@misc{KraljevskiBissiriDuckhornetal., author = {Kraljevski, Ivan and Bissiri, Maria Paola and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Glottal Stops in Upper Sorbian: A Data-Driven Approach}, series = {Proc. Interspeech 2021, 30 August - 3 September, 2021, Brno, Czechia}, journal = {Proc. Interspeech 2021, 30 August - 3 September, 2021, Brno, Czechia}, doi = {10.21437/Interspeech.2021-1101}, pages = {1001 -- 1005}, abstract = {We present a data-driven approach for the quantitative analysis of glottal stops before word-initial vowels in Upper Sorbian, a West Slavic minority language spoken in Germany. Glottal stops are word-boundary markers and their detection can improve the performance of automatic speech recognition and speech synthesis systems. We employed cross-language transfer using an acoustic model in German to develop a forced-alignment method for the phonetic segmentation of a read-speech corpus in Upper Sorbian. The missing phonemic units were created by combining the existing phoneme models. In the forced-alignment procedure, the glottal stops were considered optional in front of word-initial vowels. To investigate the influence of speaker type (males, females, and children) and vowel on the occurrence of glottal stops, binomial regression analysis with a generalized linear mixed model was performed. Results show that children glottalize word-initial vowels more frequently than adults, and that glottal stop occurrences are influenced by vowel quality.}, language = {en} } @misc{KraljevskiDuckhornBarthetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Barth, Martin and Tsch{\"o}pe, Constanze and Schubert, Frank and Wolff, Matthias}, title = {Autoencoder-based Ultrasonic NDT of Adhesive Bonds}, series = {IEEE SENSORS 2021, Conference Proceedings, Oct 31- Nov 4, Sydney, Australia}, journal = {IEEE SENSORS 2021, Conference Proceedings, Oct 31- Nov 4, Sydney, Australia}, publisher = {IEEE}, isbn = {978-1-7281-9501-8}, doi = {10.1109/SENSORS47087.2021.9639864}, pages = {4}, abstract = {We present an approach for ultrasonic non-destructive testing of adhesive bonding employing unsupervised machine learning with autoencoders.The models are trained exclusively on the features derived from pulse-echo ultrasonic signals on a specimen with good adhesive bonding and tested on another specimen with artificially added defects.The resulting pseudo-probabilities indicating anomalies are visualized and presented along to the C-scan of the same specimen. As a result, we achieved improved representation of the defects, allowing their automatic and reliable detection.}, language = {en} } @misc{KraljevskiDuckhornTschoepeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Convolutional Autoencoders for Health Indicators Extraction in Piezoelectric Sensors}, series = {2020 IEEE Sensors, 25-28 Oct. 2020, Rotterdam, Netherlands,}, journal = {2020 IEEE Sensors, 25-28 Oct. 2020, Rotterdam, Netherlands,}, address = {Rotterdam, Netherlands}, isbn = {978-1-7281-6801-2}, doi = {10.1109/SENSORS47125.2020.9323023}, pages = {1 -- 4}, abstract = {We present a method for extracting health indicators from piezoelectric sensors applied in the case of microfluidic valves. Convolutional autoencoders were used to train a model on the normal operating conditions and tested on signals of different valves. The results of the model performance evaluation, as well as, the qualitative presentation of the indicator plots for each tested component, showed that the used approach is capable of detecting features that correspond to increasing component degradation. The extracted health indicators are the prerequisite and input for reliable remaining useful life prediction.}, language = {en} } @misc{KlimczakKuscheTschoepeetal., author = {Klimczak, Peter and Kusche, Isabel and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Menschliche und maschinelle Entscheidungsrationalit{\"a}t - Zur Kontrolle und Akzeptanz K{\"u}nstlicher Intelligenz}, series = {Zeitschrift f{\"u}r Medienwissenschaft 21 - K{\"u}nstliche Intelligenz}, journal = {Zeitschrift f{\"u}r Medienwissenschaft 21 - K{\"u}nstliche Intelligenz}, number = {2}, isbn = {978-3-8376-4468-5}, issn = {1869-1722}, doi = {/10.25969/mediarep/12631}, pages = {39 -- 45}, language = {de} } @incollection{KraljevskiTschoepeWolff, author = {Kraljevski, Ivan and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Limits and Prospects of Big Data and Small Data Approaches in AI Applications}, series = {AI - Limits and Prospects of Artificial Intelligence}, booktitle = {AI - Limits and Prospects of Artificial Intelligence}, editor = {Klimczak, Peter and Petersen, Christer}, publisher = {transcript Verlag}, address = {Bielefeld}, isbn = {978-3-8376-5732-6}, doi = {10.14361/9783839457320-006}, pages = {115 -- 142}, abstract = {The renaissance of artificial intelligence (AI) in the last decade can be credited to several factors, but chief among these is the ever-increasing availability and miniaturization of computational resources. This process has contributed to the rise of ubiquitous computing via popularizing smart devices and the Internet of Things in everyday life. In turn, this has resulted in the generation of increasingly enormous amounts of data. The tech giants are harvesting and storing data on their clients' behavior and, at the same time, introducing concerns about data privacy and protection. Suddenly, such an abundance of data and computing power, which was unimaginable a few decades ago, has caused a revival of old and the invention of new machine learning paradigms, like Deep Learning. Artificial intelligence has undergone a technological breakthrough in various fields, achieving better than human performance in many areas (such as vision, board games etc.). More complex tasks require more sophisticated algorithms that need more and more data. It has often been said that data is becoming a resource that is "more valuable than oil"; however, not all data is equally available and obtainable. Big data can be described by using the "four Vs"; data with immense velocity, volume, variety, and low veracity. In contrast, small data do not possess any of those qualities; they are limited in size and nature and are observed or produced in a controlled manner. Big data, along with powerful computing and storage resources, allow "black box" AI algorithms for various problems previously deemed unsolvable. One could create AI applications even without the underlying expert knowledge, assuming there are enough data and the right tools available (e.g. end-to-end speech recognition and generation, image and object recognition). There are numerous fields in science, industry and everyday life where AI has vast potential. However, due to the lack of big data, application is not straightforward or even possible. A good example is AI in medicine, where an AI system is intended to assist physicians in diagnosing and treating rare or previously never observed conditions, and there is no or an insufficient amount of data for reliable AI deployment. Both big and small data concepts have limitations and prospects for different fields of application. This paper will try to identify and present them by giving real-world examples in various AI fields.}, language = {en} } @misc{UhligAlkhasliSchubertetal., author = {Uhlig, Sebastian and Alkhasli, Ilkin and Schubert, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {A Review of Synthetic and Augmented Training Data for Machine Learning in Ultrasonic Non-Destructive Evaluation}, series = {Ultrasonics}, journal = {Ultrasonics}, number = {134}, issn = {1874-9968}, doi = {10.1016/j.ultras.2023.107041}, abstract = {Ultrasonic Testing (UT) has seen increasing application of machine learning (ML) in recent years, promoting higher-level automation and decision-making in flaw detection and classification. Building a generalized training dataset to apply ML in non-destructive evaluation (NDE), and thus UT, is exceptionally difficult since data on pristine and representative flawed specimens are needed. Yet, in most UT test cases flawed specimen data is inherently rare making data coverage the leading problem when applying ML. Common data augmentation (DA) strategies offer limited solutions as they don't increase the dataset variance, which can lead to overfitting of the training data. The virtual defect method and the recent application of generative adversarial neural networks (GANs) in UT are sophisticated DA methods targeting to solve this problem. On the other hand, well-established research in modeling ultrasonic wave propagations allows for the generation of synthetic UT training data. In this context, we present a first thematic review to summarize the progress of the last decades on synthetic and augmented UT training data in NDE. Additionally, an overview of methods for synthetic UT data generation and augmentation is presented. Among numerical methods such as finite element, finite difference, and elastodynamic finite integration methods, semi-analytical methods such as general point source synthesis, superposition of Gaussian beams, and the pencil method as well as other UT modeling software are presented and discussed. Likewise, existing DA methods for one- and multidimensional UT data, feature space augmentation, and GANs for augmentation are presented and discussed. The paper closes with an in-detail discussion of the advantages and limitations of existing methods for both synthetic UT training data generation and DA of UT data to aid the decision-making of the reader for the application to specific test cases.}, language = {en} } @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} }