@article{45484, abstract = {{AbstractGraffiti is an urban phenomenon that is increasingly attracting the interest of the sciences. To the best of our knowledge, no suitable data corpora are available for systematic research until now. The Information System Graffiti in Germany project (Ingrid) closes this gap by dealing with graffiti image collections that have been made available to the project for public use. Within Ingrid, the graffiti images are collected, digitized and annotated. With this work, we aim to support the rapid access to a comprehensive data source on Ingrid targeted especially by researchers. In particular, we present IngridKG, an RDF knowledge graph of annotated graffiti, abides by the Linked Data and FAIR principles. We weekly update IngridKG by augmenting the new annotated graffiti to our knowledge graph. Our generation pipeline applies RDF data conversion, link discovery and data fusion approaches to the original data. The current version of IngridKG contains 460,640,154 triples and is linked to 3 other knowledge graphs by over 200,000 links. In our use case studies, we demonstrate the usefulness of our knowledge graph for different applications.}}, author = {{Sherif, Mohamed Ahmed and da Silva, Ana Alexandra Morim and Pestryakova, Svetlana and Ahmed, Abdullah Fathi and Niemann, Sven and Ngomo, Axel-Cyrille Ngonga}}, issn = {{2052-4463}}, journal = {{Scientific Data}}, keywords = {{Library and Information Sciences, Statistics, Probability and Uncertainty, Computer Science Applications, Education, Information Systems, Statistics and Probability}}, number = {{1}}, publisher = {{Springer Science and Business Media LLC}}, title = {{{IngridKG: A FAIR Knowledge Graph of Graffiti}}}, doi = {{10.1038/s41597-023-02199-8}}, volume = {{10}}, year = {{2023}}, } @article{32335, abstract = {{Aspects of data science surround us in many contexts, for example regarding climate change, air pollution, and other environmental issues. To open the “data-science-black-box” for lower secondary school students we developed a data science project focussing on the analysis of self-collected environmental data. We embed this project in computer science education, which enables us to use a new knowledge-based programming approach for the data analysis within Jupyter Notebooks and the programming language Python. In this paper, we evaluate the second cycle of this project which took place in a ninth-grade computer science class. In particular, we present how the students coped with the professional tool of Jupyter Notebooks for doing statistical investigations and which insights they gained.}}, author = {{PODWORNY, SUSANNE and Hüsing, Sven and SCHULTE, CARSTEN}}, issn = {{1570-1824}}, journal = {{STATISTICS EDUCATION RESEARCH JOURNAL}}, keywords = {{Education, Statistics and Probability}}, number = {{2}}, publisher = {{International Association for Statistical Education}}, title = {{{A PLACE FOR A DATA SCIENCE PROJECT IN SCHOOL: BETWEEN STATISTICS AND EPISTEMIC PROGRAMMING}}}, doi = {{10.52041/serj.v21i2.46}}, volume = {{21}}, year = {{2022}}, } @article{34200, abstract = {{Praxeologische Kompetenzansätze verstehen Kompetenz als sozial erlernt und folglich als relativ zum sozialen Kontext. Damit einher geht die Frage, wie solche praxeologisch gerahmten Kompetenzen eigentlich unabhängig von der sie hervorbringenden Praxis evaluiert werden können – und eben dadurch erst für einen breiteren Kompetenzdiskurs fruchtbar sind. Die Dokumentarische Evaluationsforschung bietet hierzu erste Anhaltspunkte, offenbart aber auch Grenzen, die mit dem Evaluationsverständnis zusammenhängen, sich jedoch in der Forschungspraxis so nicht finden lassen. Aus der Differenz zwischen Methode und Praxis dokumentarischer Evaluation lässt sich formulieren, wie eine praxeologische Evaluation gestaltet werden könnte. Dabei spielt die Formulierung von Referenzrahmen eine zentrale Rolle, welche einerseits der zu evaluierenden Praktik external sein, andererseits praktisch formuliert werden müssen, damit sie soziale Praktiken jenseits ihrer eigenen Sinnhaftigkeit evaluativ (er-)fassen können.}}, author = {{Bloh, Thiemo}}, issn = {{1619-5515}}, journal = {{Zeitschrift für Evaluation}}, keywords = {{Strategy and Management, Applied Psychology, Social Sciences (miscellaneous), Education, Communication, Statistics and Probability}}, number = {{02}}, pages = {{193--215}}, publisher = {{Waxmann}}, title = {{{Rekonstruktive Evaluationsforschung im Kontext praxeologischer Kompetenzdiskurse. Kritische Reflexionen und konzeptionelle Überlegungen zur Dokumentarischen Evaluationsforschung}}}, doi = {{10.31244/zfe.2022.02.02}}, volume = {{2022}}, year = {{2022}}, } @article{48108, abstract = {{Aspects of data science surround us in many contexts, for example regarding climate change, air pollution, and other environmental issues. To open the “data-science-black-box” for lower secondary school students we developed a data science project focussing on the analysis of self-collected environmental data. We embed this project in computer science education, which enables us to use a new knowledge-based programming approach for the data analysis within Jupyter Notebooks and the programming language Python. In this paper, we evaluate the second cycle of this project which took place in a ninth-grade computer science class. In particular, we present how the students coped with the professional tool of Jupyter Notebooks for doing statistical investigations and which insights they gained.}}, author = {{PODWORNY, SUSANNE and HÜSING, SVEN and SCHULTE, CARSTEN}}, issn = {{1570-1824}}, journal = {{STATISTICS EDUCATION RESEARCH JOURNAL}}, keywords = {{Education, Statistics and Probability}}, number = {{2}}, publisher = {{International Association for Statistical Education}}, title = {{{A PLACE FOR A DATA SCIENCE PROJECT IN SCHOOL: BETWEEN STATISTICS AND EPISTEMIC PROGRAMMING}}}, doi = {{10.52041/serj.v21i2.46}}, volume = {{21}}, year = {{2022}}, } @article{53238, author = {{Tavana, Madjid and Khalili Nasr, Arash and Mina, Hassan and Michnik, Jerzy}}, issn = {{0038-0121}}, journal = {{Socio-Economic Planning Sciences}}, keywords = {{Management Science and Operations Research, Statistics, Probability and Uncertainty, Strategy and Management, Economics and Econometrics, Geography, Planning and Development}}, publisher = {{Elsevier BV}}, title = {{{A private sustainable partner selection model for green public-private partnerships and regional economic development}}}, doi = {{10.1016/j.seps.2021.101189}}, volume = {{83}}, year = {{2022}}, } @article{34920, abstract = {{A very warm welcome to this Special Issue of the Statistics Education Research Journal (SERJ) on data science education. Our hope is to give an overview of selected theoretical thoughts and empirical studies on data science education from a statistics education research perspective. Data science education is rapidly developing but research into data science education is still in its infancy. The current issue presents a snapshot of this developing field.}}, author = {{Biehler, Rolf and De Veaux, Richard and Engel, Joachim and Kazak, Sibel and Frischemeier, Daniel}}, issn = {{1570-1824}}, journal = {{Statistics Education Research Journal}}, keywords = {{Education, Statistics and Probability}}, number = {{2}}, publisher = {{International Association for Statistical Education}}, title = {{{Editorial: Research on Data Science Education}}}, doi = {{10.52041/serj.v21i2.606}}, volume = {{21}}, year = {{2022}}, } @article{50024, author = {{Feng, Yuanhua and Gries, Thomas and Letmathe, Sebastian and Schulz, Dominik}}, issn = {{2073-4859}}, journal = {{The R Journal}}, keywords = {{Statistics, Probability and Uncertainty, Numerical Analysis, Statistics and Probability}}, number = {{1}}, pages = {{182--195}}, publisher = {{The R Foundation}}, title = {{{The smoots Package in R for Semiparametric Modeling of Trend Stationary Time Series}}}, doi = {{10.32614/rj-2022-017}}, volume = {{14}}, year = {{2022}}, } @article{35672, abstract = {{This study examines modelling with machine learning. In the context of a yearlong data science course, the study explores how upper secondary students apply machine learning with Jupyter Notebooks and document the modelling process as a computational essay incorporating the different steps of the CRISP-DM cycle. The students’ work is based on a teaching module about decision trees in machine learning and a worked example of such a modelling process. The study outlines the students’ performance in carrying out the machine learning technically and reasoning about bias in the data, different data preparation steps, the application context, and the resulting decision model. Furthermore, the context of the study and the theoretical backgrounds are presented.}}, author = {{Fleischer, Franz Yannik and Biehler, Rolf and Schulte, Carsten}}, issn = {{1570-1824}}, journal = {{Statistics Education Research Journal}}, keywords = {{Education, Statistics and Probability}}, number = {{2}}, publisher = {{International Association for Statistical Education}}, title = {{{Teaching and Learning Data-Driven Machine Learning with Educationally Designed Jupyter Notebooks}}}, doi = {{10.52041/serj.v21i2.61}}, volume = {{21}}, year = {{2022}}, } @article{50025, author = {{Feng, Yuanhua and Gries, Thomas and Letmathe, Sebastian and Schulz, Dominik}}, issn = {{2073-4859}}, journal = {{The R Journal}}, keywords = {{Statistics, Probability and Uncertainty, Numerical Analysis, Statistics and Probability}}, number = {{1}}, pages = {{182--195}}, publisher = {{The R Foundation}}, title = {{{The smoots Package in R for Semiparametric Modeling of Trend Stationary Time Series}}}, doi = {{10.32614/rj-2022-017}}, volume = {{14}}, year = {{2022}}, } @article{32243, abstract = {{Abstract The defining feature of active particles is that they constantly propel themselves by locally converting chemical energy into directed motion. This active self-propulsion prevents them from equilibrating with their thermal environment (e.g. an aqueous solution), thus keeping them permanently out of equilibrium. Nevertheless, the spatial dynamics of active particles might share certain equilibrium features, in particular in the steady state. We here focus on the time-reversal symmetry of individual spatial trajectories as a distinct equilibrium characteristic. We investigate to what extent the steady-state trajectories of a trapped active particle obey or break this time-reversal symmetry. Within the framework of active Ornstein–Uhlenbeck particles we find that the steady-state trajectories in a harmonic potential fulfill path-wise time-reversal symmetry exactly, while this symmetry is typically broken in anharmonic potentials.}}, author = {{Dabelow, Lennart and Bo, Stefano and Eichhorn, Ralf}}, issn = {{1742-5468}}, journal = {{Journal of Statistical Mechanics: Theory and Experiment}}, keywords = {{Statistics, Probability and Uncertainty, Statistics and Probability, Statistical and Nonlinear Physics}}, number = {{3}}, publisher = {{IOP Publishing}}, title = {{{How irreversible are steady-state trajectories of a trapped active particle?}}}, doi = {{10.1088/1742-5468/abe6fd}}, volume = {{2021}}, year = {{2021}}, } @article{33649, author = {{Kessler, Jan and Calcavecchia, Francesco and Kühne, Thomas}}, issn = {{2513-0390}}, journal = {{Advanced Theory and Simulations}}, keywords = {{Multidisciplinary, Modeling and Simulation, Numerical Analysis, Statistics and Probability}}, number = {{4}}, publisher = {{Wiley}}, title = {{{Artificial Neural Networks as Trial Wave Functions for Quantum Monte Carlo}}}, doi = {{10.1002/adts.202000269}}, volume = {{4}}, year = {{2021}}, } @article{48109, abstract = {{AbstractIn this paper, we will describe an introduction to Data Science for secondary school students. We will report on the design and implementation of an introductory unit on “Data and data detectives with CODAP” in which secondary school students used the online tool CODAP to explore real and meaningful survey data on leisure time activities and media use (so‐called JIM‐PB data) in a statistical project setting as a starting point for data science. The JIM‐PB data set served as a valuable data set that offered meaningful and exciting opportunities for data exploration for secondary school students, and CODAP proved to be a valuable tool for the first explorations of this data.}}, author = {{Frischemeier, Daniel and Biehler, Rolf and Podworny, Susanne and Budde, Lea}}, issn = {{0141-982X}}, journal = {{Teaching Statistics}}, keywords = {{Education, Statistics and Probability}}, number = {{S1}}, publisher = {{Wiley}}, title = {{{A first introduction to data science education in secondary schools: Teaching and learning about data exploration with CODAP using survey data}}}, doi = {{10.1111/test.12283}}, volume = {{43}}, year = {{2021}}, } @article{35751, author = {{Frischemeier, Daniel and Biehler, Rolf and Podworny, Susanne and Budde, Lea}}, issn = {{0141-982X}}, journal = {{Teaching Statistics}}, keywords = {{Education, Statistics and Probability}}, number = {{S1}}, pages = {{S182--S189}}, publisher = {{Wiley}}, title = {{{A first introduction to data science education in secondary schools: Teaching and learning about data exploration withCODAPusing survey data}}}, doi = {{10.1111/test.12283}}, volume = {{43}}, year = {{2021}}, } @article{35737, author = {{Biehler, Rolf and Fleischer, Franz Yannik}}, issn = {{0141-982X}}, journal = {{Teaching Statistics}}, keywords = {{Education, Statistics and Probability}}, pages = {{S133--S142}}, publisher = {{Wiley}}, title = {{{Introducing students to machine learning with decision trees using CODAP and Jupyter Notebooks}}}, doi = {{10.1111/test.12279}}, volume = {{43}}, year = {{2021}}, } @article{45561, abstract = {{The purpose of this study is to experimentally test Trockel’s game, which is a modelling of the classical Chain Store Game (CSG), and determine whether one of the two theories of Equality and Deterrence may better account for the observed behavior. The CSG is an example of a simple game in extensive form where the actual behavior of well-informed players cannot be expected to agree with the clear results of game theoretical reasoning. To explain the disagreement between the theory and the expected behavior, Trockel’s game is proposed as an alternative modelling of the scenario. The existence of more than one equilibrium in Trockel’s game opens a door for reputation building. This study is the first attempt to experimentally test this alternative game with the same purpose. According to my data, there is some evidence in favor of both Equality and Deterrence Hypotheses. However, since the strategies compatible with the Equality Hypothesis are played more frequently, I observe some patterns which share the same intuition with the Deterrence Hypothesis.}}, author = {{Duman, Papatya}}, issn = {{2073-4336}}, journal = {{Games}}, keywords = {{Applied Mathematics, Statistics, Probability and Uncertainty, Statistics and Probability}}, number = {{1}}, publisher = {{MDPI AG}}, title = {{{Does Informational Equivalence Preserve Strategic Behavior? Experimental Results on Trockel’s Model of Selten’s Chain Store Story}}}, doi = {{10.3390/g11010009}}, volume = {{11}}, year = {{2020}}, } @inproceedings{48856, abstract = {{There exist many optimal or heuristic priority rules for machine scheduling problems, which can easily be integrated into single-objective evolutionary algorithms via mutation operators. However, in the multi-objective case, simultaneously applying different priorities for different objectives may cause severe disruptions in the genome and may lead to inferior solutions. In this paper, we combine an existing mutation operator concept with new insights from detailed observation of the structure of solutions for multi-objective machine scheduling problems. This allows the comprehensive integration of priority rules to produce better Pareto-front approximations. We evaluate the extended operator concept compared to standard swap mutation and the stand-alone components of our hybrid scheme, which performs best in all evaluated cases.}}, author = {{Bossek, Jakob and Grimme, Christian}}, booktitle = {{2017 IEEE Symposium Series on Computational Intelligence (SSCI)}}, keywords = {{Evolutionary computation, Processor scheduling, Schedules, Scheduling, Sociology, Standards, Statistics}}, pages = {{1–8}}, title = {{{An Extended Mutation-Based Priority-Rule Integration Concept for Multi-Objective Machine Scheduling}}}, doi = {{10.1109/SSCI.2017.8285224}}, year = {{2017}}, } @inproceedings{11753, abstract = {{This contribution describes a step-wise source counting algorithm to determine the number of speakers in an offline scenario. Each speaker is identified by a variational expectation maximization (VEM) algorithm for complex Watson mixture models and therefore directly yields beamforming vectors for a subsequent speech separation process. An observation selection criterion is proposed which improves the robustness of the source counting in noise. The algorithm is compared to an alternative VEM approach with Gaussian mixture models based on directions of arrival and shown to deliver improved source counting accuracy. The article concludes by extending the offline algorithm towards a low-latency online estimation of the number of active sources from the streaming input data.}}, author = {{Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)}}, keywords = {{Accuracy, Acoustics, Estimation, Mathematical model, Soruce separation, Speech, Vectors, Bayes methods, Blind source separation, Directional statistics, Number of speakers, Speaker diarization}}, pages = {{213--217}}, title = {{{Towards Online Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models}}}, year = {{2014}}, } @article{11862, abstract = {{In this contribution we extend a previously proposed Bayesian approach for the enhancement of reverberant logarithmic mel power spectral coefficients for robust automatic speech recognition to the additional compensation of background noise. A recently proposed observation model is employed whose time-variant observation error statistics are obtained as a side product of the inference of the a posteriori probability density function of the clean speech feature vectors. Further a reduction of the computational effort and the memory requirements are achieved by using a recursive formulation of the observation model. The performance of the proposed algorithms is first experimentally studied on a connected digits recognition task with artificially created noisy reverberant data. It is shown that the use of the time-variant observation error model leads to a significant error rate reduction at low signal-to-noise ratios compared to a time-invariant model. Further experiments were conducted on a 5000 word task recorded in a reverberant and noisy environment. A significant word error rate reduction was obtained demonstrating the effectiveness of the approach on real-world data.}}, author = {{Leutnant, Volker and Krueger, Alexander and Haeb-Umbach, Reinhold}}, journal = {{IEEE Transactions on Audio, Speech, and Language Processing}}, keywords = {{Bayes methods, compensation, error statistics, reverberation, speech recognition, Bayesian feature enhancement, background noise, clean speech feature vectors, compensation, connected digits recognition task, error statistics, memory requirements, noisy reverberant data, posteriori probability density function, recursive formulation, reverberant logarithmic mel power spectral coefficients, robust automatic speech recognition, signal-to-noise ratios, time-variant observation, word error rate reduction, Robust automatic speech recognition, model-based Bayesian feature enhancement, observation model for reverberant and noisy speech, recursive observation model}}, number = {{8}}, pages = {{1640--1652}}, title = {{{Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition}}}, doi = {{10.1109/TASL.2013.2258013}}, volume = {{21}}, year = {{2013}}, } @inproceedings{11913, abstract = {{In this paper we propose to employ directional statistics in a complex vector space to approach the problem of blind speech separation in the presence of spatially correlated noise. We interpret the values of the short time Fourier transform of the microphone signals to be draws from a mixture of complex Watson distributions, a probabilistic model which naturally accounts for spatial aliasing. The parameters of the density are related to the a priori source probabilities, the power of the sources and the transfer function ratios from sources to sensors. Estimation formulas are derived for these parameters by employing the Expectation Maximization (EM) algorithm. The E-step corresponds to the estimation of the source presence probabilities for each time-frequency bin, while the M-step leads to a maximum signal-to-noise ratio (MaxSNR) beamformer in the presence of uncertainty about the source activity. Experimental results are reported for an implementation in a generalized sidelobe canceller (GSC) like spatial beamforming configuration for 3 speech sources with significant coherent noise in reverberant environments, demonstrating the usefulness of the novel modeling framework.}}, author = {{Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}}, booktitle = {{IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2010)}}, keywords = {{array signal processing, blind source separation, blind speech separation, complex vector space, complex Watson distribution, directional statistics, expectation-maximisation algorithm, expectation maximization algorithm, Fourier transform, Fourier transforms, generalized sidelobe canceller, interference suppression, maximum signal-to-noise ratio beamformer, microphone signal, probabilistic model, spatial aliasing, spatial beamforming configuration, speech enhancement, statistical distributions}}, pages = {{241--244}}, title = {{{Blind speech separation employing directional statistics in an Expectation Maximization framework}}}, doi = {{10.1109/ICASSP.2010.5495994}}, year = {{2010}}, } @article{34886, abstract = {{We give asymptotic upper and lower bounds for the number of squarefree d (0 < d ≤ X) such that the equation x² − dy²= −1 is solvable. These estimates, as usual, can equivalently be interpreted in terms of real quadratic fields with a fundamental unit with norm −1 and give strong evidence in the direction of a conjecture due to P. Stevenhagen.}}, author = {{Fouvry, Étienne and Klüners, Jürgen}}, issn = {{0003-486X}}, journal = {{Annals of Mathematics}}, keywords = {{Statistics, Probability and Uncertainty, Mathematics (miscellaneous)}}, number = {{3}}, pages = {{2035--2104}}, publisher = {{Annals of Mathematics}}, title = {{{On the negative Pell equation}}}, doi = {{10.4007/annals.2010.172.2035}}, volume = {{172}}, year = {{2010}}, }