TY - JOUR A1 - Schramm, Simon A1 - Pieper, Matthias A1 - Vogl, Stefanie T1 - Orthogonal Procrustes and Machine Learning: Predicting Bill of Materials errors on time JF - Computers & Industrial Engineering N2 - In an industrial product development process, the Bill of Materials (BOM) is a hierarchical, multi-level representation of all components, parts and quantities of a product. With increasing complexity of industrial products, also BOMs become more complex and thus prone to errors, for example when the individual parts of a product are changed during the product development process. Frequently, these Bill of Materials errors have to be identified manually or by using simple, rule-based schemes. In this paper, we provide a technical background of BOMs, showing the intricacy of temporal BOMs errors in an industrial product development process. The work of other authors, which focused on association mining and tree reconciliation to detect Bill of Materials errors, is analysed. We found that there is currently no system being able to prescribe where in a Bill of Materials and when in the product development process, errors are probable to occur. Also, Machine Learning (ML) methods have not been applied yet. Based on these findings, we formalize the notions Bill of Materials and Bill of Materials errors. Furthermore, we present a deterministic distance measure for BOMS. We provide an answer to the main question of how to represent a Bill of Materials for Machine Learning tasks by solving the orthogonal Procrustes problem for dynamic, hierarchical datasets. Then, we describe an isolation forest based approach to temporal anomaly detection, which points at potential errors in a Bill of Materials at a specific timestamp. Furthermore, we apply Machine Learning and present a multi-output Multi Layer Perceptron for the prediction of temporal Bill of Materials errors. The model predicts where and at which point of time Bill of Materials errors are probable to occur, which renders it a prescriptive system. Eventually, we optimize the performance of our model using contextualization via -means clustering. Finally, we apply our prescriptive pipeline to a real world dataset and show its superiority to existing methods using a qualitative comparison. Y1 - 2023 U6 - https://doi.org/10.1016/j.cie.2023.109606 VL - 185 PB - Elsevier ER - TY - JOUR A1 - Schwab, E. A1 - Pogrebnoj, S. A1 - Freund, M. A1 - Flossmann, F. A1 - Vogl, Stefanie A1 - Frommolt, K.-H. T1 - Automated bat call classification using deep convolutional neural networks JF - Bioacoustics N2 - Identification of bats is most practically done by exploiting the characteristic features of their echolocation calls. This usually involves expert knowledge, expensive equipment and time-consuming post processing of previously recorded calls. Automated solutions exist, but are usually not as accurate as human experts. We present an automated solution for the processing of bat calls and identification of bat species with extremely high classification accuracy that can be used during live recording or in an automated post-processing software. Our algorithm is the first application of a Deep Convolutional Neural Network to classify bat species based on sound spectrogram images of their echolocation calls. We tested several deep CNN architectures including a modified Google Inception and a ResNet50 architecture. The nets were trained on a very large call database consisting of images of snippets of call spectrograms. All our software was developed in the Python programming language and an executable of the software is available on request. KW - image classification KW - Bat call KW - neural network KW - secholocation Y1 - 2022 U6 - https://doi.org/10.1080/09524622.2022.2050816 SP - 1 EP - 16 PB - Taylor & Francis ER - TY - JOUR A1 - Plonus, Rene-Marcel A1 - Vogl, Stefanie A1 - Floeter, Jens T1 - Automatic Segregation of Pelagic Habitats JF - Frontiers in Marine Science N2 - It remains difficult to segregate pelagic habitats since structuring processes are dynamic on a wide range of scales and clear boundaries in the open ocean are non-existent. However, to improve our knowledge about existing ecological niches and the processes shaping the enormous diversity of marine plankton, we need a better understanding of the driving forces behind plankton patchiness. Here we describe a new machine-learning method to detect and quantify pelagic habitats based on hydrographic measurements. An Autoencoder learns two-dimensional, meaningful representations of higher-dimensional micro-habitats, which are characterized by a variety of biotic and abiotic measurements from a high-speed ROTV. Subsequently, we apply a density-based clustering algorithm to group similar micro-habitats into associated pelagic macro-habitats in the German Bight of the North Sea. Three distinct macro-habitats, a “surface mixed layer,” a “bottom layer,” and an exceptionally “productive layer” are consistently identified, each with its distinct plankton community. We provide evidence that the model detects relevant features like the doming of the thermocline within an Offshore Wind Farm or the presence of a tidal mixing front. KW - machine learning KW - North Sea KW - submesoscale KW - pelagic habitats KW - plankton patchiness Y1 - 2021 U6 - https://doi.org/10.3389/fmars.2021.754375 PB - Frontiers ET - 8 ER - TY - JOUR A1 - Beck, Nico A1 - Dovern, Jonas A1 - Vogl, Stefanie T1 - Mind the naive forecast! a rigorous evaluation of forecasting models for time series with low predictability JF - Applied Intelligence N2 - In the field of time series forecasting, numerous machine learning studies have assessed the performance of new methods on highly volatile data from macroeconomics and finance. Unlike in other domains, where models are also compared to simpler statistical or naive baselines, they mostly compare the performance solely relative to other complex models. This approach may lead to limited conclusions and reduce the practical significance of the results, as it overlooks the unpredictability of some highly volatile time series in the datasets used. We apply state-of-the-art methods from time-series econometrics and machine learning, including autoregressive integrated moving average (ARIMA), exponential smoothing (ETS), Bayesian vector autoregressive model (BVAR), long-short term memory neural networks (LSTM), historical consistent neural networks (HCNN), deep vector autoregressive neural networks (DeepVAR), temporal fusion transformers (TFT), and extreme gradient boosting (XGBoost). Our results demonstrate that no method consistently outperforms the naive (no-change) forecast for highly volatile time series from two popular datasets containing exchange rates and stock prices, rendering comparative analysis between complex models less meaningful. In contrast, when applied to more predictable macroeconomic price indices, many of the methods significantly outperform naive forecasts. We find that the performance of machine learning models deteriorates more than that of statistical models for high-volatility time series. This study highlights the critical importance of using appropriate benchmark models, including cost-effective, simple approaches, on datasets that permit meaningful conclusions. Y1 - 2025 U6 - https://doi.org/10.1007/s10489-025-06268-w VL - 55 IS - 6 PB - Springer ER - TY - JOUR A1 - Vogl, Stefanie A1 - Laux, Patrick A1 - Bialas, Joachim A1 - Reifenberger, Christian T1 - Modelling Precipitation Intensities from X-Band Radar Measurements Using Artificial Neural Networks—A Feasibility Study for the Bavarian Oberland Region JF - water N2 - Radar data may potentially provide valuable information for precipitation quantification, especially in regions with a sparse network of in situ observations or in regions with complex topography. Therefore, our aim is to conduct a feasibility study to quantify precipitation intensities based on radar measurements and additional meteorological variables. Beyond the well-established Z–R relationship for the quantification, this study employs Artificial Neural Networks (ANNs) in different settings and analyses their performance. For this purpose, the radar data of a station in Upper Bavaria (Germany) is used and analysed for its performance in quantifying in situ observations. More specifically, the effects of time resolution, time offsets in the input data, and meteorological factors on the performance of the ANNs are investigated. It is found that ANNs that use actual reflectivity as only input are outperforming the standard Z–R relationship in reproducing ground precipitation. This is reflected by an increase in correlation between modelled and observed data from 0.67 (Z–R) to 0.78 (ANN) for hourly and 0.61 to 0.86, respectively, for 10 min time resolution. However, the focus of this study was to investigate if model accuracy benefits from additional input features. It is shown that an expansion of the input feature space by using time-lagged reflectivity with lags up to two and additional meteorological variables such as temperature, relative humidity, and sunshine duration significantly increases model performance. Thus, overall, it is shown that a systematic predictor screening and the correspondent extension of the input feature space substantially improves the performance of a simple Neural Network model. For instance, air temperature and relative humidity provide valuable additional input information. It is concluded that model performance is dependent on all three ingredients: time resolution, time lagged information, and additional meteorological input features. Taking all of these into account, the model performance can be optimized to a correlation of 0.9 and minimum model bias of 0.002 between observed and modelled precipitation data even with a simple ANN architecture. Y1 - 2022 U6 - https://doi.org/10.3390/w14030276 VL - 14 IS - 3 SP - 1 EP - 17 PB - MDPI ER - TY - JOUR A1 - Paul Figueroa Cotorogea, B.S. A1 - Marino, Giuseppe A1 - Vogl, Stefanie T1 - Data driven health monitoring of Peltier modules using machine-learning-methods JF - SLAS Technology N2 - Thermal cyclers are used to perform polymerase chain reaction runs (PCR runs) and Peltier modules are the key components in these instruments. The demand for thermal cyclers has strongly increased during the COVID-19 pandemic due to the fact that they are important tools used in the research, identification, and diagnosis of the virus. Even though Peltier modules are quite durable, their failure poses a serious threat to the integrity of the instrument, which can lead to plant shutdowns and sample loss. Therefore, it is highly desirable to be able to predict the state of health of Peltier modules and thus reduce downtime. In this paper methods from three sub-categories of supervised machine learning, namely classical methods, ensemble methods and convolutional neural networks, were compared with respect to their ability to detect the state of health of Peltier modules integrated in thermal cyclers. Device-specific data from on-deck thermal cyclers (ODTC®) supplied by INHECO Industrial Heating & Cooling GmbH (Fig 1), Martinsried, Germany were used as a database for training the models. The purpose of this study was to investigate methods for data-driven condition monitoring with the aim of integrating predictive analytics into future product platforms. The results show that information about the state of health can be extracted from operational data - most importantly current readings - and that convolutional neural networks were the best at producing a generalized model for fault classification. KW - Supervised machine learning KW - Predictive maintenance KW - Condition monitoring KW - Polymerase-chain-reaction runs KW - Peltier modules Y1 - 2022 U6 - https://doi.org/10.1016/j.slast.2022.07.002 SN - 2472-6303 VL - 27 IS - 5 SP - 319 EP - 326 PB - Elsevier ER - TY - INPR A1 - Pagel, Johannes A1 - Vogl, Stefanie A1 - Israel, Laura T1 - Analyzing the Impact of Redaction on Document Classification Performance of Deep CNN Models N2 - Many companies are facing growing data archives leading to an increasing focus on the automated classification of documents in corporate processes. Due to data protection guidelines, development with clear data is often difficult. One way to overcome this difficulty is to desensitize documents using document redaction. The following study, therefore, examines the impact of redaction on the document classification performance of a deep CNN model by analyzing how the classifica- tion performance deteriorates when the model is trained on unredacted documents and evaluated on redacted data (unredacted model) or trained on redacted data and applied to unredacted documents (redacted model). For the former condition, a loss in accuracy of 2.56%P was found and a loss of 2.08%P for the latter. We were also able to show that the loss in performance differed greatly between document classes and was influenced by their proportion of redacted area (unredacted model: r=0.31; redacted model: r=0.87). For the model trained with redacted and evaluated on unredacted data, we also determined that the decrease in classification accu- racy was affected by the intra-class variability of the redacted area (r=0.74). From these results, recommendations for dealing with redacted data in document classification systems are derived. Y1 - 2024 U6 - https://doi.org/10.31219/osf.io/sntb3 PB - OSFPreprints ER - TY - BOOK A1 - Scheid, Sandro A1 - Vogl, Stefanie T1 - Data Science: Grundlagen, Methode und Modelle der Statistik KW - Big Data KW - Data Mining KW - Data Science Y1 - 2021 SN - 978-3-446-46663-0 SN - 978-3-446-47001-9 U6 - https://doi.org/10.3139/9783446470019 PB - Hanser ER - TY - JOUR A1 - Polz, Julius A1 - Glawion, Luca A1 - Gebisso, Hiob A1 - Altenstrasser, Lukas A1 - Graf, Maximilian A1 - Kunstmann, Harald A1 - Vogl, Stefanie A1 - Chwala, Christian T1 - Temporal Super-Resolution, Ground Adjustment, and Advection Correction of Radar Rainfall Using 3-D-Convolutional Neural Networks JF - IEEE Transactions on Geoscience and Remote Sensing N2 - Weather radars are highly sophisticated tools for quantitative precipitation estimation (QPE) and provide observations with unmatched spatial representativeness. However, their indirect measurement of precipitation high above ground leads to strong systematic errors compared to direct rain gauge measurements. Additionally, the temporal undersampling from 5-min instantaneous radar measurements requires advection correction. We present ResRadNet, a 3-D-convolutional residual neural network approach, to reduce these errors and, at the same time, increase the temporal resolution of the radar rainfall fields by a 5-min short-range prediction of 1-min time-steps. The network is trained to process spatiotemporal sequences of radar rainfall estimates from a composite product derived from 17 C-band weather radars in Germany. In contrast to previous approaches, we present a method that emphasizes the generation of spatiotemporally consistent and advection-corrected country-wide rainfall maps. Our approach significantly increased the Pearson correlation coefficient (PCC) of the radar product (from 0.63 to 0.74) and decreased the root mean squared error (mse) by 22% when compared to 247 rain gauges at a 5-min resolution. An additional large-scale comparison to eight years of data from 1138 independent manual daily gauges confirmed that the improvement is robust and transferable to new locations. Overall, our study shows the benefits of using 3-D convolutional neural networks (CNNs) for weather radar rainfall estimation to provide 1-min, ground-adjusted, that is, bias-corrected with respect to on-ground sensors, and advection-corrected radar rainfall estimates. KW - Rain KW - Radar measurements KW - Meteorological radar KW - Three-dimensional displays KW - Spaceborne radar KW - Spatial resolution KW - Reflectivity KW - Convolutional neural network (CNN) KW - deep learning KW - precipitation KW - residual neural network KW - weather radar Y1 - 2024 U6 - https://doi.org/10.1109/TGRS.2024.3371577 VL - 62 SP - 1 EP - 10 ER - TY - INPR A1 - Schramm, Simon A1 - Pieper, Matthias A1 - Vogl, Stefanie T1 - Orthogonal Procrustes Based Anomaly Detection and Error Prediction for Vehicle Bills of Materials T2 - SSRN N2 - Industrial Bill of Materials (BOM) suffer from an surging complexity and cause errors in production which have detrimental effects on a product’s profitability. Currently, BOM anomalies have to be identified manually and errors have to be detected in the same way. This preprint describes a combination of data analysis and Machine Learning methods, such as hierarchical and agglomerative clustering, an isolation forest algorithm, association mining and a multi-output Artificial Neural Network, all based on a deterministic distance measure for an industrial BOMs. Solving the orthogonal Procrustes problem for complex, multi-level matrices, a distance measure for real world industrial BOMs was derived. A multi-output MLP was used in order to predict error probabilities with a time- reference. Our results show how to detect anomalies and predict errors in a complex, multi-level BOM based on historical, labelled data. While other authors focus on the mere comparison of BOMs, we aimed at a holistic approach, combining descriptive and predictive methods in order to forecast where in a BOM and at what time of BOM creation process errors occur. The resulting, prescriptive system was tested using real world data and has shown to effectively predict where and when BOM errors are probable to occur. Consequently, the prescriptive system is superior to prior, purely predictive systems, can help to decrease errors and thereby decreases product development time and cost in real world companies. KW - Orthogonal Procrustes KW - Bill of Materials KW - Isolation forest KW - Multi-output Multi Layer Perceptron KW - Association mining KW - Prescriptive modeling Y1 - 2022 U6 - https://doi.org/10.2139/ssrn.4120321 PB - Elsevier ER - TY - JOUR A1 - Brunner, Philipp A1 - Vogl, Stefanie T1 - Extracting Product Improvement Insights from Social Media Comments Using Machine Learning: a Case Study in the Automotive Industry JF - Machine Learning and Knowledge Extraction N2 - This paper presents a scalable machine learning pipeline for extracting actionable, product-related insights from user-generated social media comments. Leveraging sentence embeddings from SBERT and unsupervised clustering (k-Means and agglomerative), the approach structures informal and noisy comments from Instagram and YouTube into topic groups intended to support thematic analysis. A case study on feedback regarding BMW vehicles, comprising more than 26,000 comments, illustrates how the pipeline can reveal recurring user concerns, such as design critiques, usability issues, and technology-related expectations, even in short and unstructured social media comments. The proposed pipeline operates without labeled data or manual annotation, enabling scalable application and transferability across product categories and industries. By transforming large-scale, unstructured consumer feedback into interpretable themes, the pipeline provides product teams with an efficient and structured basis for data-driven product development and improvement. KW - social media mining; sentence embeddings; unsupervised clustering; product feedback analysis; SBERT; natural language processing Y1 - 2026 U6 - https://doi.org/10.3390/make8020042 VL - 8 IS - 2 PB - MDPI ER -