Publikationen


Suche nach „[Pagany] [Raphaela]“ hat 58 Publikationen gefunden
Suchergebnis als PDF
    DigitalAngewandte InformatikTC Freyung

    Beitrag (Sammelband oder Tagungsband)

    C. Hoermann, Raphaela Pagany, K. Kirchner, Wolfgang Dorner, M. Heurich, I. Storch

    Predicting the risk of deer-vehicle collisions by inferring rules learnt from deer experience and movement patterns in the vicinity of roads

    [Accepted for publication]

    Proceedings of the 2020 10th International Conference on Advanced Computer Information Technologies (ACIT) [September 6-8, 2020; Deggendorf]

    DigitalAngewandte InformatikTC Freyung

    Beitrag (Sammelband oder Tagungsband)

    Raphaela Pagany, Javier Valdés, Wolfgang Dorner

    Risk prediction of wildlife-vehicle collisions comparing machine learning methods and data use

    [Accepted for publication]

    Proceedings of the 2020 10th International Conference on Advanced Computer Information Technologies (ACIT) [September 6-8, 2020; Deggendorf]

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    C. Hoermann, Raphaela Pagany, K. Kirchner, Wolfgang Dorner, M. Heurich, I. Storch

    Predicting the risk of deer-vehicle collisions by inferring rules learnt from deer experience and movement patterns in the vicinity of roads

    2020 10th International Conference on Advanced Computer Information Technologies (ACIT), Deggendorf

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    Raphaela Pagany, Javier Valdés, Wolfgang Dorner

    Risk prediction of wildlife-vehicle collisions comparing machine learning methods and data use

    2020 10th International Conference on Advanced Computer Information Technologies (ACIT), Deggendorf

    DigitalAngewandte InformatikTC Freyung

    Zeitschriftenartikel

    J. Trager, L. Kalová, Raphaela Pagany, Wolfgang Dorner

    Warning apps for road safety – a technological and economical perspective for autonomous driving

    [Article submitted]

    International Journal of Human–Computer Interaction

    DigitalAngewandte InformatikTC Freyung

    Zeitschriftenartikel

    Raphaela Pagany

    Wildlife-vehicle collisions—Influencing factors, data collection and research methods

    [Article submitted]

    Biological Conservation

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    Raphaela Pagany

    Spatiotemporal risk prediction of wildlife-vehicle collisions

    IENE - Infrastructure and Ecology Network Europe, Évora, Portugal (conference postponed)

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    Raphaela Pagany

    Risk prediction on road—Exemplified for wildlife-vehicle collisions

    ESAR - Expert Symposium on Accident Research, Hannover (conference postponed)

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    C. Hoermann, Raphaela Pagany, F. Ossi, F. Cagnacci, Wolfgang Dorner, M. Heurich

    L‘ecologia del movimento e gli investimenti stradali: Un‘analisi a larga scala sul capriolo europeo (Capreolus capreolus)

    Workshop Wildunfälle in Südtirol - Incidenti stradali con la fauna selvatica in Alto Adige, Bozen, Italy

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    Simon Graf, Raphaela Pagany, Wolfgang Dorner, A. Weigold

    Georeferencing of Road Infrastructure from Photographs using Computer Vision and Deep Learning for Road Safety Applications

    5th International Conference on Geographical Information Systems Theory, Applications and Management, Heraklion, Greece

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    Raphaela Pagany, Alexander Faschingbauer, Simon Graf, Wolfgang Dorner

    Geoanalyse mit Methoden der Künstlichen Intelligenz - Datenaufbereitung, Homogenisierung und Anwendung am Fallbeispiel der (Wild-)Unfallprognose

    Posterpräsentation

    Fachsymposium Mobilität der Zukunft, Deggendorf

    DigitalAngewandte InformatikTC Freyung

    Vortrag

    Raphaela Pagany, Alexander Faschingbauer, Simon Graf, Wolfgang Dorner

    Geoanalyse mit Methoden der Künstlichen Intelligenz - Datenaufbereitung, Homogenisierung und Anwendung am Fallbeispiel der (Wild-)Unfallprognose

    Posterpräsentation

    AGIT Symposium & Expo 2019 - Angewandte Geoinformatik, Salzburg, Österreich

    DigitalMobilElektrotechnik und MedientechnikTC Freyung

    Beitrag (Sammelband oder Tagungsband)

    Simon Graf, Raphaela Pagany, Wolfgang Dorner, A. Weigold

    Georeferencing of road infrastructure from photographs using computer vision and deep learning for road safety applications

    Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management (GISTAM) [May 3-5, 2019; Heraklion, Greece], vol. Vol. 1

    DOI: 10.5220/0007706800710076

    MobilElektrotechnik und MedientechnikTC Freyung

    Zeitschriftenartikel

    Raphaela Pagany, Anna Marquardt, Roland Zink

    Electric Charging Demand Location Model—A User- and Destination-Based Locating Approach for Electric Vehicle Charging Stations

    Sustainability, vol. 11, no. 8

    DOI: 10.3390/su11082301

    Abstract anzeigen

    In recent years, with the increased focus on climate protection, electric vehicles (EVs) have become a relevant alternative to conventional motorized vehicles. Even though the market share of EVs is still comparatively low, there are ongoing considerations for integrating EVs in transportation systems. Along with pushing EV sales numbers, the installation of charging infrastructure is necessary. This paper presents a user- and destination-based approach for locating charging stations (CSs) for EVs—the electric charging demand location (ECDL) model. With regard to the daily activities of potential EV users, potential positions for CSs are derived on a micro-location level in public and semipublic spaces using geographic information systems (GIS). Depending on the vehicle users’ dwell times and visiting frequencies at potential points of interest (POIs), the charging demand at such locations is calculated. The model is mainly based on a survey analyzing the average time spent per daily activity, regional data about driver and vehicle ownership numbers, and the georeferenced localization of regularly visited POIs. Optimal sites for parking and charging EVs within the POIs neighborhood are selected based on walking distance calculations, including spatial neighborhood effects, such as the density of POIs. In a case study in southeastern Germany, the model identifies concrete places with the highest overall demand for CSs, resulting in an extensive coverage of the electric energy demand while considering as many destinations within the acceptable walking distance threshold as possible.

    MobilElektrotechnik und MedientechnikTC Freyung

    Zeitschriftenartikel

    Raphaela Pagany, Wolfgang Dorner

    Do Crash Barriers and Fences Have an Impact on Wildlife-Vehicle Collisions? An Artificial Intelligence and GIS-Based Analysis

    ISPRS International Journal of Geo-Information, vol. 8, no. 2

    DOI: 10.3390/ijgi8020066

    Abstract anzeigen

    Wildlife–vehicle collisions (WVCs) cause significant road mortality of wildlife and have led to the installation of protective measures along streets. Until now, it has been difficult to determine the impact of roadside infrastructure that might act as a barrier for animals. The main deficits are the lack of geodata for roadside infrastructure and georeferenced accidents recorded for a larger area. We analyzed 113 km of road network of the district Freyung-Grafenau, Germany, and 1571 WVCs, examining correlations between the appearance of WVCs, the presence or absence of roadside infrastructure, particularly crash barriers and fences, and the relevance of the blocking effect for individual species. To receive infrastructure data on a larger scale, we analyzed 5596 road inspection images with a neural network for barrier recognition and a GIS for a complete spatial inventory. This data was combined with the data of WVCs in GIS to evaluate the infrastructure’s impact on accidents. The results show that crash barriers have an effect on WVCs, as collisions are lower on roads with crash barriers. In particular, smaller animals have a lower collision share. The risk reduction at fenced sections could not be proven as fenced sections are only available at 3% of the analyzed roads. Thus, especially the fence dataset must be validated by a larger sample number. However, these preliminary results indicate that the combination of artificial intelligence and GIS may be used to analyze and better allocate protective barriers or to apply it in alternative measures, such as dynamic WVC risk-warning.

    DigitalMobilElektrotechnik und MedientechnikTC Freyung

    Zeitschriftenartikel

    Raphaela Pagany, Wolfgang Dorner

    Achtung Wildwechsel! Wie ein dynamische GIS-Lösung hilft, Unfälle zu verhindern

    arcAKTUELL: Operational Intelligence - Vorausschauend planen, no. 3, pp. 60-61

    DigitalMobilElektrotechnik und MedientechnikTC Freyung

    Vortrag

    Raphaela Pagany

    WilDa - Dynamische Wildunfallwarnung mit Hilfe von Verkehrs-, Unfall- und Umweltdaten

    4. Jahreskonferenz des Netzwerks INDIGO (Internet und Digitalisierung Ostbayern), Deggendorf

    MobilElektrotechnik und MedientechnikTC Freyung

    Vortrag

    C. Hoermann, Raphaela Pagany, Wolfgang Dorner, M. Heurich

    Experience of roe deer individuals helps to prevent traffic accidents

    BioMove Symposium 2018: Integrating Biodiversity Research with Movement Ecology, Potsdam

    MobilElektrotechnik und MedientechnikTC Freyung

    Vortrag

    C. Hoermann, Raphaela Pagany, Wolfgang Dorner, M. Heurich

    Movement ecology meets roads

    48th Annual Meeting of the Ecological Society of Germany, Austria and Switzerland, Wien, Österreich

    MobilElektrotechnik und MedientechnikTC Freyung

    Zeitschriftenartikel

    Raphaela Pagany, Luis Ramirez Camargo, Wolfgang Dorner

    A review of spatial localization methodologies for the electric vehicle charging infrastructure

    International Journal of Sustainable Transportation, pp. 1-17

    DOI: 10.1080/15568318.2018.1481243

    Abstract anzeigen

    With view to the high share of the transport sector in total energy consumption, e-mobility should play an important role within the transition of the energy systems. Policymakers in several countries consider electric vehicles (EV) as an alternative to fossil-fueled vehicles. In order to allow for the development of EV, the charging infrastructure has to be set up at locations with high charging potential, identified by means of various criteria such as demand density or trip length. Many methodologies for locating charging stations (CS) have been developed in the last few years. First, this paper presents a broad overview of publications in the domain of CS localization. A classification scheme is proposed regarding modeling theory and empirical application; further on, models are analyzed, distinguishing between users, route or destination centricity of the approaches and outcomes. In a second step, studies in the field of explicit spatial location planning are reviewed in more detail, that is, in terms of their target criteria and the specialization of underlying analytical processes. One divergence of these approaches lies in the varying level of spatial planning, which could be crucial depending on the planning requirements. It is striking that almost all CS locating concepts are proposed for urban areas. Other constraints, such as the lack of extensive empirical EV traffic data for a better understanding of the driving behavior, are identified. This paper provides an overview of the CS models, a classification approach especially considering the problem’s spatial dimension, and derives perspectives for further research.