TY - JOUR A1 - Heusinger, Moritz T1 - Dimensionality reduction in the context of dynamic social media data streams JF - Evolving Systems N2 - In recent years social media became an important part of everyday life for many people. A big challenge of social media is, to find posts, that are interesting for the user. Many social networks like Twitter handle this problem with so-called hashtags. A user can label his own Tweet (post) with a hashtag, while other users can search for posts containing a specified hashtag. But what about finding posts which are not labeled by the creator? We provide a way of completing hashtags for unlabeled posts using classification on a novel real-world Twitter data stream. New posts will be created every second, thus this context fits perfectly for non-stationary data analysis. Our goal is to show, how labels (hashtags) of social media posts can be predicted by stream classifiers. In particular, we employ random projection (RP) as a preprocessing step in calculating streaming models. Also, we provide a novel real-world data set for streaming analysis called NSDQ with a comprehensive data description. We show that this dataset is a real challenge for state-of-the-art stream classifiers. While RP has been widely used and evaluated in stationary data analysis scenarios, non-stationary environments are not well analyzed. In this paper, we provide a use case of RP on real-world streaming data, especially on NSDQ dataset. We discuss why RP can be used in this scenario and how it can handle stream-specific situations like concept drift. We also provide experiments with RP on streaming data, using state-of-the-art stream classifiers like adaptive random forest and concept drift detectors. Additionally, we experimentally evaluate an online principal component analysis (PCA) approach in the same fashion as we do for RP. To obtain higher dimensional synthetic streams, we use random Fourier features (RFF) in an online manner which allows us, to increase the number of dimensions of low dimensional streams. KW - social media KW - data Y1 - 2021 UR - https://doi.org/10.1007/s12530-021-09396-z SN - 1868-6486 ER - TY - JOUR A1 - Heusinger, Moritz T1 - Passive concept drift handling via variations of learning vector quantization JF - Neural Computing and Applications N2 - Concept drift is a change of the underlying data distribution which occurs especially with streaming data. Besides other challenges in the field of streaming data classification, concept drift has to be addressed to obtain reliable predictions. Robust Soft Learning Vector Quantization as well as Generalized Learning Vector Quantization has already shown good performance in traditional settings and is modified in this work to handle streaming data. Further, momentum-based stochastic gradient descent techniques are applied to tackle concept drift passively due to increased learning capabilities. The proposed work is tested against common benchmark algorithms and streaming data in the field and achieved promising results. KW - concept drift KW - data Y1 - 2020 UR - https://doi.org/10.1007/s00521-020-05242-6 SN - 1433-3058 VL - 34 SP - 89 EP - 100 ER - TY - JOUR A1 - Raab, Christoph A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael T1 - Reactive Soft Prototype Computing for Concept Drift Streams JF - Neurocomputing Y1 - 2020 U6 - https://doi.org/10.1016/j.neucom.2019.11.111 VL - 416 SP - 340 EP - 351 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael ED - Rojas, Ignacio ED - Joya, Gonzalo ED - Català, Andreu T1 - Classification in Non-stationary Environments Using Coresets over Sliding Windows T2 - Advances in Computational Intelligence - 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event, June 16-18, 2021, Proceedings, Part I Y1 - 2021 U6 - https://doi.org/10.1007/978-3-030-85030-2_11 SP - 126 EP - 137 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael ED - Rutkowski, Leszek ED - Scherer, Rafal ED - Korytkowski, Marcin ED - Pedrycz, Witold ED - Tadeusiewicz, Ryszard ED - Zurada, Jacek M. T1 - A Streaming Approach to the Core Vector Machine T2 - Artificial Intelligence and Soft Computing - 21st International Conference, ICAISC 2022, Zakopane, Poland, June 19-23, 2022, Proceedings, Part II Y1 - 2023 U6 - https://doi.org/10.1007/978-3-031-23480-4_8 SP - 91 EP - 101 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael ED - Rutkowski, Leszek ED - Scherer, Rafal ED - Korytkowski, Marcin ED - Pedrycz, Witold ED - Tadeusiewicz, Ryszard ED - Zurada, Jacek M. T1 - Random Projection in the Presence of Concept Drift in Supervised Environments T2 - Artificial Intelligence and Soft Computing - 19th International Conference, ICAISC 2020, Zakopane, Poland, October 12-14, 2020, Proceedings, Part I Y1 - 2020 U6 - https://doi.org/10.1007/978-3-030-61401-0_48 SP - 514 EP - 524 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Raab, Christoph A1 - Schleif, Frank-Michael ED - Vellido, Alfredo ED - Gibert, Karina ED - Angulo, Cecilio ED - David Martı́n-Guerrero, José T1 - Passive Concept Drift Handling via Momentum Based Robust Soft Learning Vector Quantization T2 - Advances in Self-Organizing Maps, Learning Vector Quantization, Clustering and Data Visualization - Proceedings of the 13th International Workshop, WSOM+ 2019, Barcelona, Spain, June 26-28, 2019 Y1 - 2019 U6 - https://doi.org/10.1007/978-3-030-19642-4_20 SP - 200 EP - 209 ER - TY - CHAP A1 - Raab, Christoph A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael T1 - Reactive Soft Prototype Computing for frequent reoccurring Concept Drift T2 - 27th European Symposium on Artificial Neural Networks, ESANN 2019, Bruges, Belgium, April 24-26, 2019 Y1 - 2019 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael T1 - Random Projection in supervised non-stationary environments T2 - 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2020, Bruges, Belgium, October 2-4, 2020 Y1 - 2020 SP - 405 EP - 410 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Schleif, Frank-Michael T1 - Reactive Concept Drift Detection Using Coresets Over Sliding Windows T2 - 2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020, Canberra, Australia, December 1-4, 2020 Y1 - 2020 U6 - https://doi.org/10.1109/SSCI47803.2020.9308521 SP - 1350 EP - 1355 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Raab, Christoph A1 - Rossi, Fabrice A1 - Schleif, Frank-Michael T1 - Federated Learning - Methods, Applications and beyond T2 - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2021, Online event (Bruges, Belgium), October 6-8, 2021 Y1 - 2021 U6 - https://doi.org/10.14428/esann/2021.ES2021-4 ER - TY - CHAP A1 - Heusinger, Moritz A1 - Raab, Christoph A1 - Schleif, Frank-Michael T1 - Analyzing Dynamic Social Media Data via Random Projection - A New Challenge for Stream Classifiers T2 - 2020 IEEE Conference on Evolving and Adaptive Intelligent Systems, EAIS 2020, Bari, Italy, May 27-29, 2020 Y1 - 2020 U6 - https://doi.org/10.1109/EAIS48028.2020.9122780 SP - 1 EP - 8 ER - TY - CHAP A1 - Hartmann, Jürgen A1 - Dobhan, Alexander A1 - Engelmann, Bastian A1 - Eberhardt, Lars A1 - Heusinger, Moritz A1 - Raab, C A1 - Schleif, Frank-Michael A1 - Türk, M. T1 - Optimierung von Prozessen und Werkzeugmaschinen durch Bereitstellung, Analyse und Soll-Ist-Vergleich von Produktionsdaten: Digitalkonferenz Y1 - 2020 ER - TY - JOUR A1 - Ziegler, Cedric C. A1 - Dobhan, Alexander A1 - Heusinger, Moritz T1 - Applications of Neural Networks in Engineer-to-order Environment JF - Procedia CIRP N2 - Machine tool selection and quotation costing have a low level of automation in today's engineer-to-order environments. The decision-making process is based on imprecise human judgment even if all final product characteristics are known. To improve precision and save time, we propose to apply artificial neural networks that are trained on data of already produced products. In particular, we address the selection of several grinding wheels to produce a milling cutter, which is a multiple-criteria decision, using multi-label classification. The quotation costing is a single output regression problem. In both tasks, our results on real-world data show high accuracy. Y1 - 2022 U6 - https://doi.org/10.1016/j.procir.2022.09.052 VL - 112 SP - 140 EP - 145 PB - Elsevier ER - TY - JOUR A1 - Miller, Eddi A1 - Borysenko, Vladyslav A1 - Heusinger, Moritz A1 - Niedner, Niklas A1 - Engelmann, Bastian A1 - Schmitt, Jan T1 - Enhanced Changeover Detection in Industry 4.0 Environments with Machine Learning JF - Sensors Y1 - 2021 VL - 21 IS - 17 SP - 5896 EP - 5896 ER - TY - JOUR A1 - Hofmann, Jan A1 - Eberhardt, Lars A1 - Heusinger, Moritz A1 - Dobhan, Alexander A1 - Engelmann, Bastian A1 - Schleif, Frank-Michael T1 - Optimierung von Prozessen und Werkzeugmaschinen durch Bereitstellung, Analyse und Soll-Ist-Vergleich von Produktionsdaten JF - FHWS Science Journal N2 - Mit einem Umsatz von 103 Milliarden Euro ist die Metallindustrie eine der größten deutschen Industriebranchen. Diese ist von volatilen Marktbedingungen und hohem Wettbewerb geprägt [1][2]. Kleine und mittlere produzierende Unternehmen (sogenannte KMU) sehen zunehmend gravierende Probleme bei der Einhaltung von Lieferterminen bedingt durch hohe Durchlaufzeiten in der Produktion [3]. Neben kaufmännischen Planungssystemen zur Erstellung von Produktionsplänen nutzen Unternehmen als Planungsgrundlage weiterhin Excel mit 31 % und manuelle Prozesse mit 10 % [4]. Gleiches gilt für Produktwechselvorgänge auf Maschinen (Rüsten). Aufgrund dieser Aspekte ist es notwendig, die Rentabilität der KMU in der Metallindustrie zu steigern. Das wird durch effiziente Produktionsplanung und -steuerung, sowie der daraus resultierenden hohen Reaktionsfähigkeit und Flexibilität realisiert. Daher ist die Produktionsplanung auf die Markt- und Kundenanforderungen und die Anlageneffektivität auf ein hohes und stabiles Niveau auszurichten [5]. Hier bietet die Erfassung von Echtzeitdaten eine adäquate Reaktion auf die genannten Anforderungen. Ebenfalls liefert sie großes Potenzial für die Produktionsplanung und -steuerung, um die Disposition und Koordination von Arbeitsaufträgen zu optimieren. Weiterhin werden Störgrößen oder unvorhergesehene Planungsabweichungen reduziert [4][6]. Zusätzlich ist eine erhöhte Transparenz und Verbesserung menschlicher Entscheidungsprozesse notwendig. Dies kann durch datengetriebene Methoden unterstützt und sichergestellt werden [7]. Ein Ansatz zur Optimierung des Produktionsergebnisses kann durch die Erhöhung der Anlagenproduktivität selbst realisiert werden. Dazu muss die Verfügbarkeit der Anlagen durch Lokalisierung und Reduzierung von Verlusten erhöht werden. Die Umrüstungsprozesse tragen stark negativ zur Verfügbarkeit einer Produktion bei. Eine Steigerung der Gesamtanlageneffektivität (overall equipment effectiveness oder kurz OEE) in einer Fertigungsumgebung ist jedoch möglich durch eine intelligente Nutzung von Sensordaten mit Techniken wie z. B. Machine Learning (ML). KW - produktionsdaten KW - metall Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-20012 UR - https://nbn-resolving.org/urn:nbn:de:bvb:863-opus-19389 SN - 2196-6095 VL - 5 IS - 2 SP - 135 EP - 142 ER -