05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
11 results
Search Results
Item Open Access A deep learning approach for large-scale groundwater heat pump temperature prediction(2022) Scheurer, StefaniaHeating and cooling buildings is one of the most energy-intensive aspects of modern life. To minimize the impact on global warming and decelerate climate change, more efficient and carbon emission-mitigating technologies such as openloop groundwater heat pumps (GWHP) for heating and cooling buildings are being used and quickly adopted. Nowadays, in order to guarantee their optimal use and prevent negative interactions, city planners need to optimize their placement in the urban landscape. This optimization process requires fast models that simulate the effect of a GWHP on the groundwater temperature. Considering a large domain with multiple GWHPs, this work introduces a framework for the groundwater temperature prediction. While using a learned local surrogate model, a convolutional neural network, to predict the local temperature field around every single GWHP, a physics-informed neural network (PINN) is employed afterwards to correct the global initial solution of stitched together local predictions. As the violations of the physical laws described by the underlying partial differential equation(s) are spatially unevenly distributed, two different methods for drawing sampling points, on the basis of which the training of the PINN to correct the global initial solution takes place, are investigated and compared. This work shows that it is possible for a PINN to correct the global initial solution of stitched together local predictions in a domain with multiple GWHPs. However, there are still opportunities to improve the quality and decrease the computational time of the presented framework. The best method for drawing sampling points depends on the scenario and the placement of the GWHPs. Thus, no general statement can be made, which of the two methods is more suitable. This work provides a good basis for further investigation of the presented framework.Item Open Access Improving the accuracy of musculotendon models for the simulation of active lengthening(2023) Millard, Matthew; Kempter, Fabian; Stutzig, Norman; Siebert, Tobias; Fehr, JörgVehicle accidents can cause neck injuries which are costly for individuals and society. Safety systems could be designed to reduce the risk of neck injury if it were possible to accurately simulate the tissue-level injuries that later lead to chronic pain. During a crash, reflexes cause the muscles of the neck to be actively lengthened. Although the muscles of the neck are often only mildly injured, the forces developed by the neck’s musculature affect the tissues that are more severely injured. In this work, we compare the forces developed by MAT_156, LS-DYNA’s Hill-type model, and the newly proposed VEXAT muscle model during active lengthening. The results show that Hill-type muscle models underestimate forces developed during active lengthening, while the VEXAT model can more faithfully reproduce experimental measurements.Item Open Access Comparison of different Hyperparameter-Tuners for Support Vector Machines : an analysis using Parallel Least-Squares SVM Library on GPU(2024) Dzubba, Yannick MarianWorking with large datasets requires sophisticated tools. One such tool developed for classification is the Support Vector Machine (SVM). As with any ML algorithm, the user has to set several different Hyper Parameter (HP) to run a SVM. Finding the optimal choice of HPs is important for model performance and it is highly dependent on the dataset. Given the number of different HPs, a search space might be massive, so optimization methods have been developed, to automate this search. This work aims to compare three popular choices: The Grid Search, the Random Search and Bayesian Model Search. They are compared in different metrics, such as performance, runtime and energy. Optuna [ASY+19] was used as optimizer backend, it implements all three optimizer types, it implements Tree-Parzan Estimator (TPE) as Bayesian Search algorithm. It was connected to Parallel Least-Squares Support Vector Machine (PLSSVM) [VCBP22] as SVM implementation. PLSSVM can efficiently exploit parallel compute cores. The optimizers have been tested on a selection of different search spaces and datasets with PLSSVM running on Graphic Processing Unit (GPU).Item Open Access The art of brainwaves : a survey on event-related potential visualization practices(2024) Mikheev, Vladimir; Skukies, René; Ehinger, Benedikt V.Item Open Access Real-time visualized and GPU-accelerated lattice Boltzmann simulations(2025) Graf, MarcelIn a preceding project, four lattice Boltzmann algorithms were implemented on the CPU using HPX. Building up on this project, the goal of this work is to implement the two most suitable algorithms on the GPU together with a framework permitting real-time visualization. In the propaedeuticum, fundamental concepts of GPU programming are elaborated, and based on the insights gained, the aptitude of the four algorithms from the project for a portation to the GPU is investigated. The two-lattice and the swap algorithm were identified as the most promising candidates. The visualization framework was designed using the Dear ImGui and ImPlot APIs. In the bachelor thesis, the swap algorithm and multiple variants of the two-lattice algorithm were realized using AdaptiveCpp, which is one of two major implementations of the SYCL standard. Kármán vortex streets were chosen as a scenario demonstrating the capabilities of the proposed simulations. Since all algorithms update the lattice faster than the frontend can accept new frames, all of them are suitable for fulfilling the objective under the limitations imposed by the visualization framework. Similarly to the project, a simple and mostly runtime-coordinated two-lattice variant was recognized as the most convenient and, at the same time, very competitive implementation. Out of the data layouts proposed by Mattila et al., the bundle layout is well suited for devices with small caches, while the stream layout uses the memory bandwidth more efficiently. The optimal work group size and subdomain shape also depend on the targeted hardware.Item Open Access Prompt-based continual learning for visual question answering(2024) Ostertag, MagnusIn an ever-evolving world, Continual Learning (CL) strives to enable a costly trained model to learn new tasks without forgetting previously acquired knowledge. This work critically examines current CL benchmarks for Visual Question Answering (VQA), identifying significant shortcomings in the construction introducing bias. To address these issues, we propose a new CL-VQA benchmark based on GQA, designed to be incremental in both the language and the visual modality. Combined with learning it in one modality only, it can offer rich new diagnostics for a model. Additionally, we extend DualPrompt, a prompt-based CL method, DualPrompt, to the multi-modal domain. Using Dark Experience Replay as a baseline, we evaluate the performance against the new benchmark.Item Open Access Immersive analysis of multi-scalar field point clouds(2025) Flach, Ayla-IrinaPoint cloud data is increasingly used as a digital representation of three-dimensional objects in the real world. As acquisition devices become more commonly available (some smartphones now include Light Detection and Ranging (LiDAR) sensors), “intelligent” buildings provide growing amounts of multi-variate data and the size of the resulting point clouds continues to increase, novel techniques for visualization and exploration of the data within its spatial context are required. Traditional tools for this purpose rely on two-dimensional desktop environments which often pose challenges such as a steep learning curve and difficulties in correctly conveying spatial context. Recent research has explored the use of Virtual Reality (VR) for a more immersive exploration of point clouds. This project introduces an immersive VR environment, which provides the ability to explore multiple scalar fields associated with point cloud data using two distinct visualization methods. Additionally, users can annotate the point cloud with a virtual painting device while navigating with natural walking movement by means of an omnidirectional treadmill. This functionality can be used for manual classification of objects in the point cloud as well as for generation of artificial scalar data where none is available. A pilot study is then conducted to assess user satisfaction and system usability.Item Open Access Uncertainty quantification and propagation in surrogate-based Bayesian inference(2025) Reiser, Philipp; Aguilar, Javier Enrique; Guthke, Anneli; Bürkner, Paul-ChristianSurrogate models are statistical or conceptual approximations for more complex simulation models. In this context, it is crucial to propagate the uncertainty induced by limited simulation budget and surrogate approximation error to predictions, inference, and subsequent decision-relevant quantities. However, quantifying and then propagating the uncertainty of surrogates is usually limited to special analytic cases or is otherwise computationally very expensive. In this paper, we propose a framework enabling a scalable, Bayesian approach to surrogate modeling with thorough uncertainty quantification, propagation, and validation. Specifically, we present three methods for Bayesian inference with surrogate models given measurement data. This is a task where the propagation of surrogate uncertainty is especially relevant, because failing to account for it may lead to biased and/or overconfident estimates of the parameters of interest. We showcase our approach in three detailed case studies for linear and nonlinear real-world modeling scenarios. Uncertainty propagation in surrogate models enables more reliable and safe approximation of expensive simulators and will therefore be useful in various fields of applications.Item Open Access Research data management in simulation science : infrastructure, tools, and applications(2024) Flemisch, Bernd; Hermann, Sibylle; Herschel, Melanie; Pflüger, Dirk; Pleiss, Jürgen; Range, Jan; Roy, Sarbani; Takamoto, Makoto; Uekermann, BenjaminResearch Data Management (RDM) has gained significant traction in recent years, being essential to allowing research data to be, e.g., findable, accessible, interoperable, and reproducible (FAIR), thereby fostering collaboration or accelerating scientific findings. We present solutions for RDM developed within the DFG-Funded Cluster of Excellence EXC2075 Data-Integrated Simulation Science (SimTech). After an introduction to the scientific context and challenges faced by simulation scientists, we outline the general data management infrastructure and present tools that address these challenges. Exemplary domain applications demonstrate the use and benefits of the proposed data management software solutions. These are complemented by additional measures for enablement and dissemination to foster the adoption of these techniques.Item Open Access Towards trustworthy amortized Bayesian inference with deep learning(2025) Schmitt, Marvin; Bürkner, Paul-Christian (Prof. Dr.)