@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} } @misc{BhatMuenchKaesoetal., author = {Bhat, Darshankumar and Muench, Stefan and Kaeso, Mathias and Roellig, Mike and Tschoepe, Constanze and Haertling, Thomas}, title = {Prognostics and health monitoring : case study of a light rail vehicle power converter assembly}, series = {2025 25th European Microelectronics and Packaging Conference \& Exhibition (EMPC)}, journal = {2025 25th European Microelectronics and Packaging Conference \& Exhibition (EMPC)}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-7395005-1-1}, doi = {10.23919/EMPC63132.2025.11222406}, pages = {1 -- 8}, abstract = {Electronic systems form the backbone of today's fast-moving and highly connected world. The reliability of electronics is consequently relevant, especially when electronics are used in safety-critical applications such as public transportation. Worn-out electronics can disrupt public transportation or even lead to catastrophic accidents. With the help of Prognostic and Health Monitoring (PHM), electronic failures can be anticipated in advance and predictive maintenance can be planned. However, the availability of sufficient data for health status prediction often is a challenge. In this article, we therefore present a cascade of machine learning (ML)-models for fatigue prediction based on insufficient data. As the use case, the application of a PHM approach to fleets of Light Rail Vehicles (LRVs) was chosen, and more specifically to solder joints in power converter assembly (PCA) used in these LRVs. Thermal loads are one of the major causes of solder fatigue. However, this load history is not directly available in most cases. Therefore, the first objective of the study is to predict thermal loads that the PCA experiences via virtual sensing techniques. Three prediction models - a linear model, a multilayer perceptron (MLP), and a long shortterm memory (LSTM) network - were developed to estimate the temperature based on the input current and ambient air temperature. Both the MLP and LSTM models demonstrated high prediction accuracy with coefficient of determination (R2) greater than 0.9, making them suitable for further use for fatigue estimation. The second objective of the study is to develop a solder fatigue estimation model. With the help of a virtual twin in the form of a physical model (finite element simulation), two sets of solder fatigue data were generated: one based on a synthetic temperature profile, and the other based on acquired mission profile loads from the LRV. An MLP was trained and successfully demonstrated to predict fatigue evolution in the solder joint under thermal loads with an averaged error less than 5 \%. Overall, this research provided two major PHM methodologies: virtual sensing for temperature prediction and a fatigue prediction model for solder joints in the PCA. The cascade of them enables a fatigue prediction for LRV based on insufficient data.}, language = {en} }