192815 research outputs found
Sort by
Evaluating Knowledge Graph Sources for Non-Personalized Financial Asset Recommendation: 10K Reports vs. Wikidata
No full textFinancial asset recommender (FAR) systems suggest investment assets to customers based on past market information. Many of these models choose those securities which they estimate to be more profitable for customers. Financial knowledge graphs (KGs) – data structures containing information about assets and their relations to other involved entities (companies, people) – have been one of the data sources exploited to drive asset selection. Although the construction of knowledge graphs from different sources (news, reports) has previously been investigated, there has been limited analysis of the effect these construction strategies have for FAR. In this work, we compare two different knowledge graphs representing U.S. stocks under a unified FAR framework: a knowledge graph crawled from a general knowledge base, Wikidata, and a knowledge graph built by extracting entities and relations from 10K financial reports using the GoLLIE open information extraction model. We show that integrating these KGs in FAR can lead up to 10.7% improvements in monthly ROI. However, the nature of these graphs makes algorithms prone to bias the recommendations towards different asset types. Therefore, we further propose and evaluate an adaptive graph selection strategy, which dynamically chooses the suitable graph prediction model—trained on either the 10K Graph or the Wikidata Graph—for each asset. The findings indicate that stock-level and sector-level selection strategies respond differently to the length of the recency window, reflecting, respectively, a preference for short-term responsiveness and long-term stability
Ichnos: a Carbon Footprint Estimator for Scientific Workflows
Get PDFScientific workflows facilitate the automation of data analysis, and are used to process increasing amounts of data. Therefore, they tend to be resource-intensive and long-running, leading to significant energy consumption and carbon emissions. With ever-increasing emissions from the ICT sector, it is crucial to quantify and understand the carbon footprint of scientific workflows. However, existing tooling requires significant effort from users – such as setting up power monitoring before executing workloads, or translating monitored metrics into the carbon footprints post-execution. In this paper, we introduce a system to estimate the carbon footprint of Nextflow scientific workflows that enables post-hoc estimation based on existing workflow traces, power models for computational resources utilised, and carbon intensity data aligned with the execution time. We discuss our automated power modelling approach, and compare it with commonly used estimation
methodologies. Furthermore, we exemplify several potential use cases and evaluate our energy consumption estimation approach, finding its estimation error to be between 3.9–10.3%, outperforming both baseline methodologies
Beyond Reconstruction: a Physics Based Neural Deferred Shader for Photo-realistic Rendering
No full textDeep learning based rendering has achieved major improvements in photo-realistic image synthesis, with potential applications including visual effects in movies and photo-realistic scene building in video games. However, a significant limitation is the difficulty of decomposing the illumination and material parameters, which limits such methods to reconstructing an input scene, without any possibility to control these parameters. This paper introduces a novel physics based neural deferred shading pipeline to decompose the data-driven rendering process, learn a generalizable shading function to produce photo-realistic results for shading and relighting tasks; we also propose a shadow estimator to efficiently mimic shadowing effects. Our model achieves improved performance compared to classical models and a state-of-art neural shading model, and enables generalizable photo-realistic shading from arbitrary illumination input
Computational hermeneutics: evaluating generative AI as a cultural technology
Get PDFGenerative AI (GenAI) systems are increasingly recognized as cultural technologies, yet current evaluation frameworks often treat culture as a variable to be measured rather than fundamental to the system's operation. Drawing on hermeneutic theory from the humanities, we argue that GenAI systems function as "context machines" that must inherently address three interpretive challenges: situatedness (meaning only emerges in context), plurality (multiple valid interpretations coexist), and ambiguity (interpretations naturally conflict). We present computational hermeneutics as an emerging framework offering an interpretive account of what GenAI systems do, and how they might do it better. We offer three principles for hermeneutic evaluation—that benchmarks should be iterative, not one-off; include people, not just machines; and measure cultural context, not just model output. This perspective offers a nascent paradigm for designing and evaluating contemporary AI systems: shifting from standardized questions about accuracy to contextual ones about meaning
From heat maps to cooling actions: AI-driven citywide hourly mapping of thermal stress, drivers, and targeted cooling
Get PDFThermal stress is critical for sustainable, health-oriented urban planning, yet remains difficult to characterize at hourly resolution and citywide in dense cities. Using Hong Kong as a case study, this study develops a regression-based machine learning framework to predict hourly thermal stress, expressed as Net Effective Temperature (NET). Long-term meteorological data was combined with detailed geographic, urban-morphological, and landscape composition–configuration metrics in a multilayer perceptron artificial neural network (MLP-ANN). The model uses 37 input variables, while the target variable is the continuous hourly NET. The model attains high predictive skill (R² = 0.97, RMSE=1.1°C over the full dataset) and captures pronounced diurnal and seasonal patterns in thermal stress. Performance remains robust under hot (R² = 0.97, RMSE = 0.5°C) and cold (R² = 0.94, RMSE = 1.7°C) conditions. In summer, afternoon NET reaches about 30.3°C and remains elevated at night, whereas in winter nocturnal NET can fall below –4°C. Spatially, higher NET concentrates in dense urban and industrial districts, with summer hotspots around the airport, Northwest New Territories, and Kwai Tsing Container Terminals. Daytime NET is dominated by near-surface air temperature, followed by and NDBI, along with configuration metrics such as SHAPE, CIRCLE, and AREA, while and NDWI become especially influential in winter daytime. At night, configuration metrics including FRAC, CONTIG, CORE, and GYRATE gain importance. The framework delivers citywide, hourly NET maps and quantitative driver rankings to guide targeted, nature-based and morphological interventions in subtropical high-density cities
Assessing low temperature waste heat integration in 5th generation district heating and cooling: a case study evaluation
Get PDFDecarbonising urban heating and cooling necessitates innovative solutions that can cost-effectively integrate low-temperature waste heat, such as from Wastewater Treatment Plants (WWTPs). While 5th Generation District Heating and Cooling (5GDHC) offers promising pathways for energy reuse and sector coupling, its techno-economic-environmental performance, particularly when leveraging WWTPs as a dual heat source/sink without Seasonal Thermal Energy Storage (STES), and its precise impact on the electricity grid, remain underexplored. This study investigates the feasibility of 5GDHC in Glasgow’s Clyde Gateway, a large-scale urban regeneration. It critically analyses two WWTP-integrated 5GDHC configurations (direct heat exchanger vs. sewer water source heat pump) and compares their techno-economic-environmental performance against established alternatives: 4th Generation District Heating with individual Air Condition units (4GDH&AC) and building-level reversible Air-Source Heat Pumps (ASHPs). Results demonstrate that even with low heating and cooling demand co-occurrence (3.4% DOC), the direct heat exchanger 5GDHC configuration (5GDHC-1) proved most economically viable, achieving the lowest Levelised Cost of Energy (£227/MWh) compared to 4GDH&AC (£257/MWh). Crucially, 5GDHC solutions exhibited a significantly lower electrical capacity demand (0.7 MVA) than 4GDH&AC (1.5 MVA) and ASHPs (3.0 MVA), offering substantial benefits for grid infrastructure and broader electrification. While 4GDH&AC showed lower overall energy consumption, 5GDHC’s ability to minimise peak electrical load is a distinct advantage. This research highlights that strategic waste heat integration, particularly through direct exchange with the WWTP leveraging ambient network temperature profiles, enables economically viable 5GDHC without STES in low demand co-occurrence scenarios. It provides critical insights for developing resilient, low-carbon urban thermal systems with reduced electricity grid impact
Observation of the rare baryonic decay B+ → pΛ¯ and measurement of its weak decay parameter
No full textThe first observation of the decay B + → p Λ ¯ is presented using proton-proton collision data collected by the LHCb experiment between 2016 and 2018 at a center-of-mass energy of 13 TeV, corresponding to an integrated luminosity of 5.4 fb − 1 . The signal significance exceeds seven standard deviations. Using the B + → K S 0 π + decay as a normalization channel, the branching fraction is measured and combined with previous LHCb results based on data collected at 7 and 8 TeV in 2011 and 2012, yielding B ( B + → p Λ ¯ ) = ( 1.24 ± 0.17 ± 0.05 ± 0.03 ) × 10 − 7 , where the first uncertainty is statistical, the second is systematic, and the third comes from the uncertainty on the branching fraction of the normalization channel. The B + → p Λ ¯ weak decay parameter is measured to be α B = 0.8 7 − 0.29 + 0.26 ± 0.09 , indicating the presence of comparable S-wave and P-wave decay amplitudes
Religious community, language and family: why the neo-protestant churches in Romania support emigration to the US
No full textExisting scholarship has studied the Church’s role in facilitating emigration through providing
various forms of assistance. However, there is limited research about the characteristics of the
migrants benefiting from such aid, particularly in terms of the combination between social
embeddedness and religious devotion. This study addresses this gap by investigating how the
Neo-Protestant churches in Romania help in the emigration process, and explains the support
they provide as a type of religious capital. Based on primary data from an online survey and
semi-structured interviews with Romanian emigrants in the US, the analysis reveals that the
Churches’ assistance is directed more toward individuals with strong ties to the religious community, those facing linguistic barriers, and those migrating for the purpose of family reunification
Projection-displacement based query performance prediction for embedded space of dense retrievers
No full textRecent advances in representation learning have enabled neural Information Retrieval (IR) systems to use learned dense representations for queries and documents to effectively handle semantics, language nuances, and vocabulary mismatch problems. In contrast to traditional IR systems that rely on word matching, dense IR models exploit query/document similarity in dense latent spaces to account for semantics. This requires substantial training data and comes with increased computational demands. Thus, it would be beneficial to predict how a system will perform for a given query to decide whether a dense IR model is the best option or alternatives should be used. Traditional Query Performance Prediction (QPP) models are designed for lexical IR approaches and perform sub-optimally when applied to dense neural IR systems. Therefore, there has been a renewed interest in QPP methods to improve their effectiveness for dense neural IR models. While the results of the new QPP methods are generally encouraging, there is ample room for improvement in absolute performance and stability. We argue that by using features more aligned with the underlying rationale of dense IR models, we can enhance the performance of QPP. In this respect, we propose the Projection-DisplacementBased QPP(PDQPP),whichexploits the geometric properties of dense IR models, projects queries and retrieved documents onto subspaces defined by pseudo-relevant documents, and considers changes in retrieval scores within them as a proxy for retrieval coherence. Minor score changes suggest robust and coherent retrieval, while significant alterations indicate semantic divergence and potentially poor performance. Results over a wide range of experimental settings on both traditional (TREC Robust) and neural-oriented (TREC Deep Learning) test collections show that PDQPP mostly outperforms the state-of-the-art QPP baselines
Converting sWeights to probabilities with density ratios
Get PDFThe use of machine learning approaches continues to have many benefits in experimental nuclear and particle physics. One common issue is generating training data which is sufficiently realistic to give reliable results. Here we advocate using real experimental data as the source of training data and demonstrate how one might subtract background contributions through the use of probabilistic weights which can be readily applied to training data. The sPlot formalism is a common tool used to isolate distributions from different sources. However, the negative sWeights produced by the sPlot technique can cause training problems and poor predictive power. This article demonstrates how density ratio estimation can be applied to convert sWeights to event probabilities, which we call drWeights. The drWeights can then be applied to produce the distributions of interest and are consistent with direct use of the sWeights. This article will also show how decision trees are particularly well suited to convert sWeights, with the benefit of fast prediction rates and adaptability to aspects of experimental data such as the data sample size and proportions of different event sources. We also show that a density ratio product approach in which the initial drWeights are reweighted by an additional converter gives substantially better results
Data sources:
Access Repository Dashboard
Do you manage Open Research Online? Become a CORE Member to access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard! 👇