Lars Linsen

Hennes Rave, Katharina Kronenberg, Hannes Gödde et al.

Hyperspectral bioimaging techniques such as infrared (IR) microscopy and laser ablation-inductively coupled plasma-mass spectrometry (LA-ICP-MS) produce high-dimensional, spatially resolved datasets that require sophisticated analysis to reveal chemically and anatomically meaningful structures. Existing software solutions are typically modality-specific and cover only parts of the analytical workflow, forcing researchers to transfer data across multiple tools and manually reconcile results. We present MIA (Multiscale Image Analysis), a modality-agnostic visual analysis environment that integrates the full exploratory workflow -- from spectral preprocessing and dimensionality reduction to interactive segmentation and spectral similarity analysis -- within a single, tightly coupled interface. MIA supports hierarchical and landmark-based embeddings to handle datasets of varying scale and complexity, interactive and automatic segmentation with a shared state across all linked views, and multimodal analysis of co-registered datasets from different instruments. We demonstrate the effectiveness of MIA through three use cases drawn from real analytical chemistry workflows: (1) the recovery of biologically meaningful tissue compartments through derivative preprocessing and hierarchical embedding, (2) pigment identification via spectral similarity search with spatial overview, and (3) multimodal tissue characterization combining molecular IR and elemental LA-ICP-MS data. Qualitative feedback from domain expert collaborators confirms that MIA reduces the need for tool-switching and supports analytical insights that are difficult to obtain with existing software.

Simon Leistikow, Thomas Miro, Adrian Kummerländer et al.

Background and Objective: Hemodynamic analysis of blood flow through arteries and veins is critical for diagnosing cardiovascular diseases, such as aneurysms and stenoses, and for investigating cardiovascular parameters, such as turbulence and wall shear stress. For subject-specific analyses, the anatomy and blood flow of the subject can be captured non-invasively using structural and 4D Magnetic Resonance Imaging (MRI). Computational Fluid Dynamics (CFD), on the other hand, can be used to generate blood flow simulations by solving the Navier-Stokes equations. To generate and analyze subject-specific blood flow simulations, MRI and CFD have to be brought together. Methods: We present an interactive, customizable, and user-oriented visual analysis tool that assists researchers in both medicine and numerical analysis. Our open-source tool is applicable to domains such as CFD and MRI, and it facilitates the analysis of simulation results and medical data, especially in hemodynamic studies. It enables the creation of simulation ensembles with a high variety of parameters. Furthermore, it allows for the visual and analytical examination of simulations and measurements through 2D embeddings of the similarity space. Results: To demonstrate the effectiveness of our tool, we applied it to three real-world use cases, showcasing its ability to configure simulation ensembles and analyse blood flow dynamics. We evaluated our example cases together with MRI and CFD experts to further enhance features and increase the usability. Conclusions: By combining the strengths of both CFD and MRI, our tool provides a more comprehensive understanding of hemodynamic parameters, facilitating more accurate analysis of hemodynamic biomarkers.

Hennes Rave, Vladimir Molchanov, Lars Linsen

Scatterplots provide a visual representation of bivariate data (or 2D embeddings of multivariate data) that allows for effective analyses of data dependencies, clusters, trends, and outliers. Unfortunately, classical scatterplots suffer from scalability issues, since growing data sizes eventually lead to overplotting and visual clutter on a screen with a fixed resolution, which hinders the data analysis process. We propose an algorithm that compensates for irregular sample distributions by a smooth transformation of the scatterplot's visual domain. Our algorithm evaluates the scatterplot's density distribution to compute a regularization mapping based on integral images of the rasterized density function. The mapping preserves the samples' neighborhood relations. Few regularization iterations suffice to achieve a nearly uniform sample distribution that efficiently uses the available screen space. We further propose approaches to visually convey the transformation that was applied to the scatterplot and compare them in a user study. We present a novel parallel algorithm for fast GPU-based integral-image computation, which allows for integrating our de-cluttering approach into interactive visual data analysis systems.

Vladimir Molchanov, Hennes Rave, Lars Linsen

Cartograms are a technique for visually representing geographically distributed statistical data, where values of a numerical attribute are mapped to the size of geographic regions. Contiguous cartograms preserve the adjacencies of the original regions during the mapping. To be useful, contiguous cartograms also require approximate preservation of shapes and relative positions. Due to these desirable properties, contiguous cartograms are among the most popular ones. Most methods for constructing contiguous cartograms exploit a deformation of the original map. Aiming at the preservation of geographical properties, existing approaches are often algorithmically cumbersome and computationally intensive. We propose a novel deformation technique for computing time-varying contiguous cartograms based on integral images evaluated for a series of discrete density distributions. The density textures represent the given dynamic statistical data. The iterative application of the proposed mapping smoothly transforms the domain to gradually equalize the temporal density, i.e., region areas grow or shrink following their evolutionary statistical data. Global shape preservation at each time step is controlled by a single parameter that can be interactively adjusted by the user. Our efficient GPU implementation of the proposed algorithm is significantly faster than existing state-of-the-art methods while achieving comparable quality for cartographic accuracy, shape preservation, and topological error. We investigate strategies for transitioning between adjacent time steps and discuss the parameter choice. Our approach applies to comparative cartograms' morphing and interactive cartogram exploration.

Reyhaneh Sabbagh Gol, Dimitar Valkov, Lars Linsen

Hand kinematics can be measured in Human-Computer Interaction (HCI) with the intention to predict the user's intention in a reach-to-grasp action. Using multiple hand sensors, multivariate time series data are being captured. Given a number of possible actions on a number of objects, the goal is to classify the multivariate time series data, where the class shall be predicted as early as possible. Many machine-learning methods have been developed for such classification tasks, where different approaches produce favorable solutions on different data sets. We, therefore, employ an ensemble approach that includes and weights different approaches. To provide a trustworthy classification production, we present the XMTC tool that incorporates coordinated multiple-view visualizations to analyze the predictions. Temporal accuracy plots, confusion matrix heatmaps, temporal confidence heatmaps, and partial dependence plots allow for the identification of the best trade-off between early prediction and prediction quality, the detection and analysis of challenging classification conditions, and the investigation of the prediction evolution in an overview and detail manner. We employ XMTC to real-world HCI data in multiple scenarios and show that good classification predictions can be achieved early on with our classifier as well as which conditions are easy to distinguish, which multivariate time series measurements impose challenges, and which features have most impact.

Valerie Müller, Christian Sieg, Lars Linsen

Topic modeling is a state-of-the-art technique for analyzing text corpora. It uses a statistical model, most commonly Latent Dirichlet Allocation (LDA), to discover abstract topics that occur in the document collection. However, the LDA-based topic modeling procedure is based on a randomly selected initial configuration as well as a number of parameter values than need to be chosen. This induces uncertainties on the topic modeling results, and visualization methods should convey these uncertainties during the analysis process. We propose a visual uncertainty-aware topic modeling analysis. We capture the uncertainty by computing topic modeling ensembles and propose measures for estimating topic modeling uncertainty from the ensemble. Then, we propose to enhance state-of-the-art topic modeling visualization methods to convey the uncertainty in the topic modeling process. We visualize the entire ensemble of topic modeling results at different levels for topic and document analysis. We apply our visualization methods to a text corpus to document the impact of uncertainty on the analysis.

Karim Huesmann, Luis Garcia Rodriguez, Lars Linsen et al.

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is however poorly understood. In this study we introduce a perplexity-based sparsity definition to derive and visualise layer-wise activation measures. These novel explainable AI strategies reveal a surprising relationship between activation sparsity and overfitting, namely an increase in sparsity in the feature extraction layers shortly before the test loss starts rising. This tendency is preserved across network architectures and reguralisation strategies so that our measures can be used as a reliable indicator for overfitting while decoupling the network's generalisation capabilities from its loss-based definition. Moreover, our differentiable sparsity formulation can be used to explicitly penalise the emergence of sparsity during training so that the impact of reduced sparsity on overfitting can be studied in real-time. Applying this penalty and analysing activation sparsity for well known regularisers and in common network architectures supports the hypothesis that reduced activation sparsity can effectively improve the generalisation and classification performance. In line with other recent work on this topic, our methods reveal novel insights into the contradicting concepts of activation sparsity and network capacity by demonstrating that dense activations can enable discriminative feature learning while efficiently exploiting the capacity of deep models without suffering from overfitting, even when trained excessively.

Karim Huesmann, Soeren Klemm, Lars Linsen et al.

Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. Here, we demonstrate that neural network activation sparsity is a reliable indicator for overfitting which we utilize to propose novel targeted sparsity visualization and regularization strategies. Based on these strategies we are able to understand and counteract overfitting caused by activation sparsity and filter correlation in a targeted layer-by-layer manner. Our results demonstrate that targeted sparsity regularization can efficiently be used to regularize well-known datasets and architectures with a significant increase in image classification performance while outperforming both dropout and batch normalization. Ultimately, our study reveals novel insights into the contradicting concepts of activation sparsity and network capacity by demonstrating that targeted sparsity regularization enables salient and discriminative feature learning while exploiting the full capacity of deep models without suffering from overfitting, even when trained excessively.