@misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes Ferdinand Joachim and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian}, series = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, journal = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, publisher = {European Language Resources Association}, isbn = {978-2-493814-07-4}, pages = {28 -- 35}, abstract = {In this paper we show how word class based language modeling can support the integration of a small language in modern applications of speech technology. The methods described in this paper can be applied for any language. We demonstrate the methods on Upper Sorbian. The word classes model the semantic expressions of numerals, date and time of day. The implementation of the created grammars was realized in the form of finite-state-transducers (FSTs) and minimalists grammars (MGs). We practically demonstrate the usage of the FSTs in a simple smart-home speech application, that is able to set wake-up alarms and appointments expressed in a variety of spontaneous and natural sentences. While the created MGs are not integrated in an application for practical use yet, they provide evidence that MGs could potentially work more efficient than FSTs in built-on applications. In particular, MGs can work with a significantly smaller lexicon size, since their more complex structure lets them generate more expressions with less items, while still avoiding wrong expressions.}, language = {en} } @misc{KraljevskiJuIvanovetal., author = {Kraljevski, Ivan and Ju, Yong Chul and Ivanov, Dmitrij and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {How to Do Machine Learning with Small Data? - A Review from an Industrial Perspective}, series = {arXiv}, journal = {arXiv}, abstract = {Artificial intelligence experienced a technological breakthrough in science, industry, and everyday life in the recent few decades. The advancements can be credited to the ever-increasing availability and miniaturization of computational resources that resulted in exponential data growth. However, because of the insufficient amount of data in some cases, employing machine learning in solving complex tasks is not straightforward or even possible. As a result, machine learning with small data experiences rising importance in data science and application in several fields. The authors focus on interpreting the general term of "small data" and their engineering and industrial application role. They give a brief overview of the most important industrial applications of machine learning and small data. Small data is defined in terms of various characteristics compared to big data, and a machine learning formalism was introduced. Five critical challenges of machine learning with small data in industrial applications are presented: unlabeled data, imbalanced data, missing data, insufficient data, and rare events. Based on those definitions, an overview of the considerations in domain representation and data acquisition is given along with a taxonomy of machine learning approaches in the context of small data.}, language = {en} } @misc{KraljevskiDuckhornTschoepeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Schubert, Frank and Wolff, Matthias}, title = {Paper Tissue Softness Rating by Acoustic Emission Analysis}, series = {Applied Sciences}, volume = {13}, journal = {Applied Sciences}, number = {3}, issn = {2076-3417}, doi = {10.3390/app13031670}, abstract = {Softness is one of the essential properties of hygiene tissue products. Reliably measuring it is of utmost importance to ensure the balance between customer expectations and cost-effective tissue production. This study presents a method for assessing softness by analyzing acoustic emissions produced while tearing a tissue specimen. The aim was to train neural network models using the corrected results of human panel tests as the ground truth labels and to predict the tissue softness in two- and three-class recognition tasks. We also investigate the possibility of predicting some production parameters related to the softness property. The results proved that tissue softness and production parameters could be reliably estimated only by the tearing noise.}, language = {en} } @misc{JuKraljevskiNeunuebeletal., author = {Ju, Yong Chul and Kraljevski, Ivan and Neun{\"u}bel, Heiko and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Acoustic Resonance Testing of Small Data on Sintered Cogwheels}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {15}, issn = {1424-8220}, doi = {10.3390/s22155814}, abstract = {Based on the fact that cogwheels are indispensable parts in manufacturing, we present the acoustic resonance testing (ART) of small data on sintered cogwheels for quality control in the context of non-destructive testing (NDT). Considering the lack of extensive studies on cogwheel data by means of ART in combination with machine learning (ML), we utilize time-frequency domain feature analysis and apply ML algorithms to the obtained feature sets in order to detect damaged samples in two ways: one-class and binary classification. In each case, despite small data, our approach delivers robust performance: All damaged test samples reflecting real-world scenarios are recognized in two one-class classifiers (also called detectors), and one intact test sample is misclassified in binary ones. This shows the usefulness of ML and time-frequency domain feature analysis in ART on a sintered cogwheel dataset.}, language = {en} } @misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian, LREC 2022, Marseille}, series = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, journal = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, doi = {10.5281/zenodo.7501145}, pages = {1}, language = {en} } @book{WirschingSchmittWolff, author = {Wirsching, G{\"u}nther and Schmitt, Ingo and Wolff, Matthias}, title = {Quantenlogik, Band 1 : eine Einf{\"u}hrung f{\"u}r Ingenieure und Informatiker}, edition = {2. Auflage}, publisher = {Springer Vieweg}, address = {Berlin ; Heidelberg}, isbn = {978-3-662-71335-8}, doi = {10.1007/978-3-662-71335-8}, pages = {xiii, 495}, abstract = {Messungen an Quantenobjekten haben eine logische Struktur. Diese schließt die klassische Logik ein, geht jedoch weit dar{\"u}ber hinaus. Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge der Quantenlogik zu vermitteln und technische Anwendungsm{\"o}glichkeiten aufzuzeigen. Die daf{\"u}r erforderlichen mathematischen Sachverhalte werden anhand von Beispielen so erl{\"a}utert und motiviert, dass sie f{\"u}r angehende Ingenieure und Informatiker verst{\"a}ndlich sind. Die vorliegende Auflage wurde korrigiert und um zahlreiche Anwendungen, zus{\"a}tzliche Beispiele und Beweise erweitert sowie um ein neues Beispiel zur Mustererkennung erg{\"a}nzt.}, language = {de} } @book{WirschingWolffSchmitt, author = {Wirsching, G{\"u}nther and Wolff, Matthias and Schmitt, Ingo}, title = {Quantenlogik : eine Einf{\"u}hrung f{\"u}r Ingenieure und Informatiker}, edition = {1. Auflage}, publisher = {Springer Vieweg}, address = {Berlin ; Heidelberg}, isbn = {978-3-662-66779-8}, doi = {10.1007/978-3-662-66780-4}, pages = {XI, 386}, abstract = {Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse auf der Grundlage der klassischen Logik und der Quantenlogik zu entwickeln. Die daf{\"u}r erforderlichen mathematischen Sachverhalte werden so dargestellt und anhand von Beispielen motiviert, dass sie f{\"u}r angehende Ingenieure und Informatiker verst{\"a}ndlich sind. - Kompakte logische Darstellung der mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse - Beispiele erl{\"a}utern die Anwendung im Engineering Zielgruppen sind insbesondere Studierende der Ingenieurwissenschaften und der Informatik, aber auch Studierende der Mathematik oder der Physik k{\"o}nnen durch den anwendungsbezogenen Blick ihren Horizont erweitern.}, language = {de} } @misc{RoemerHuberLieblWolff, author = {R{\"o}mer, Ronald and Huber-Liebl, Markus and Wolff, Matthias}, title = {Quantum-inspired representation and querying of semiotic object properties by cognitive agents}, series = {2025 IEEE 16th International Conference on Cognitive Infocommunications (CogInfoCom)}, journal = {2025 IEEE 16th International Conference on Cognitive Infocommunications (CogInfoCom)}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {979-8-3503-5691-5}, doi = {10.1109/CogInfoCom66819.2025.11200567}, pages = {000129 -- 000134}, abstract = {Advanced intelligence often relies on the ability to build and use models. They allow the representation of knowledge, enable predictions, and serve to plan goal-directed actions. However, the successfull use of models requires a certain level of competence in interacting with models. This competence can be acquired by exploiting the separation of the cognitive agent from the objects represented in the model; because it allows the differentiation of individual semiotic levels. This includes the separation of self-sufficient and non self-sufficient object attributes. Non self-sufficient attributes that the agent assigned to potential target objects during the exploration phase form the starting point for the information requirement regarding the self-sufficient attributes of these objects. These attributes are required for target selection and the subsequent alignment of the model-based planning. This process is characterized by a series of queries to the environment model and thus shows a certain similarity to information retrieval (IR). Therefore, in this work we particularly investigate quantum-inspired IR-methods for representation and querying. We demonstrate that they are suitable for modelling cognitive effort and behavior, as they represent a realistic and universally applicable descriptive tool.}, language = {en} } @misc{HuberLieblRosenowRoemeretal., author = {Huber-Liebl, Markus and Rosenow, Tillmann and R{\"o}mer, Ronald and Wirsching, G{\"u}nther and Wolff, Matthias}, title = {Knowledge representation and querying with tensors for a class of practical test problems}, series = {Refereed Paper Proceedings - KM Conference 2025 - Siena, Italy}, journal = {Refereed Paper Proceedings - KM Conference 2025 - Siena, Italy}, publisher = {International Institute for Applied Knowledge Management}, pages = {111 -- 123}, abstract = {We further promote the idea of quantum inspiration and propose to equip cognitive systems not only with tensors for data representation but also for operation representation and querying. We discuss ideas from information retrieval and translate them into our method of behavioral control. We formalize the method with tensor algebra and discuss its extensions to learning. At the example of the problem of 𝑁-dimensional aiming, we visualize the transfer of our stated theoretical foundation to a class of practical test problems.}, language = {en} } @misc{SchmittSowoidnichGosswamietal., author = {Schmitt, Ingo and Sowoidnich, Kay and Gosswami, Tapashi and Sumpf, Bernd and Maiwald, Martin and Wolff, Matthias}, title = {PCA-based peak feature selection for classification of spectroscopic datasets}, series = {Journal of chemometrics}, volume = {39}, journal = {Journal of chemometrics}, number = {11}, publisher = {John Wiley \& Sons Ltd.}, address = {New York, NY}, issn = {0886-9383}, doi = {10.1002/cem.70074}, pages = {1 -- 14}, abstract = {Reducing feature dimensionality in spectroscopic data is crucial for efficient analysis and classification. Using all available features for classification typically results in an unacceptably high runtime and poor accuracy. Popular feature extraction methods, such as principal component analysis (PCA), linear discriminant analysis (LDA), and autoencoders, reduce feature dimensionality by extracting latent features that can be challenging to interpret. To enable better human interpretation of the classification model, we avoid extraction methods and instead propose applying feature selection methods. In this work, we develop an innovative PCA-based feature selection method for spectroscopic data, providing an essential subset of the original features. As an important advantage, no prior knowledge about the characteristic signals of the respective target substance is required. In this proof-of-concept study, the proposed method is initially characterized using simulated Raman and infrared absorption datasets. From the top five PCA eigenvectors of spectroscopic data, we identify a set of three top peaks each at specific wavenumbers (features). The compact set of selected features is then used for classification tasks applying a decision tree. Based on two well-defined spectroscopic datasets, our study demonstrates that our new method of PCA-based peak finding outperforms selected other approaches with regard to interpretability and accuracy. For both investigated datasets, accuracies greater than 97\% are achieved. Our approach shows large potential for accurate classification combined with interpretability in further scenarios involving spectroscopic datasets.}, language = {en} }