Refine
H-BRS Bibliography
- yes (74) (remove)
Departments, institutes and facilities
- Fachbereich Informatik (36)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (25)
- Fachbereich Ingenieurwissenschaften und Kommunikation (19)
- Fachbereich Wirtschaftswissenschaften (13)
- Institut für Verbraucherinformatik (IVI) (10)
- Institut für Cyber Security & Privacy (ICSP) (7)
- Zentrum für Innovation und Entwicklung in der Lehre (ZIEL) (5)
- Institut für KI und Autonome Systeme (A2S) (4)
- Fachbereich Angewandte Naturwissenschaften (3)
- Institute of Visual Computing (IVC) (3)
Document Type
- Conference Object (74) (remove)
Year of publication
- 2023 (74) (remove)
Keywords
- Virtual Reality (3)
- document similarity (3)
- Digital Sovereignty (2)
- Higher education (2)
- Machine Learning (2)
- Named Entity Recognition (2)
- Robotics (2)
- Survey (2)
- Word embeddings (2)
- 450 MHz (1)
A PM2.5 concentration prediction framework with vehicle tracking system: From cause to effect
(2023)
The continuously increasing number of biomedical scholarly publications makes it challenging to construct document recommendation algorithms that can efficiently navigate through literature. Such algorithms would help researchers in finding similar, relevant, and related publications that align with their research interests. Natural Language Processing offers various alternatives to compare publications, ranging from entity recognition to document embeddings. In this paper, we present the results of a comparative analysis of vector-based approaches to assess document similarity in the RELISH corpus. We aim to determine the best approach that resembles relevance without the need for further training. Specifically, we employ five different techniques to generate vectors representing the text in the documents. These techniques employ a combination of various Natural Language Processing frameworks such as Word2Vec, Doc2Vec, dictionary-based Named Entity Recognition, and state-of-the-art models based on BERT. To evaluate the document similarity obtained by these approaches, we utilize different evaluation metrics that account for relevance judgment, relevance search, and re-ranking of the relevance search. Our results demonstrate that the most promising approach is an in-house version of document embeddings, starting with word embeddings and using centroids to aggregate them by document.
The continuous increase of biomedical scholarly publications makes it challenging to construct document recommendation algorithms to navigate through literature, an important feature for researchers to keep up with relevant publications. Understanding semantic relatedness and similarity between two documents could improve document recommendations. The objective of this study is performing a comparative analysis of vector-based approaches to assess document similarity in the RELISH corpus. Here we present our approach to compare five different techniques to generate vectors representing the text in the documents. These techniques employ a combination of various Natural Language Processing frameworks such as Word2Vec, Doc2Vec, dictionary-based Named Entity Recognition as well as state-of-the-art models based on BERT.
Here we present a doc-2-doc relevance assessment performed on a subset of the TREC Genomics Track 2005 collection. Our approach includes an experimental set up to manually assess doc-2-doc relevance and the corresponding analysis done on the results obtained from this experiment. The experiment takes one document as a reference and assesses a second document regarding its relevance to the reference one. The consistency of the assessments done by 4 domain experts was evaluated. The lack of agreement between annotators may be due to: i) The abstract lacks key information and/or ii) Lack of experience of the annotators in the evaluation of some topics.
Hydrogen as a versatile, greenhouse gas-free energy carrier will play an important role in our future economy. Yet sustainable, competitive production and distribution of hydrogen remains a challenge. Highly integrated solar water splitting systems aim to combine solar energy harvesting and electrolysis in a single device, similar to a photovoltaic module.[1] Such a system can produce hydrogen locally without the requirement to be connected to the electricity grid. Unlike large electrolysis that draws power from the grid, the power density of such a device is reduced so far that it does not require active cooling, but its operating temperature will closely follow outdoor conditions.
Here, we present our work on high-efficiency integrated solar water splitting devices based on multi-junction solar absorbers. The light-absorbing component is sensitive to the shape of the solar spectrum and generally becomes more efficient at lower temperatures. Catalysis, on the other hand, benefits from higher temperatures. These conflicting trends wih respect to the temperature impact the design of the solar hydrogen production system. We analyse how the local climate affects production efficiency[2] and show in a lab study that adequate system design allows efficient operation at temperatures as low as -20°C.[3] These insights can help to design small-scale distributed solar hydrogen production for both temperate regions, but also more extreme climatic conditions.
Die Projektverbünde in der Förderlinie FDMScouts.nrw haben am 28.03.2023 die Online-Veranstaltung "#datendienstag: Datenmanagementpläne und Forschungsdatenmanagement in Forschungsanträgen" angeboten. Der Vortrag richtete sich an Forschende und Infrastrukturangehörige – vor allem aus der Forschungsförderung, welche die Antragsstellung begleiten.
Viele Drittmittelgeber erwarten als Teil eines Förderantrags Informationen zum Umgang mit Forschungsdaten. Ein formeller Datenmanagementplan (DMP) wird nur in den seltensten Fällen verlangt. Dennoch ist ein DMP für die Arbeit in einem Forschungsprojekt von Vorteil. Welche Vorteile dies sind und welche Anforderungen Forschende bei der Antragstellung bezüglich des FDMs zu erwarten haben, waren – neben Tipps und Tricks – Gegenstand dieser Veranstaltung.
The transport of carbon dioxide through pipelines is one of the important components of Carbon dioxide Capture and Storage (CCS) systems that are currently being developed. If high flow rates are desired a transportation in the liquid or supercritical phase is to be preferred. For technical reasons, the transport must stay in that phase, without transitioning to the gaseous state. In this paper, a numerical simulation of the stationary process of carbon dioxide transport with impurities and phase transitions is considered. We use the Homogeneous Equilibrium Model (HEM) and the GERG-2008 thermodynamic equation of state to describe the transport parameters. The algorithms used allow to solve scenarios of carbon dioxide transport in the liquid or supercritical phase, with the detection of approaching the phase transition region. Convergence of the solution algorithms is analyzed in connection with fast and abrupt changes of the equation of state and the enthalpy function in the region of phase transitions.
In the project EILD.nrw, Open Educational Resources (OER) have been developed for teaching databases. Lecturers can use the tools and courses in a variety of learning scenarios. Students of computer science and application subjects can learn the complete life cycle of databases. For this purpose, quizzes, interactive tools, instructional videos, and courses for learning management systems are developed and published under a Creative Commons license. We give an overview of the developed OERs according to subject, description, teaching form, and format. Following, we describe how licencing, sustainability, accessibility, contextualization, content description, and technical adaptability are implemented. The feedback of students in ongoing classes are evaluated.
AI systems pose unknown challenges for designers, policymakers, and users which aggravates the assessment of potential harms and outcomes. Although understanding risks is a requirement for building trust in technology, users are often excluded from legal assessments and explanations of AI hazards. To address this issue we conducted three focus groups with 18 participants in total and discussed the European proposal for a legal framework for AI. Based on this, we aim to build a (conceptual) model that guides policymakers, designers, and researchers in understanding users’ risk perception of AI systems. In this paper, we provide selected examples based on our preliminary results. Moreover, we argue for the benefits of such a perspective.
When dialogues with voice assistants (VAs) fall apart, users often become confused or even frustrated. To address these issues and related privacy concerns, Amazon recently introduced a feature allowing Alexa users to inquire about why it behaved in a certain way. But how do users perceive this new feature? In this paper, we present preliminary results from research conducted as part of a three-year project involving 33 German households. This project utilized interviews, fieldwork, and co-design workshops to identify common unexpected behaviors of VAs, as well as users’ needs and expectations for explanations. Our findings show that, contrary to its intended purpose, the new feature actually exacerbates user confusion and frustration instead of clarifying Alexa's behavior. We argue that such voice interactions should be characterized as explanatory dialogs that account for VA’s unexpected behavior by providing interpretable information and prompting users to take action to improve their current and future interactions.
Smart heating systems are one of the core components of smart homes. A large portion of domestic energy consumption is derived from HVAC (heating, ventilation and air conditioning) systems, making them a relevant topic of the efforts to support an energy transition in private housing. For that reason, the technology has attracted attention both from the academic and the industry communities. User interfaces of smart heating systems have evolved from simple adjusting knobs to advanced data visualization interfaces, that allow for more advanced setting such as time tables and status information. With the advent of AI, we are interested in exploring how the interfaces will be evolving to build the connection between user needs and underlying AI system. Hence, this paper is targeted to provide early design implications towards an AI-based user interface for smart heating systems.
Accurate forecasting of solar irradiance is crucial for the integration of solar energy into the power grid, power system planning, and the operation of solar power plants. The Weather Research and Forecasting (WRF) model, with its solar radiation (WRF-Solar) extension, has been used to forecast solar irradiance in various regions worldwide. However, the application of the WRF-Solar model for global horizontal irradiance (GHI) forecasting in West Africa, specifically in Ghana, has not been studied. This study aims to evaluate the performance of the WRF-Solar model for GHI forecasting in Ghana, focusing on 3 health centers (Kologo, Kumasi and Akwatia) for the year 2021. We applied a two one-way nested domain (D1=15 km and D2=3 km) to investigate the ability of the WRF solar model to forecast GHI up to 72 hours in advance under different atmospheric conditions. The initial and lateral boundary conditions were taken from the ECMWF operational forecasts. In addition, the optical aerosol depth (AOD) data at 550 nm from the Copernicus Atmosphere Monitoring Service (CAMS) were considered. The study uses statistical metrics such as mean bias error (MBE), root mean square error (RMSE), to evaluate the performance of the WRF-Solar model with the observational data obtained from automatic weather stations in the three health centers in Ghana. The results of this study will contribute to the understanding of the capabilities and limitations of the WRF-Solar model for forecasting GHI in West Africa, particularly in Ghana, and provide valuable information for stakeholders involved in solar energy generation and grid integration towards optimized management of in the region.
The representation, or encoding, utilized in evolutionary algorithms has a substantial effect on their performance. Examination of the suitability of widely used representations for quality diversity optimization (QD) in robotic domains has yielded inconsistent results regarding the most appropriate encoding method. Given the domain-dependent nature of QD, additional evidence from other domains is necessary. This study compares the impact of several representations, including direct encoding, a dictionary-based representation, parametric encoding, compositional pattern producing networks, and cellular automata, on the generation of voxelized meshes in an architecture setting. The results reveal that some indirect encodings outperform direct encodings and can generate more diverse solution sets, especially when considering full phenotypic diversity. The paper introduces a multi-encoding QD approach that incorporates all evaluated representations in the same archive. Species of encodings compete on the basis of phenotypic features, leading to an approach that demonstrates similar performance to the best single-encoding QD approach. This is noteworthy, as it does not always require the contribution of the best-performing single encoding.