@article{HeelDiktaBraekers2021, author = {Heel, Mareike van and Dikta, Gerhard and Braekers, Roel}, title = {Bootstrap based goodness‑of‑fit tests for binary multivariate regression models}, series = {Journal of the Korean Statistical Society}, volume = {51}, journal = {Journal of the Korean Statistical Society}, publisher = {Springer Nature}, address = {Singapur}, issn = {2005-2863 (Online)}, doi = {10.1007/s42952-021-00142-4}, pages = {28 Seiten}, year = {2021}, abstract = {We consider a binary multivariate regression model where the conditional expectation of a binary variable given a higher-dimensional input variable belongs to a parametric family. Based on this, we introduce a model-based bootstrap (MBB) for higher-dimensional input variables. This test can be used to check whether a sequence of independent and identically distributed observations belongs to such a parametric family. The approach is based on the empirical residual process introduced by Stute (Ann Statist 25:613-641, 1997). In contrast to Stute and Zhu's approach (2002) Stute \& Zhu (Scandinavian J Statist 29:535-545, 2002), a transformation is not required. Thus, any problems associated with non-parametric regression estimation are avoided. As a result, the MBB method is much easier for users to implement. To illustrate the power of the MBB based tests, a small simulation study is performed. Compared to the approach of Stute \& Zhu (Scandinavian J Statist 29:535-545, 2002), the simulations indicate a slightly improved power of the MBB based method. Finally, both methods are applied to a real data set.}, language = {en} } @inproceedings{KloeserKohlKraftetal.2021, author = {Kl{\"o}ser, Lars and Kohl, Philipp and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {Multi-attribute relation extraction (MARE): simplifying the application of relation extraction}, series = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1}, booktitle = {Proceedings of the 2nd International Conference on Deep Learning Theory and Applications DeLTA - Volume 1}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-526-5}, doi = {10.5220/0010559201480156}, pages = {148 -- 156}, year = {2021}, abstract = {Natural language understanding's relation extraction makes innovative and encouraging novel business concepts possible and facilitates new digitilized decision-making processes. Current approaches allow the extraction of relations with a fixed number of entities as attributes. Extracting relations with an arbitrary amount of attributes requires complex systems and costly relation-trigger annotations to assist these systems. We introduce multi-attribute relation extraction (MARE) as an assumption-less problem formulation with two approaches, facilitating an explicit mapping from business use cases to the data annotations. Avoiding elaborated annotation constraints simplifies the application of relation extraction approaches. The evaluation compares our models to current state-of-the-art event extraction and binary relation extraction methods. Our approaches show improvement compared to these on the extraction of general multi-attribute relations.}, language = {en} } @inproceedings{KohlSchmidtsKloeseretal.2021, author = {Kohl, Philipp and Schmidts, Oliver and Kl{\"o}ser, Lars and Werth, Henri and Kraft, Bodo and Z{\"u}ndorf, Albert}, title = {STAMP 4 NLP - an agile framework for rapid quality-driven NLP applications development}, series = {Quality of Information and Communications Technology. QUATIC 2021}, booktitle = {Quality of Information and Communications Technology. QUATIC 2021}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-85346-4}, doi = {10.1007/978-3-030-85347-1_12}, pages = {156 -- 166}, year = {2021}, abstract = {The progress in natural language processing (NLP) research over the last years, offers novel business opportunities for companies, as automated user interaction or improved data analysis. Building sophisticated NLP applications requires dealing with modern machine learning (ML) technologies, which impedes enterprises from establishing successful NLP projects. Our experience in applied NLP research projects shows that the continuous integration of research prototypes in production-like environments with quality assurance builds trust in the software and shows convenience and usefulness regarding the business goal. We introduce STAMP 4 NLP as an iterative and incremental process model for developing NLP applications. With STAMP 4 NLP, we merge software engineering principles with best practices from data science. Instantiating our process model allows efficiently creating prototypes by utilizing templates, conventions, and implementations, enabling developers and data scientists to focus on the business goals. Due to our iterative-incremental approach, businesses can deploy an enhanced version of the prototype to their software environment after every iteration, maximizing potential business value and trust early and avoiding the cost of successful yet never deployed experiments.}, language = {en} } @inproceedings{SchmidtsKraftWinkensetal.2021, author = {Schmidts, Oliver and Kraft, Bodo and Winkens, Marvin and Z{\"u}ndorf, Albert}, title = {Catalog integration of heterogeneous and volatile product data}, series = {DATA 2020: Data Management Technologies and Applications}, booktitle = {DATA 2020: Data Management Technologies and Applications}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-83013-7}, doi = {10.1007/978-3-030-83014-4_7}, pages = {134 -- 153}, year = {2021}, abstract = {The integration of frequently changing, volatile product data from different manufacturers into a single catalog is a significant challenge for small and medium-sized e-commerce companies. They rely on timely integrating product data to present them aggregated in an online shop without knowing format specifications, concept understanding of manufacturers, and data quality. Furthermore, format, concepts, and data quality may change at any time. Consequently, integrating product catalogs into a single standardized catalog is often a laborious manual task. Current strategies to streamline or automate catalog integration use techniques based on machine learning, word vectorization, or semantic similarity. However, most approaches struggle with low-quality or real-world data. We propose Attribute Label Ranking (ALR) as a recommendation engine to simplify the integration process of previously unknown, proprietary tabular format into a standardized catalog for practitioners. We evaluate ALR by focusing on the impact of different neural network architectures, language features, and semantic similarity. Additionally, we consider metrics for industrial application and present the impact of ALR in production and its limitations.}, language = {en} } @article{JahnkeRousselHombachetal.2016, author = {Jahnke, Siegfried and Roussel, Johanna and Hombach, Thomas and Kochs, Johannes and Fischbach, Andreas and Huber, Gregor and Scharr, Hanno}, title = {phenoSeeder - A robot system for automated handling and phenotyping of individual seeds}, series = {Plant physiology}, volume = {172}, journal = {Plant physiology}, number = {3}, publisher = {Oxford University Press}, address = {Oxford}, issn = {0032-0889}, doi = {10.1104/pp.16.01122}, pages = {1358 -- 1370}, year = {2016}, abstract = {The enormous diversity of seed traits is an intriguing feature and critical for the overwhelming success of higher plants. In particular, seed mass is generally regarded to be key for seedling development but is mostly approximated by using scanning methods delivering only two-dimensional data, often termed seed size. However, three-dimensional traits, such as the volume or mass of single seeds, are very rarely determined in routine measurements. Here, we introduce a device named phenoSeeder, which enables the handling and phenotyping of individual seeds of very different sizes. The system consists of a pick-and-place robot and a modular setup of sensors that can be versatilely extended. Basic biometric traits detected for individual seeds are two-dimensional data from projections, three-dimensional data from volumetric measures, and mass, from which seed density is also calculated. Each seed is tracked by an identifier and, after phenotyping, can be planted, sorted, or individually stored for further evaluation or processing (e.g. in routine seed-to-plant tracking pipelines). By investigating seeds of Arabidopsis (Arabidopsis thaliana), rapeseed (Brassica napus), and barley (Hordeum vulgare), we observed that, even for apparently round-shaped seeds of rapeseed, correlations between the projected area and the mass of seeds were much weaker than between volume and mass. This indicates that simple projections may not deliver good proxies for seed mass. Although throughput is limited, we expect that automated seed phenotyping on a single-seed basis can contribute valuable information for applications in a wide range of wild or crop species, including seed classification, seed sorting, and assessment of seed quality.}, language = {en} } @misc{Schreiber2016, author = {Schreiber, Marc}, title = {Mit Maximum-Entropie das Parsing nat{\"u}rlicher Sprache erlernen}, publisher = {FH Aachen}, address = {Aachen}, pages = {23 Seiten}, year = {2016}, abstract = {F{\"u}r die Verarbeitung von nat{\"u}rlicher Sprache ist ein wichtiger Zwischenschritt das Parsing, bei dem f{\"u}r S{\"a}tze der nat{\"u}rlichen Sprache Ableitungsb{\"a}ume bestimmt werden. Dieses Verfahren ist vergleichbar zum Parsen formaler Sprachen, wie z. B. das Parsen eines Quelltextes. Die Parsing-Methoden der formalen Sprachen, z. B. Bottom-up-Parser, k{\"o}nnen nicht auf das Parsen der nat{\"u}rlichen Sprache {\"u}bertragen werden, da keine Formalisierung der nat{\"u}rlichen Sprachen existiert [3, 12, 23, 30]. In den ersten Programmen, die nat{\"u}rliche Sprache verarbeiten [32, 41], wurde versucht die nat{\"u}rliche Sprache mit festen Regelmengen zu verarbeiten. Dieser Ansatz stieß jedoch schnell an seine Grenzen, da die Regelmenge nicht vollst{\"a}ndig sowie nicht minimal ist und wegen der ben{\"o}tigten Menge an Regeln schwer zu verwalten ist. Die Korpuslinguistik [22] bot die M{\"o}glichkeit, die Regelmenge durch Supervised-Machine-Learning-Verfahren [2] abzul{\"o}sen. Teil der Korpuslinguistik ist es, große Textkorpora zu erstellen und diese mit sprachlichen Strukturen zu annotieren. Zu diesen Strukturen geh{\"o}ren sowohl die Wortarten als auch die Ableitungsb{\"a}ume der S{\"a}tze. Vorteil dieser Methodik ist es, dass repr{\"a}sentative Daten zur Verf{\"u}gung stehen. Diese Daten werden genutzt, um mit Supervised-Machine-Learning-Verfahren die Gesetzm{\"a}ßigkeiten der nat{\"u}rliche Sprachen zu erlernen. Das Maximum-Entropie-Verfahren ist ein Supervised-Machine-Learning-Verfahren, das genutzt wird, um nat{\"u}rliche Sprache zu erlernen. Ratnaparkhi [25] nutzt Maximum-Entropie, um Ableitungsb{\"a}ume f{\"u}r S{\"a}tze der nat{\"u}rlichen Sprache zu erlernen. Dieses Verfahren macht es m{\"o}glich, die nat{\"u}rliche Sprache (abgebildet als Σ∗) trotz einer fehlenden formalen Grammatik zu parsen.}, language = {de} } @article{LanzlKotliar2017, author = {Lanzl, I. and Kotliar, Konstantin}, title = {K{\"o}nnen Anti-VEGF-Injektionen Glaukom oder okul{\"a}re Hypertension verursachen?}, series = {Klinische Monatsbl{\"a}tter f{\"u}r Augenheilkunde}, volume = {234}, journal = {Klinische Monatsbl{\"a}tter f{\"u}r Augenheilkunde}, number = {2}, publisher = {Thieme}, address = {Stuttgart}, issn = {0023-2165}, doi = {10.1055/s-0043-101819}, pages = {191 -- 193}, year = {2017}, language = {de} } @article{ZangeSchopenAlbrachtetal.2017, author = {Zange, Jochen and Schopen, Kathrin and Albracht, Kirsten and Gerlach, Darius A. and Frings-Meuthen, Petra and Maffiuletti, Nicola A. and Bloch, Wilhelm and Rittweger, J{\"o}rn}, title = {Using the Hephaistos orthotic device to study countermeasure effectiveness of neuromuscular electrical stimulation and dietary lupin protein supplementation, a randomised controlled trial}, series = {Plos one}, volume = {12}, journal = {Plos one}, number = {2}, doi = {10.1371/journal.pone.0171562}, year = {2017}, language = {en} } @inproceedings{GoldmannBraunsteinHeinrichetal.2015, author = {Goldmann, Jan-Peter and Braunstein, Bjoern and Heinrich, Kai and Sanno, Maximilian and St{\"a}udle, Benjamin and Ritzdorf, Wolfgang and Br{\"u}ggemann, Gert-Peter and Albracht, Kirsten}, title = {Joint work of the take-off leg during elite high jump}, series = {Proceedings of the 33th International Conference on Biomechanics in Sports (ISBS)}, booktitle = {Proceedings of the 33th International Conference on Biomechanics in Sports (ISBS)}, pages = {3 S.}, year = {2015}, language = {en} } @inproceedings{DroszezSannoGoldmannetal.2016, author = {Droszez, Anna and Sanno, Maximilian and Goldmann, Jan-Peter and Albracht, Kirsten and Br{\"u}ggemann, Gerd-Peter and Braunstein, Bjoern}, title = {Differences between take-off behavior during vertical jumps and two artistic elements}, series = {34th International Conference of Biomechanics in Sport, Tsukuba, Japan, July 18-22, 2016}, booktitle = {34th International Conference of Biomechanics in Sport, Tsukuba, Japan, July 18-22, 2016}, issn = {1999-4168}, pages = {577 -- 580}, year = {2016}, language = {en} }