检索结果-内蒙古大学图书馆

Increasing the Accessibility of Causal Domain Knowledge via Causal Information Extraction Methods: A Case Study in the Semiconductor Manufacturing Industry

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Razouk, Houssam Benischke, Leonie Gärber, Daniel Kern, Roman Quality Management Infineon Technologies Austria AG Carinthia Villach9500 Austria Institute of Interactive Systems and Data Science Graz University of Technology Styria Graz8010 Austria Centre de Recherches Interdisciplinaires et Transculturelles Université Bourgogne Franche-Comté Besançon Franche-Comté25000 France Know-Center GmbH Styria Graz8010 Austria

The extraction of causal information from textual data is crucial in the industry for identifying and mitigating potential failures, enhancing process efficiency, prompting quality improvements, and addressing various operational challenges. This paper presents a study on the development of automated methods for causal information extraction from actual industrial documents in the semiconductor manufacturing industry. The study proposes two types of causal information extraction methods, single-stage sequence tagging (SST) and multistage sequence tagging (MST), and evaluates their performance using existing documents from a semiconductor manufacturing company, including presentation slides and FMEA (Failure Mode and Effects Analysis) documents. The study also investigates the effect of representation learning on downstream tasks. The presented case study showcases that the proposed MST methods for extracting causal information from industrial documents are suitable for practical applications, especially for semi structured documents such as FMEAs, with a 93% F1 score. Additionally, MST achieves a 73% F1 score on texts extracted from presentation slides. Finally, the study highlights the importance of choosing a language model that is more aligned with the domain and in-domain fine-tuning. © 2024, CC BY.

关键词： Natural language processing systems

The dynamics of diversity on corporate boards

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Raddant, Matthias Karimi, Fariba Graz University of Technology Institute of Software Technology Inffeldgasse 16b/II Graz8010 Austria University for Continuing Education Krems Department for Knowledge and Communication Management Dr.-Karl-Dorrek-Straße 30 Krems3500 Austria Graz University of Technology Institute of Interactive Systems and Data Science Sandgasse 36/III Graz8010 Austria Complexity Science Hub Vienna Josefstädter Straße 39 Vienna1080 Austria

Diversity in leadership positions, including corporate boards, is an important aspect of equality. It is important because it is the key to better decision-making and innovation, and above all, it paves the way for future generations to participate and shape our society. Many studies emphasize the importance of the visibility of role models and the effect that connectivity has on the success of minorities in leadership. However, the connectivity of firms, the dynamics of the adoption of minorities into leadership positions, and the long-term effects in terms of group dynamics and visibility are not well understood. Here, we present a model that shows how these effects work together in a dynamic model that is calibrated with empirical data of firm and board networks. We show that homophily - the appointment of minorities is influenced by the presence of minorities in a board and its neighboring entities - is an important effect shaping the trajectory towards equality. We further show how perception biases and feedback related to the visibility of minority members influence the dynamic. We find that reaching equality can be sped up or slowed down depending on the distribution of minorities in central firms. These insights bear significant implications for policy-making geared towards fostering equality and diversity within corporate boards. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

Testing robustness of predictions of trained classifiers against naturally occurring perturbations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Scher, Sebastian Trügler, Andreas Know-Center GmbH Inffeldgasse 13/6 Graz8010 Austria Institute of Interactive Systems and Data Science Graz University of Technology Inffeldgasse 16C Graz8010 Austria Department of Geography and Regional Science University of Graz Heinrichstraße 36 Graz8010 Austria

Correctly quantifying the robustness of machine learning models is a central aspect in judging their suitability for specific tasks, and ultimately, for generating trust in them. We address the problem of finding the robustness of individual predictions. We show both theoretically and with empirical examples that a method based on counterfactuals that was previously proposed for this is insufficient, as it is not a valid metric for determining the robustness against perturbations that occur "naturally", outside specific adversarial attack scenarios. We propose a flexible approach that models possible perturbations in input data individually for each application. This is then combined with a probabilistic approach that computes the likelihood that a "real-world" perturbation will change a prediction, thus giving quantitative information of the robustness of individual predictions of the trained machine learning model. The method does not require access to the internals of the classifier and thus in principle works for any black-box model. It is, however, based on Monte-Carlo sampling and thus only suited for input spaces with small dimensions. We illustrate our approach on the Iris and the Ionosphere datasets, on an application predicting fog at an airport, and on analytically solvable cases. Copyright © 2022, The Authors. All rights reserved.

关键词： Ionosphere

Parasitic resistance as a predictor of faulty anodes in electro galvanizing: a comparison of machine learning, physical and hybrid models

学校读者我要写书评

暂无评论

Advanced Modeling and Simulation in Engineering sciences 2020年第1期7卷 1-16页

作者： Lovrić, Mario Meister, Richard Steck, Thomas Fadljević, Leon Gerdenitsch, Johann Schuster, Stefan Schiefermüller, Lukas Lindstaedt, Stefanie Kern, Roman Institute of Interactive Systems and Data Science TU Graz Inffeldgasse 16c Graz 8010 Austria Know-Center Inffeldgasse 13/6 Graz 8010 Austria Voestalpine Stahl GmbH Linz 4020 Austria

In industrial electro galvanizing lines aged anodes deteriorate zinc coating distribution over the strip width, leading to an increase in electricity and zinc cost. We introduce a data-driven approach in predictive maintenance of anodes to replace the cost- and labor-intensive manual inspection, which is still common for this task. The approach is based on parasitic resistance as an indicator of anode condition which might be aged or mis-installed. The parasitic resistance is indirectly observable via the voltage difference between the measured and baseline (theoretical) voltage for healthy anode. Here we calculate the baseline voltage by means of two approaches: (1) a physical model based on electrical and electrochemical laws, and (2) advanced machine learning techniques including boosting and bagging regression. The data was collected on one exemplary rectifier unit equipped with two anodes being studied for a total period of two years. The dataset consists of one target variable (rectifier voltage) and nine predictive variables used in the models, observing electrical current, electrolyte, and steel strip characteristics. For predictive modelling, we used Random Forest, Partial Least Squares and AdaBoost Regression. The model training was conducted on intervals where the anodes were in good condition and validated on other segments which served as a proof of concept that bad anode conditions can be identified using the parasitic resistance predicted by our models. Our results show a RMSE of 0.24 V for baseline rectifier voltage with a mean ± standard deviation of 11.32 ± 2.53 V for the best model on the validation set. The best-performing model is a hybrid version of a Random Forest which incorporates meta-variables computed from the physical model. We found that a large predicted parasitic resistance coincides well with the results of the manual inspection. The results of this work will be implemented in online monitoring of anode conditions to reduce operation

关键词： Big data Electroplating Gravitel cell Random forest Steel Voltage Zinc coating

Work-in-Progress—Conceptual Framework for User Interface in Virtual Reality

学校读者我要写书评

暂无评论

Work-in-Progress—Conceptual Framework for User Interface in...

Immersive Learning Research Network (iLRN), Conference of the

作者： Saeed Safikhani Michael Holly Johanna Pirker Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

ISBN: (数字)9781734899504

ISBN: (纸本)9781728152264

Presence in VR is a perceptual sense that leads to an automatic reaction of the brain-body system. An expected interaction in VR can lead to a higher sense of presence. In this work in progress paper we present a conceptual framework for innovative user interface (UI) design in VR with a focus on realistic interactions with the environment. We investigate several successful VR games by focusing on their user interactions and the UI system. The first part of this framework is implemented in a tutorial room where we designed some common UI elements such as the menu, inventory system, and quest manager.

关键词： Games User interfaces Tutorials Three-dimensional displays Usability Two dimensional displays Virtual reality

Room Scale Virtual Reality Physics Education: Use Cases for the Classroom

学校读者我要写书评

暂无评论

Room Scale Virtual Reality Physics Education: Use Cases for ...

Immersive Learning Research Network (iLRN), Conference of the

作者： Johanna Pirker Michael Holly Christian Gütl Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria

ISBN: (数字)9781734899504

ISBN: (纸本)9781728152264

interactive and digital learning experiences are becoming increasingly important and used to improve various learning scenarios. In physics education, the use of digital simulations or virtual laboratories to support the learners' understanding is already part of most classrooms. Virtual reality experiences can be used to create even more exciting, engaging, and realistic learning setups to conduct experiments and work with simulations. A range of studies has shown a positive effect of virtual reality experiences for learning. In this paper, we explore the potential of physics education in virtual reality in school-based classroom scenarios. We present a study with 147 high school students from four different schools, to evaluate the potential of room-scale VR learning setups in classroom learning with a focus on engagement and learning experience and focus on dandifying potential use cases for learning experiences in schools from the students' perspective. In this study, we found that students described the experiences as highly engaging and a valuable tool to increase motivation in classrooms. They would rather use VR for learning in the classroom than at home. They prefer a PC-based VR setup over a mobile phone setup. Four main identified use cases for using VR in classrooms from the students' perspective are evaluated and discussed.

关键词： Virtual reality Tools Physics education Solid modeling Games Usability Laboratories

Assessment of the effectiveness of Omicron transmission mitigation strategies for European universities using an agent-based network model

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lasser, Jana Hell, Timotheus Garcia, David Graz University of Technology Institute for Interactive Systems and Data Science Inffeldgasse 16C Graz8010 Austria Complexity Science Hub Vienna Josefstädterstraße 39 Vienna1080 Austria Graz University of Technology Higher Education and Programme Development Rechbauerstraße 12 Graz8010 Austria Medical University of Vienna Center for Medical Statistics Informatics and Intelligent Systems Spitalgasse 23 Vienna1090 Austria

Returning universities to full on-campus operations while the COVID-19 pandemic is ongoing has been a controversial discussion in many countries. The risk of large outbreaks in dense course settings is contrasted by the benefits of in-person teaching. Transmission risk depends on a range of parameters, such as vaccination coverage and efficacy, number of contacts and adoption of non-pharmaceutical intervention measures (NPIs). Due to the generalised academic freedom in Europe, many universities are asked to autonomously decide on and implement intervention measures and regulate on-campus operations. In the context of rapidly changing vaccination coverage and parameters of the virus, universities often lack sufficient scientific insight to base these decisions on. To address this problem, we analyse a calibrated, data-driven agent-based simulation of transmission dynamics of 13,284 students and 1,482 faculty members in a medium-sized European university. We use a co-location network reconstructed from student enrollment data and calibrate transmission risk based on outbreak size distributions in education institutions. We focus on actionable interventions that are part of the already existing decision-making process of universities to provide guidance for concrete policy decisions. Here we show that, with the Omicron variant of the SARS-CoV-2 virus, even a reduction to 25% occupancy and universal mask mandates are not enough to prevent large outbreaks given the vaccination coverage of about 80% recently reported for students in Austria. Our results show that controlling the spread of the virus with available vaccines in combination with NPIs is not feasible in the university setting if presence of students and faculty on campus is required. © 2022, CC BY-SA.

关键词： Vaccines

Stress-testing the Resilience of the Austrian Healthcare System Using Agent-Based Simulation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kaleta, Michaela Lasser, Jana Dervic, Elma Yang, Liuhuaying Sorger, Johannes Sardo, Ruggiero Lo Thurner, Stefan Kautzky-Willer, Alexandra Klimek, Peter Complexity Science Hub Vienna Josefstädter Straße 39 Vienna1080 Austria Medical University of Vienna Section for Science of Complex Systems CeMSIIS Spitalgasse 23 Vienna1090 Austria Graz University of Technology Institute for Interactive Systems and Data Science Inffeldgasse 16C Graz8010 Austria Department of Internal Medicine III Clinical Division of Endocrinology and Metabolism Medical University of Vienna Währinger Gürtel 18-20 ViennaA-1090 Austria Gender Institute Gars am Kamp A-3571 Austria

Patients do not access physicians at random but rather via naturally emerging networks of patient flows between them. As retirements, mass quarantines and absence due to sickness during pandemics, or other shocks thin out these networks, the system might be pushed closer to a tipping point where it loses its ability to deliver care to the population. Here we propose a data-driven framework to quantify the regional resilience to such shocks of primary and secondary care in Austria via an agent-based model. For each region and medical specialty we construct detailed patient-sharing networks from administrative data and stress-test these networks by removing increasing numbers of physicians from the system. This allows us to measure regional resilience indicators describing how many physicians can be removed from a certain area before individual patients won't be treated anymore. We find that such tipping points do indeed exist and that regions and medical specialties differ substantially in their resilience. These systemic differences can be related to indicators for individual physicians by quantifying how much their hypothetical removal would stress the system (risk score) or how much of the stress from the removal of other physicians they would be able to absorb (benefit score). Our stress-testing framework could enable health authorities to rapidly identify bottlenecks in access to care as well as to inspect these naturally emerging physician networks and how potential absences would impact them. © 2022, CC BY.

关键词： Autonomous agents

Insights in Learners' Behaviour and Early Dropout Detection based on Coursera MOOCs

学校读者我要写书评

暂无评论

Insights in Learners' Behaviour and Early Dropout Detection ...

International Conference on Information Technology Based Higher Education and Training, ITHET

作者： Sarah Frank Christian Gütl Mar Pérez-Sanagustín Isabel Hilliger Institute of Interactive Systems and Data Science Graz University of Technology Graz Austria Institute Recherche en Informatique de Toulouse Université Paul Sabatier Toulouse France School of Engineering Pontificia Universidad Católica de Chile Santiago Chile

ISBN: (纸本)9781728188843

Increased utilization of distance learning makes the creation of effective learning tools ever more important. However, while Massive Open Online Courses (MOOCs) are a popular online learning tool, they often suffer from high user attrition. This paper investigated this effect for 6 different MOOCs with more than 35 thousand users, using AdaBoosted decision trees to create a model which was then used for the prediction of dropouts, as well as the calculation of feature importance scores. The resulting model generally scored high accuracy scores which were plotted for each course, and feature importance scores were especially high for the features encompassing the number of user requests, the user's total active time and the average time between clicks. Furthermore, the paper explored the results of the inclusion of forum data in this setting. While the forum features did not lead to a major increase in model accuracy, there was a statistical difference between the number of forum interactions for those who completed the MOOCs and those who did not, which opens up possibilities for future research into utilization of forum interaction data, and forums in MOOCs in general.

关键词： Training Computer aided instruction Analytical models Electronic learning Statistical analysis Predictive models Feature extraction