@inproceedings{decke2023dado, abstract = {In this work, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations widely used in industry and engineering. We are interested in optimizing the design of structural components, where a set of parameters describes the shape. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two query strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our query strategies in accelerating design optimization. Furthermore, the introduced method is easily transferable to other self-optimization problems in industry and engineering.}, author = {Decke, Jens and Gruhl, Christian and Rauch, Lukas and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, doi = {10.1109/ICMLA58977.2023.00244}, interhash = {9818328a6809ca9723fcf46b834e1bf2}, intrahash = {e6ecfa5a1489519a2c4c3b9f08ceb2ee}, pages = {1611--1618}, publisher = {IEEE}, title = {DADO – Low-Cost Query Strategies for Deep Active Design Optimization}, year = 2023 } @inproceedings{nivarthi2023towards, abstract = {Anomaly detection plays a pivotal role in diverse realworld applications such as cybersecurity, fault detection, network monitoring, predictive maintenance, and highly automated driving. However, obtaining labeled anomalous data can be a formidable challenge, especially when anomalies exhibit temporal evolution. This paper introduces LATAM (Long short-term memory Autoencoder with Temporal Attention Mechanism) for few-shot anomaly detection, with the aim of enhancing detection performance in scenarios with limited labeled anomaly data. LATAM effectively captures temporal dependencies and emphasizes significant patterns in multivariate time series data. In our investigation, we comprehensively evaluate LATAM against other anomaly detection models, particularly assessing its capability in few-shot learning scenarios where we have minimal examples from the normal class and none from the anomalous class in the training data. Our experimental results, derived from real-world photovoltaic inverter data, highlight LATAM’s superiority, showcasing a substantial 27% mean F1 score improvement, even when trained on a mere two-week dataset. Furthermore, LATAM demonstrates remarkable results on the open-source SWaT dataset, achieving a 12% boost in accuracy with only two days of training data. Moreover, we introduce a simple yet effective dynamic thresholding mechanism, further enhancing the anomaly detection capabilities of LATAM. This underscores LATAM’s efficacy in addressing the challenges posed by limited labeled anomalies in practical scenarios and it proves valuable for downstream tasks involving temporal representation and time series prediction, extending its utility beyond anomaly detection applications.}, author = {Nivarthi, Chandana Priya and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, doi = {10.1109/ICMLA58977.2023.00218}, interhash = {2c7b944a23ce00dd5e4637ce2c572f31}, intrahash = {a4a29acb67656f837ca6e532fc88958d}, pages = {1444--1450}, publisher = {IEEE}, title = {Towards Few-Shot Time Series Anomaly Detection with Temporal Attention and Dynamic Thresholding}, year = 2023 } @inproceedings{heidecker2023context, abstract = {Context information provided along with a dataset can be very helpful for solving a problem because the additional knowledge is already available and does not need to be extracted. Moreover, the context indicates how diverse a dataset is, i.e., how many samples per context category are available to train and test machine learning (ML) models. In this article, we present context annotations for the BDD100k image dataset. The annotations comprise, for instance, information about daytime, road condition (dry/wet), and dirt on the windshield. Sometimes, no or only little data are available for unique or rare combinations of these context attributes. However, data that matches these context conditions is crucial when discussing corner cases: Firstly, most ML models, e.g., object detectors, are not trained on such data, which leads to the assumption that they will perform poorly in those situations. Secondly, data containing corner cases are required for validating ML models. With this in mind, separate ML models dedicated to context detection are useful for expanding the training set with additional data of special interest, such as corner cases.}, author = {Heidecker, Florian and Susetzky, Tobias and Fuchs, Erich and Sick, Bernhard}, booktitle = {IEEE International Conference on Intelligent Transportation Systems (ITSC)}, doi = {10.1109/ITSC57777.2023.10422414}, interhash = {176a956134ff5471596cb400e7df61af}, intrahash = {6a9cc7dc53de472e969176e9fa8a4f32}, pages = {1522--1529}, publisher = {IEEE}, title = {Context Information for Corner Case Detection in Highly Automated Driving}, year = 2023 } @inproceedings{moallemyoureh2023marked, abstract = {Spatio-Temporal Point Processes (STPPs) have recently become increasingly interesting for learning dynamic graph data since many scientific fields, ranging from mathematics, biology, social sciences, and physics to computer science, are naturally related and dynamic. While training Recurrent Neural Networks and solving PDEs for representing temporal data is expensive, TPPs were a good alternative. The drawback is that constructing an appropriate TPP for modeling temporal data requires the assumption of a particular temporal behavior of the data. To overcome this problem, Neural TPPs have been developed that enable learning of the parameters of the TPP. However, the research is relatively young for modeling dynamic graphs, and only a few TPPs have been proposed to handle edge-dynamic graphs. To allow for learning on a fully dynamic graph, we propose the first Marked Neural Spatio-Temporal Point Process (MNSTPP) that leverages a Dynamic Graph Neural Network to learn Spatio-TPPs to model and predict any event in a graph stream. In addition, our model can be updated efficiently by considering single events for local retraining.}, author = {Moallemy-Oureh, Alice and Beddar-Wiesing, Silvia and Nather, Rüdiger and Thomas, Josephine}, booktitle = {Workshop on Temporal Graph Learning (TGL), NeurIPS}, interhash = {cbaaa3961c750da47057c7dc57548dfb}, intrahash = {cd51b29eef2304afa558a492070b5433}, pages = {1--7}, title = {Marked Neural Spatio-Temporal Point Process Involving a Dynamic Graph Neural Network}, url = {https://openreview.net/forum?id=QJx3Cmddsy}, year = 2023 } @inproceedings{lachi2023graph, abstract = {In the domain of graph neural networks (GNNs), pooling operators are fundamental to reduce the size of the graph by simplifying graph structures and vertex features. Recent advances have shown that well-designed pooling operators, coupled with message-passing layers, can endow hierarchical GNNs with an expressive power regarding the graph isomorphism test that is equal to the Weisfeiler-Leman test. However, the ability of hierarchical GNNs to increase expressive power by utilizing graph coarsening was not yet explored. This results in uncertainties about the benefits of pooling operators and a lack of sufficient properties to guide their design. In this work, we identify conditions for pooling operators to generate WL-distinguishable coarsened graphs from originally WL-indistinguishable but non-isomorphic graphs. Our conditions are versatile and can be tailored to specific tasks and data characteristics, offering a promising avenue for further research.}, author = {Lachi, Veronica and Moallemy-Oureh, Alice and Roth, Andreas and Welke, Pascal}, booktitle = {Workshop on New Frontiers in Graph Learning, NeurIPS}, interhash = {a4898a33a173ccf4f46c04a5694994e3}, intrahash = {e1ea17f1ffa6ae37f7e79d245f6b5d6b}, pages = {1--7}, title = {Graph Pooling Provably Improves Expressivity}, url = {https://openreview.net/forum?id=lR5NYB9zrv}, year = 2023 } @inproceedings{magnussen2023leveraging, abstract = {Often, producing large labelled datasets for supervised machine learning is difficult and expensive. In cases where the expensive part is due to labelling and obtaining ground truth, it is often comparably easy to acquire large datasets containing unlabelled data points. For reproducible measurements, it is possible to record information on multiple data points being from the same reproducible measurement series, which should thus have an equal but unknown ground truth. In this article, we propose a method to incorporate a dataset of such unlabelled data points for which some data points are known to be equal in end-to-end training of otherwise labelled data. We show that, with the example of predicting the carotenoid concentration in human skin from optical multiple spatially resolved reflection spectroscopy data, the proposed method is capable of reducing the required number of labelled data points to achieve the same prediction accuracy for different model architectures. In addition, we show that the proposed method is capable of reducing the negative impact of noisy data when performing a repeated measurement of the same sample. }, author = {Magnussen, Birk Martin and Stern, Claudius and Sick, Bernhard}, booktitle = {International Conference on Computational Intelligence and Intelligent Systems (CIIS)}, doi = {10.1145/3638209.3638210}, interhash = {cfa80f8a0854c4ed202e26fede67f4ee}, intrahash = {eb478ebd071d2643bfe9752a0a25ee16}, pages = {1--6}, publisher = {ACM}, title = {Leveraging Repeated Unlabelled Noisy Measurements to Augment Supervised Learning}, url = {https://dl.acm.org/doi/10.1145/3638209.3638210}, year = 2023 } @article{beddarwiesing2024weisfeiler, abstract = {Graph Neural Networks (GNNs) are a large class of relational models for graph processing. Recent theoretical studies on the expressive power of GNNs have focused on two issues. On the one hand, it has been proven that GNNs are as powerful as the Weisfeiler–Lehman test (1-WL) in their ability to distinguish graphs. Moreover, it has been shown that the equivalence enforced by 1-WL equals unfolding equivalence. On the other hand, GNNs turned out to be universal approximators on graphs modulo the constraints enforced by 1-WL/unfolding equivalence. However, these results only apply to Static Attributed Undirected Homogeneous Graphs (SAUHG) with node attributes. In contrast, real-life applications often involve a much larger variety of graph types. In this paper, we conduct a theoretical analysis of the expressive power of GNNs for two other graph domains that are particularly interesting in practical applications, namely dynamic graphs and SAUGHs with edge attributes. Dynamic graphs are widely used in modern applications; hence, the study of the expressive capability of GNNs in this domain is essential for practical reasons and, in addition, it requires a new analyzing approach due to the difference in the architecture of dynamic GNNs compared to static ones. On the other hand, the examination of SAUHGs is of particular relevance since they act as a standard form for all graph types: it has been shown that all graph types can be transformed without loss of information to SAUHGs with both attributes on nodes and edges. This paper considers generic GNN models and appropriate 1-WL tests for those domains. Then, the known results on the expressive power of GNNs are extended to the mentioned domains: it is proven that GNNs have the same capability as the 1-WL test, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence. Moreover, the proof of the approximation capability is mostly constructive and allows us to deduce hints on the architecture of GNNs that can achieve the desired approximation.}, author = {Beddar-Wiesing, Silvia and D'Inverno, Alessio and Graziani, Caterina and Lachi, Veronica and Moallemy-Oureh, Alice and Scarselli, Franco and Thomas, Josephine}, doi = {10.1016/j.neunet.2024.106213}, interhash = {2f32fbb1387911744c61e5895b224cbc}, intrahash = {d2777197f992700161caeaa302801fb8}, journal = {Neural Networks}, pages = 106213, publisher = {Elsevier}, title = {Weisfeiler–Lehman goes dynamic: An analysis of the expressive power of Graph Neural Networks for attributed and dynamic graphs}, url = {https://www.sciencedirect.com/science/article/pii/S0893608024001370}, volume = 173, year = 2024 } @article{loeser2022vision, abstract = {Due to the ongoing trend towards a decarbonisation of energy use, the power system is expected to become the backbone of all energy sectors and thus the fundamental critical infrastructure. High penetration with distributed energy resources demands the coordination of a large number of prosumers, partly controlled by home energy management systems (HEMS), to be designed in such a way that the power system’s operational limits are not violated. On the grid level, distribution management systems (DMS) seek to keep the power system in the normal operational state. On the prosumer level, distributed HEMS optimise the internal power flows by setpoint specification of batteries, photovoltaic generators, or flexible loads. The vision of the ODiS (Organic Distribution System) initiative is to develop an architecture to operate a distribution grid reliably, with high resiliency, and fully autonomously by developing “organic” HEMS and DMS which possess multiple self-x capabilities, collectively referred to as self-management. Thus, ODiS seeks answers to the following question: How can we create the most appropriate models, techniques, and algorithms to develop novel kinds of self-configuring, self-organising, self-healing, and self-optimising DMS that are integrally coupled with the distributed HEMS? In this concept paper, the vision of ODiS is presented in detail based on a thorough review of the state of the art.}, author = {Loeser, Inga and Braun, Martin and Gruhl, Christian and Menke, Jan-Hendrik and Sick, Bernhard and Tomforde, Sven}, doi = {10.3390/en15030881}, interhash = {e50a289dec013d0734c525b6b1202f7c}, intrahash = {59ad7fc64fe334ebd891c97911a9b687}, journal = {Energies}, number = 3, pages = 881, publisher = {MDPI}, title = {The Vision of Self-Management in Cognitive Organic Power Distribution Systems}, url = {https://www.mdpi.com/1996-1073/15/3/881}, volume = 15, year = 2022 } @article{nivarthi2023multi, abstract = {Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.}, author = {Nivarthi, Chandana Priya and Vogt, Stephan and Sick, Bernhard}, doi = {10.3390/make5030062}, interhash = {ea288b3abb9b7e9d4b4cbda762618a3d}, intrahash = {184cd7568f877ca9620a01132c152162}, journal = {Machine Learning and Knowledge Extraction (MAKE)}, number = 3, pages = {1214--1233}, publisher = {MDPI}, title = {Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions}, url = {https://www.mdpi.com/2504-4990/5/3/62}, volume = 5, year = 2023 } @inproceedings{huang2023spatio, abstract = {RUL prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the existing literature, it appears that many studies either do not fully integrate both spatial and temporal features or employ only a single attention mechanism. Furthermore, there seems to be inconsistency in the choice of data normalization methods, particularly concerning operating conditions, which might influence predictive performance. To bridge these observations, this study presents the Spatio-Temporal Attention Graph Neural Network. Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively. The cascade of these extractors, combined with multihead attention mechanisms for both spatio-temporal dimensions, aims to improve predictive precision and refine model explainability. Comprehensive experiments were conducted on the CMAPSS dataset to evaluate the impact of unified versus clustering normalization. The findings suggest that our model performs state-of-the-art results using only the unified normalization. Additionally, when dealing with datasets with multiple operating conditions, cluster normalization enhances the performance of our proposed model by up to 27%.}, author = {Huang, Zhixin and He, Yujiang and Sick, Bernhard}, booktitle = {Computational Science and Computational Intelligence (CSCI)}, interhash = {d2c044e372780d668eb0140a724454e0}, intrahash = {ad927931297c4668fb4cda3fa215b717}, note = {(accepted)}, publisher = {IEEE}, title = {Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction}, year = 2023 } @book{tomforde2022organic, doi = {10.17170/kobra-202202215780}, editor = {Tomforde, Sven and Krupitzer, Christian}, interhash = {8d5f659463edbf43ec92eb3038e71f86}, intrahash = {7647b51cffa0dc81c1bdc564a4929c52}, publisher = {kassel university press}, series = {Intelligent Embedded Systems}, title = {Organic Computing -- Doctoral Dissertation Colloquium 2021}, volume = 20, year = 2022 } @inproceedings{schreck2023height, abstract = {We present a novel method for free space detection in dynamic environments like factory sites, crucial for autonomous forklifts to avoid collisions. It introduces a technique for fast surface normal estimation using spherical projected LiDAR data, which helps in detecting free space efficiently and in real-time. The method's effectiveness is proven with a 50.90% mIoU score on the Semantic KITTI dataset at 105 Hz, and a 63.30% mIoU score on a factory site dataset at 54 Hz.}, author = {Schreck, Steven and Reichert, Hannes and Hetzel, Manuel and Doll, Konrad and Sick, Bernhard}, booktitle = {International Conference on Control, Mechatronics and Automation (ICCMA)}, doi = {10.1109/ICCMA59762.2023.10374705}, interhash = {d3c0bbf124344c070311798efc0d96cd}, intrahash = {c68e47214fba4ebbe449b410278ca949}, pages = {171--176}, publisher = {IEEE}, title = {Height Change Feature Based Free Space Detection}, year = 2023 } @inproceedings{breitenstein2023what, abstract = {In safety-critical applications such as automated driving, perception errors may create an imminent risk to vulnerable road users (VRU). To mitigate the occurrence of unexpected and potentially dangerous situations, so-called corner cases, perception models are trained on a huge amount of data. However, the models are typically evaluated using task-agnostic metrics, which do not reflect the severity of safety-critical misdetections. Consequently, misdetections with particular relevance for the safe driving task should entail a more severe penalty during evaluation to pinpoint corner cases in large-scale datasets. In this work, we propose a novel metric IoUw that exploits relevance on the pixel level of the semantic segmentation output to extend the notion of the intersection over union (IoU) by emphasizing small areas of an image affected by corner cases. We (i) employ IoUw to measure the effect of pre-defined relevance criteria on the segmentation evaluation, and (ii) use the relevance-adapted IoUw to refine the identification of corner cases. In our experiments, we investigate vision-based relevance criteria and physical attributes as per-pixel criticality to factor in the imminent risk, showing that IoUw precisely accentuates the relevance of corner cases.}, author = {Breitenstein, Jasmin and Heidecker, Florian and Lyssenko, Maria and Bogdoll, Daniel and Bieshaar, Maarten and Zöllner, J. Marius and Sick, Bernhard and Fingscheidt, Tim}, booktitle = {Workshop on roBustness and Reliability of Autonomous Vehicles in the Open-world (BRAVO), ICCV}, interhash = {82fd272efc4669189c8e047fa90b6db9}, intrahash = {dd6f5a976f1b9423ffe3a36248745b42}, pages = {3991--4000}, title = {What Does Really Count? Estimating Relevance of Corner Cases for Semantic Segmentation in Automated Driving}, url = {https://openaccess.thecvf.com/content/ICCV2023W/BRAVO/html/Breitenstein_What_Does_Really_Count_Estimating_Relevance_of_Corner_Cases_for_ICCVW_2023_paper.html}, year = 2023 } @inproceedings{salzer2023time, abstract = {Graph Neural Networks (GNNs) provide a framework for computing functions over graphs based on learnable parameters, which gained much attention in recent years. The most popular GNN models, so-called convolutional GNN or message-passing GNN apply a neighborhood aggregation procedure to each node in a graph to compute its output. Usually, such GNNs are used for classification or prediction tasks over static graphs. However, this limits their applicability in contexts like social networks or knowledge graphs, where underlying graphs change stepwise or time-continuously. Temporal Graph Neural Networks (TGNN) try to close this gap. The general idea of TGNN is to generalize the neighborhood aggregation procedure mentioned above to temporal graphs, usually represented as a tuple of a base graph with a series of time-stamped observed changes. In most applications involving Neural Network based models, giving reliable safety certificates are highly desirable but also a significant challenge, especially because of the blackbox nature of neural models. In this extended abstract, we address the topic of verifying TGNN, which is an unexplored area of research. We present a first notion of a time-aware robustness property for TGNN used for link prediction tasks, motivated by recent work on similar time-aware attacks. Furthermore, we discuss our ongoing work regarding promising verification approaches for the presented or similar safety properties and possible next steps in this research direction.}, author = {Sälzer, Marco and Beddar-Wiesing, Silvia}, booktitle = {International Symposium on Temporal Representation and Reasoning (TIME)}, doi = {10.4230/LIPIcs.TIME.2023.19}, interhash = {2e42c833267591af092e0091fa040f3f}, intrahash = {16d1e6e5ffb9eb59bb08724aa72ba92a}, pages = {19:1--19:3}, title = {Time-aware Robustness of Temporal Graph Neural Networks for Link Prediction}, year = 2023 } @article{heinrich2023targeted, abstract = {In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.}, author = {Heinrich, René and Scholz, Christoph and Vogt, Stephan and Lehna, Malte}, codeurl = {https://github.com/FraunhoferIEE/taaowpf}, doi = {10.1007/s10994-023-06396-9}, interhash = {b25c4cf1609a5d217e90fe6761ada42d}, intrahash = {c85f3b4d92e02dde845c55776a4fa4e6}, journal = {Machine Learning}, number = 2, pages = {863--889}, publisher = {Springer}, title = {Targeted Adversarial Attacks on Wind Power Forecasts}, volume = 113, year = 2023 } @article{magnussen2023continuous, abstract = {Continuous Kernels have been a recent development in convolutional neural networks. Such kernels are used to process data sampled at different resolutions as well as irregularly and inconsistently sampled data. Convolutional neural networks have the property of translational invariance (e.g., features are detected regardless of their position in the measurement domain), which is unsuitable if the position of detected features is relevant for the prediction task. However, the capabilities of continuous kernels to process irregularly sampled data are still desired. This article introduces the continuous feature network, a novel method utilizing continuous kernels, for detecting global features at absolute positions in the data domain. Through a use case in processing multiple spatially resolved reflection spectroscopy data, which is sampled irregularly and inconsistently, we show that the proposed method is capable of processing such data directly without additional preprocessing or augmentation as is needed using comparable methods. In addition, we show that the proposed method is able to achieve a higher prediction accuracy than a comparable network on a dataset with position-dependent features. Furthermore, a higher robustness to missing data compared to a benchmark network using data interpolation is observed, which allows the network to adapt to sensors with a failure of individual light emitters or detectors without the need for retraining. The article shows how these capabilities stem from the continuous kernels used and how the number of available kernels to be trained affects the model. Finally, the article proposes a method to utilize the introduced method as a base for an interpretable model usable for explainable AI.}, author = {Magnussen, Birk Martin and Stern, Claudius and Sick, Bernhard}, interhash = {434184bb75ae12985550054d2fab2b1b}, intrahash = {c259363d28ef8db4fc8f92c8d1b22a55}, journal = {International Journal On Advances in Intelligent Systems}, number = {3&4}, pages = {43--50}, publisher = {ThinkMind}, title = {Continuous Feature Networks: A Novel Method to Process Irregularly and Inconsistently Sampled Data With Position-Dependent Features}, url = {http://www.thinkmind.org/index.php?view=article&articleid=intsys_v16_n34_2023_3}, volume = 16, year = 2023 } @inproceedings{magnussen2024optical, abstract = {Obesity is a common problem for many people. In order to assist people combating obesity, providing methods to quickly, easily, and inexpensively assess their body composition is important. This article investigates how noninvasive, optical sensors based on multiple spatially resolved reflection spectroscopy can be used to measure the body mass index and body composition parameters. Using machine learning to train continuous feature networks, it is possible to predict the body mass index of a subject, with a correlation of $R=0.61$ with $p<0.0001$. Similarly, the predicted body mass index shows correlations to both the subject's visceral fat ($R=0.44,p=0.0023$) and skeletal muscle mass index ($R=0.52,p=0.0003$), indicating that the trained neural network is capable of identifying both types of tissue. Strategies to independently detect either type of tissue are discussed.}, author = {Magnussen, Birk Martin and Möckel, Frank and Jessulat, Maik and Stern, Claudius and Sick, Bernhard}, booktitle = {International Conference on Bioinformatics and Computational Biology (ICBCB)}, interhash = {18ad3ce27575a6b6d7e73f635a3493c3}, intrahash = {cbb5f43d06e449f8f0cdcd3d498c989c}, note = {(accepted)}, publisher = {IEEE}, title = {Optical Detection of the Body Mass Index and Related Parameters Using Multiple Spatially Resolved Reflection Spectroscopy}, year = 2024 } @article{heidecker2023corner, abstract = {Applications using machine learning (ML), such as highly autonomous driving, depend highly on the performance of the ML model. The data amount and quality used for model training and validation are crucial. If the model cannot detect and interpret a new, rare, or perhaps dangerous situation, often referred to as a corner case, we will likely blame the data for not being good enough or too small in number. However, the implemented ML model and its associated architecture also influence the behavior. Therefore, the occurrence of prediction errors resulting from the ML model itself is not surprising. This work addresses a corner case definition from an ML model's perspective to determine which aspects must be considered. To achieve this goal, we present an overview of properties for corner cases that are beneficial for the description, explanation, reproduction, or synthetic generation of corner cases. To define ML corner cases, we review different considerations in the literature and summarize them in a general description and mathematical formulation, whereby the expected relevance-weighted loss is the key to distinguishing corner cases from common data. Moreover, we show how to operationalize the corner case characteristics to determine the value of a corner case. To conclude, we present the extended taxonomy for ML corner cases by adding the input, model, and deployment levels, considering the influence of the corner case properties.}, author = {Heidecker, Florian and Bieshaar, Maarten and Sick, Bernhard}, doi = {10.1186/s42467-023-00015-y}, interhash = {5b1d7bb1c601936a75db0ec2a314bd8b}, intrahash = {0c4bf55fdaa2f29b7bf25aa1cab45a6c}, journal = {AI Perspectives & Advances}, number = 1, pages = {1--17}, title = {Corner Cases in Machine Learning Processes}, url = {https://aiperspectives.springeropen.com/articles/10.1186/s42467-023-00015-y}, volume = 6, year = 2023 } @inproceedings{assenmacher2023towards, abstract = {Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active Learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised Learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas.}, author = {Aßenmacher, Matthias and Rauch, Lukas and Goschenhofer, Jann and Stephan, Andreas and Bischl, Bernd and Roth, Benjamin and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, interhash = {882f6a87062886130218d167ac495ca6}, intrahash = {eb7a15841410f3b4eab2ed55781bee9d}, pages = {65--73}, title = {Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering}, url = {https://ceur-ws.org/Vol-3470/paper7.pdf}, year = 2023 } @article{deinzer2023it, abstract = {Objective: To assess the effect of the toothbrush handle on video-observed toothbrushing behaviour and toothbrushing effectiveness Methods: This is a randomized counterbalanced cross-over study. N = 50 university students brushed their teeth at two occasions, one week apart, using either a commercial ergonomically designed manual toothbrush (MT) or Brushalyze V1 (BV1), a manual toothbrush with a thick cylindrical handle without any specific ergonomic features. Brushing behaviour was video-analysed. Plaque was assessed at the second occasion immediately after brushing. Participants directly compared the two brushes regarding their handling and compared them to the brushed they used at home. Results: The study participants found the BV1 significantly more cumbersome than the M1 or their brush at home. (p < 0.05). However, correlation analyses revealed a strong consistency of brushing behavior with the two brushes (0.71 < r < 0.91). Means differed only slightly (all d < 0.36). These differences became statistically significant only for the brushing time at inner surfaces (d = 0.31 p = 0.03) and horizontal movements at inner surfaces (d = 0.35, p = 0.02). Plaque levels at the gingival margins did not differ while slightly more plaque persisted at the more coronal aspects of the crown after brushing with BV1 (d = 0.592; p 0.042) Discussion: The results of the study indicate that the brushing handle does not play a major role in brushing behavior or brushing effectiveness.}, author = {Deinzer, Renate and Eidenhardt, Zdenka and Sohrabi, Keywan and Stenger, Manuel and Kraft, Dominik and Sick, Bernhard and Götz-Hahn, Franz and Bottenbruch, Carlotta and Berneburg, Nils and Weik, Ulrike}, doi = {10.21203/rs.3.rs-3491691/v1}, interhash = {c169f01a44fafb98de74a5dac12d33bc}, intrahash = {9d681945057ec9baa33fe2ed36892470}, journal = {Research Square}, note = {(preprint)}, title = {It is the habit not the handle that affects tooth brushing. Results of a randomised counterbalanced cross over study}, url = {https://www.researchsquare.com/article/rs-3491691/v1}, year = 2023 }