TY - GEN A1 - Kraljevski, Ivan A1 - Bissiri, Maria Paola A1 - Duckhorn, Frank A1 - Tschöpe, Constanze A1 - Wolff, Matthias T1 - Glottal Stops in Upper Sorbian: A Data-Driven Approach T2 - Proc. Interspeech 2021, 30 August – 3 September, 2021, Brno, Czechia N2 - 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. Y1 - 2021 UR - https://www.isca-speech.org/archive/interspeech_2021/kraljevski21_interspeech.html U6 - https://doi.org/10.21437/Interspeech.2021-1101 SP - 1001 EP - 1005 ER - TY - GEN A1 - Kraljevski, Ivan A1 - Duckhorn, Frank A1 - Barth, Martin A1 - Tschöpe, Constanze A1 - Schubert, Frank A1 - Wolff, Matthias T1 - Autoencoder-based Ultrasonic NDT of Adhesive Bonds T2 - IEEE SENSORS 2021, Conference Proceedings, Oct 31- Nov 4, Sydney, Australia N2 - 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. Y1 - 2021 SN - 978-1-7281-9501-8 U6 - https://doi.org/10.1109/SENSORS47087.2021.9639864 PB - IEEE ER - TY - GEN A1 - Kraljevski, Ivan A1 - Duckhorn, Frank A1 - Tschöpe, Constanze A1 - Wolff, Matthias T1 - Convolutional Autoencoders for Health Indicators Extraction in Piezoelectric Sensors T2 - 2020 IEEE Sensors, 25-28 Oct. 2020, Rotterdam, Netherlands, N2 - 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. Y1 - 2020 UR - https://ieeexplore.ieee.org/document/9323023 SN - 978-1-7281-6801-2 U6 - https://doi.org/10.1109/SENSORS47125.2020.9323023 SP - 1 EP - 4 CY - Rotterdam, Netherlands ER - TY - GEN A1 - Klimczak, Peter A1 - Kusche, Isabel A1 - Tschöpe, Constanze A1 - Wolff, Matthias T1 - Menschliche und maschinelle Entscheidungsrationalität - Zur Kontrolle und Akzeptanz Künstlicher Intelligenz T2 - Zeitschrift für Medienwissenschaft 21 - Künstliche Intelligenz Y1 - 2019 UR - https://mediarep.org/handle/doc/13542 SN - 978-3-8376-4468-5 U6 - https://doi.org//10.25969/mediarep/12631 SN - 1869-1722 SN - 2296-4126 IS - 2 SP - 39 EP - 45 ER - TY - CHAP A1 - Kraljevski, Ivan A1 - Tschöpe, Constanze A1 - Wolff, Matthias ED - Klimczak, Peter ED - Petersen, Christer T1 - Limits and Prospects of Big Data and Small Data Approaches in AI Applications T2 - AI - Limits and Prospects of Artificial Intelligence N2 - 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. Y1 - 2023 UR - https://www.transcript-verlag.de/chunk_detail_seite.php?doi=10.14361%2F9783839457320-006 SN - 978-3-8376-5732-6 U6 - https://doi.org/10.14361/9783839457320-006 SP - 115 EP - 142 PB - transcript Verlag CY - Bielefeld ER - TY - GEN A1 - Uhlig, Sebastian A1 - Alkhasli, Ilkin A1 - Schubert, Frank A1 - Tschöpe, Constanze A1 - Wolff, Matthias T1 - A Review of Synthetic and Augmented Training Data for Machine Learning in Ultrasonic Non-Destructive Evaluation T2 - Ultrasonics N2 - 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. KW - Non-destructive testing KW - NDT KW - Non-destructive evaluation KW - NDE KW - Ultrasonic testing KW - Ultrasonics KW - Flaw detection KW - Machine learning KW - Artificial intelligence KW - Deep learning KW - Synthetic training data KW - Data augmentation Y1 - 2023 UR - https://www.sciencedirect.com/science/article/pii/S0041624X23001178 U6 - https://doi.org/10.1016/j.ultras.2023.107041 SN - 1874-9968 IS - 134 ER - TY - GEN A1 - Maier, Isidor Konrad A1 - Kuhn, Johannes Ferdinand Joachim A1 - Duckhorn, Frank A1 - Kraljevski, Ivan A1 - Sobe, Daniel A1 - Wolff, Matthias A1 - Tschöpe, Constanze T1 - Word Class Based Language Modeling: A Case of Upper Sorbian T2 - 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 N2 - 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. KW - word classes, minimalist grammar, language modeling, speech recognition, Upper Sorbian Y1 - 2022 UR - http://www.lrec-conf.org/proceedings/lrec2022/workshops/EURALI/pdf/2022.eurali-1.5.pdf SN - 978-2-493814-07-4 SP - 28 EP - 35 PB - European Language Resources Association ER - TY - GEN A1 - Kraljevski, Ivan A1 - Ju, Yong Chul A1 - Ivanov, Dmitrij A1 - Tschöpe, Constanze A1 - Wolff, Matthias T1 - How to Do Machine Learning with Small Data? - A Review from an Industrial Perspective T2 - arXiv N2 - 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. Y1 - 2023 UR - https://arxiv.org/abs/2311.07126 ER - TY - GEN A1 - Kraljevski, Ivan A1 - Duckhorn, Frank A1 - Tschöpe, Constanze A1 - Schubert, Frank A1 - Wolff, Matthias T1 - Paper Tissue Softness Rating by Acoustic Emission Analysis T2 - Applied Sciences N2 - 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. KW - acoustic emission KW - machine learning KW - tissue softness analysis Y1 - 2022 U6 - https://doi.org/10.3390/app13031670 SN - 2076-3417 VL - 13 IS - 3 ER - TY - GEN A1 - Ju, Yong Chul A1 - Kraljevski, Ivan A1 - Neunübel, Heiko A1 - Tschöpe, Constanze A1 - Wolff, Matthias T1 - Acoustic Resonance Testing of Small Data on Sintered Cogwheels T2 - Sensors N2 - 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. KW - acoustic resonance testing (ART) non-destructive testing (NDT) KW - deep learning KW - machine learning KW - small-data KW - non-destructive testing (NDT) Y1 - 2022 U6 - https://doi.org/10.3390/s22155814 SN - 1424-8220 VL - 22 IS - 15 ER - TY - GEN A1 - Maier, Isidor Konrad A1 - Kuhn, Johannes A1 - Duckhorn, Frank A1 - Kraljevski, Ivan A1 - Sobe, Daniel A1 - Wolff, Matthias A1 - Tschöpe, Constanze T1 - Word Class Based Language Modeling: A Case of Upper Sorbian, LREC 2022, Marseille T2 - Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13 Y1 - 2022 U6 - https://doi.org/10.5281/zenodo.7501145 ER - TY - BOOK A1 - Wirsching, Günther A1 - Schmitt, Ingo A1 - Wolff, Matthias T1 - Quantenlogik, Band 1 : eine Einführung für Ingenieure und Informatiker N2 - Messungen an Quantenobjekten haben eine logische Struktur. Diese schließt die klassische Logik ein, geht jedoch weit darüber hinaus. Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge der Quantenlogik zu vermitteln und technische Anwendungsmöglichkeiten aufzuzeigen. Die dafür erforderlichen mathematischen Sachverhalte werden anhand von Beispielen so erläutert und motiviert, dass sie für angehende Ingenieure und Informatiker verständlich sind. Die vorliegende Auflage wurde korrigiert und um zahlreiche Anwendungen, zusätzliche Beispiele und Beweise erweitert sowie um ein neues Beispiel zur Mustererkennung ergänzt. KW - Projektive Geometrie KW - Lineare Algebra KW - Verbandstheorie KW - Information Retrieval KW - Kognitive Systeme KW - Künstliche Intelligenz KW - Vektor-symbolische Architekturen KW - Quantenmessung KW - Wahrscheinlichkeiten KW - Anfragesysteme KW - Informationskodierung KW - Quantenlogik KW - Logik KW - Mathematische Strukturen KW - Logik der Orthogonalprojektoren KW - Quantenregister KW - Quantenbit KW - Qubits KW - Fuzzy-Logik KW - Skalarproduktraum Y1 - 2025 UR - https://link.springer.com/book/10.1007/978-3-662-71335-8 SN - 978-3-662-71335-8 SN - 978-3-662-71334-1 U6 - https://doi.org/10.1007/978-3-662-71335-8 PB - Springer Vieweg CY - Berlin ; Heidelberg ET - 2. Auflage ER - TY - BOOK A1 - Wirsching, Günther A1 - Wolff, Matthias A1 - Schmitt, Ingo T1 - Quantenlogik : eine Einführung für Ingenieure und Informatiker N2 - 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 dafür erforderlichen mathematischen Sachverhalte werden so dargestellt und anhand von Beispielen motiviert, dass sie für angehende Ingenieure und Informatiker verständlich sind. - Kompakte logische Darstellung der mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse - Beispiele erläutern die Anwendung im Engineering Zielgruppen sind insbesondere Studierende der Ingenieurwissenschaften und der Informatik, aber auch Studierende der Mathematik oder der Physik können durch den anwendungsbezogenen Blick ihren Horizont erweitern. KW - Projektive Geometrie KW - Lineare Algebra KW - Verbandstheorie KW - Information Retrieval KW - Kognitive Systeme KW - Künstliche Intelligenz KW - vektor-symbolische Architekturen KW - Quantenmessung KW - Wahrscheinlichkeiten KW - Anfragesysteme KW - Informationskodierung Y1 - 2023 UR - https://link.springer.com/book/10.1007/978-3-662-66780-4 SN - 978-3-662-66779-8 SN - 978-3-662-66780-4 U6 - https://doi.org/10.1007/978-3-662-66780-4 PB - Springer Vieweg CY - Berlin ; Heidelberg ET - 1. Auflage ER - TY - GEN A1 - Römer, Ronald A1 - Huber-Liebl, Markus A1 - Wolff, Matthias T1 - Quantum-inspired representation and querying of semiotic object properties by cognitive agents T2 - 2025 IEEE 16th International Conference on Cognitive Infocommunications (CogInfoCom) N2 - 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. KW - Information retrieval KW - Semiotics KW - Planning Y1 - 2025 SN - 979-8-3503-5691-5 U6 - https://doi.org/10.1109/CogInfoCom66819.2025.11200567 SP - 000129 EP - 000134 PB - IEEE CY - Piscataway, NJ ER - TY - GEN A1 - Huber-Liebl, Markus A1 - Rosenow, Tillmann A1 - Römer, Ronald A1 - Wirsching, Günther A1 - Wolff, Matthias T1 - Knowledge representation and querying with tensors for a class of practical test problems T2 - Refereed Paper Proceedings - KM Conference 2025 – Siena, Italy N2 - 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. KW - Knowledge representation KW - Cognitive agents KW - Tensor algebra KW - Quantum inspiration Y1 - 2025 UR - https://www.iiakm.org/conference/proceedings/KM2025_RefereedProceedingsPapers.pdf SP - 111 EP - 123 PB - International Institute for Applied Knowledge Management ER - TY - GEN A1 - Schmitt, Ingo A1 - Sowoidnich, Kay A1 - Gosswami, Tapashi A1 - Sumpf, Bernd A1 - Maiwald, Martin A1 - Wolff, Matthias T1 - PCA-based peak feature selection for classification of spectroscopic datasets T2 - Journal of chemometrics N2 - 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. KW - Cclassification KW - Decision tree KW - Peak finding KW - Principal component analysis KW - Spectroscopic data Y1 - 2025 U6 - https://doi.org/10.1002/cem.70074 SN - 0886-9383 SN - 1099-128X VL - 39 IS - 11 SP - 1 EP - 14 PB - John Wiley & Sons Ltd. CY - New York, NY ER -