All that has given rise to fantastic stories about the mining wealth of the underground world and the mining heritage interpreted with modern approaches and new findings. In addition to managers and heritage owners, the revitalization process also includes scientists, artists, architects and educators who, each in their own way, contribute to a holistic perspective of the values of the past in light of contemporary understanding of this type of heritage. As a result, the territory has witnessed the revitalization of the medieval lead and silver mine Padež pri Laškem, the former Laško coal mine machine room, which was transformed into the Strojnica Gallery, and the polymineral mine Sitarjevec within the last five years. All mentioned examples are cases of abandoned mining activities with long-lasting mining tradition, which left an imprint in the area in terms of the diverse social structure of the population and in terms of town development, which also allows us to evaluate from a distance the contribution to the construction of the railway between Vienna and Trieste, which put these towns on the European map of centres of industrial significance in the mid-19th century. Trains that still connect the Austrian capital with the Adriatic coast may in future, in light of sustainable green tourism, attract curious guests to stop and linger a while, which is the ultimate goal of the attempts of local communities to revitalise mining heritage. Meanwhile, the goals set can only be realised with the help of new and attractive tourist products that reflect own creativity related with tradition ranging from design ideas, music events, art installations, popular science evenings; in short, with contents that are suited to visitors of all ages. Ključne besede: mines, heritage, revitalisation, geoturism Objavljeno v DiRROS: 11.12.2023; Ogledov: 307; Prenosov: 119
Celotno besedilo (1,27 MB) Gradivo ima več datotek! Več... |