LIVIVO - Search results -

Search results

Result 1 - 10 of total 68

Search options

Article ; Online: The Transform-and-Perform Framework: Explainable Deep Learning Beyond Classification.

Prasad, Vidya / van Sloun, Ruud J G / Elzen, Stef van den / Vilanova, Anna / Pezzotti, Nicola

IEEE transactions on visualization and computer graphics

2024 Volume 30, Issue 2, Page(s) 1502–1515

Abstract: In recent years, visual analytics (VA) has shown promise in alleviating the challenges of interpreting black-box deep learning (DL) models. While the focus of VA for explainable DL has been mainly on classification problems, DL is gaining popularity in ... ...

Abstract	In recent years, visual analytics (VA) has shown promise in alleviating the challenges of interpreting black-box deep learning (DL) models. While the focus of VA for explainable DL has been mainly on classification problems, DL is gaining popularity in high-dimensional-to-high-dimensional (H-H) problems such as image-to-image translation. In contrast to classification, H-H problems have no explicit instance groups or classes to study. Each output is continuous, high-dimensional, and changes in an unknown non-linear manner with changes in the input. These unknown relations between the input, model and output necessitate the user to analyze them in conjunction, leveraging symmetries between them. Since classification tasks do not exhibit some of these challenges, most existing VA systems and frameworks allow limited control of the components required to analyze models beyond classification. Hence, we identify the need for and present a unified conceptual framework, the Transform-and-Perform framework (T&P), to facilitate the design of VA systems for DL model analysis focusing on H-H problems. T&P provides a checklist to structure and identify workflows and analysis strategies to design new VA systems, and understand existing ones to uncover potential gaps for improvements. The goal is to aid the creation of effective VA systems that support the structuring of model understanding and identifying actionable insights for model improvements. We highlight the growing need for new frameworks like T&P with a real-world image-to-image translation application. We illustrate how T&P effectively supports the understanding and identification of potential gaps in existing VA systems.
Language	English
Publishing date	2024-01-02
Publishing country	United States
Document type	Journal Article
ISSN	1941-0506
ISSN (online)	1941-0506
DOI	10.1109/TVCG.2022.3219248
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Class-Constrained t-SNE: Combining Data Features and Class Probabilities.

Meng, Linhao / van den Elzen, Stef / Pezzotti, Nicola / Vilanova, Anna

IEEE transactions on visualization and computer graphics

2023 Volume 30, Issue 1, Page(s) 164–174

Abstract: Data features and class probabilities are two main perspectives when, e.g., evaluating model results and identifying problematic items. Class probabilities represent the likelihood that each instance belongs to a particular class, which can be produced ... ...

Abstract	Data features and class probabilities are two main perspectives when, e.g., evaluating model results and identifying problematic items. Class probabilities represent the likelihood that each instance belongs to a particular class, which can be produced by probabilistic classifiers or even human labeling with uncertainty. Since both perspectives are multi-dimensional data, dimensionality reduction (DR) techniques are commonly used to extract informative characteristics from them. However, existing methods either focus solely on the data feature perspective or rely on class probability estimates to guide the DR process. In contrast to previous work where separate views are linked to conduct the analysis, we propose a novel approach, class-constrained t-SNE, that combines data features and class probabilities in the same DR result. Specifically, we combine them by balancing two corresponding components in a cost function to optimize the positions of data points and iconic representation of classes - class landmarks. Furthermore, an interactive user-adjustable parameter balances these two components so that users can focus on the weighted perspectives of interest and also empowers a smooth visual transition between varying perspectives to preserve the mental map. We illustrate its application potential in model evaluation and visual-interactive labeling. A comparative analysis is performed to evaluate the DR results.
Language	English
Publishing date	2023-12-25
Publishing country	United States
Document type	Journal Article
ISSN	1941-0506
ISSN (online)	1941-0506
DOI	10.1109/TVCG.2023.3326600
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: ProactiV: Studying Deep Learning Model Behavior under Input Transformations.

Prasad, Vidya / Sloun, Ruud J G van / Vilanova, Anna / Pezzotti, Nicola

IEEE transactions on visualization and computer graphics

2023 Volume PP

Abstract: Deep learning (DL) models have shown performance benefits across many applications, from classification to image-to-image translation. However, low interpretability often leads to unexpected model behavior once deployed in the real world. Usually, this ... ...

Abstract	Deep learning (DL) models have shown performance benefits across many applications, from classification to image-to-image translation. However, low interpretability often leads to unexpected model behavior once deployed in the real world. Usually, this unexpected behavior is because the training data domain does not reflect the deployment data domain. Identifying a model's breaking points under input conditions and domain shifts, i.e., input transformations, is essential to improve models. Although visual analytics (VA) has shown promise in studying the behavior of model outputs under continually varying inputs, existing methods mainly focus on per-class or instance-level analysis. We aim to generalize beyond classification where classes do not exist and provide a global view of model behavior under co-occurring input transformations. We present a DL model-agnostic VA method (ProactiV) to help model developers proactively study output behavior under input transformations to identify and verify breaking points. ProactiV relies on a proposed input optimization method to determine the changes to a given transformed input to achieve the desired output. The data from this optimization process allows the study of global and local model behavior under input transformations at scale. Additionally, the optimization method provides insights into the input characteristics that result in desired outputs and helps recognize model biases. We highlight how ProactiV effectively supports studying model behavior with example classification and image-to-image translation tasks.
Language	English
Publishing date	2023-08-03
Publishing country	United States
Document type	Journal Article
ISSN	1941-0506
ISSN (online)	1941-0506
DOI	10.1109/TVCG.2023.3301722
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Inclusion Depth for Contour Ensembles.

Chaves-de-Plaza, Nicolas F / Mody, Prerak / Staring, Marius / van Egmond, Rene / Vilanova, Anna / Hildebrandt, Klaus

IEEE transactions on visualization and computer graphics

2024 Volume PP

Abstract: Ensembles of contours arise in various applications like simulation, computer-aided design, and semantic segmentation. Uncovering ensemble patterns and analyzing individual members is a challenging task that suffers from clutter. Ensemble statistical ... ...

Abstract	Ensembles of contours arise in various applications like simulation, computer-aided design, and semantic segmentation. Uncovering ensemble patterns and analyzing individual members is a challenging task that suffers from clutter. Ensemble statistical summarization can alleviate this issue by permitting analyzing ensembles' distributional components like the mean and median, confidence intervals, and outliers. Contour boxplots, powered by Contour Band Depth (CBD), are a popular non-parametric ensemble summarization method that benefits from CBD's generality, robustness, and theoretical properties. In this work, we introduce Inclusion Depth (ID), a new notion of contour depth with three defining characteristics. First, ID is a generalization of functional Half-Region Depth, which offers several theoretical guarantees. Second, ID relies on a simple principle: the inside/outside relationships between contours. This facilitates implementing ID and understanding its results. Third, the computational complexity of ID scales quadratically in the number of members of the ensemble, improving CBD's cubic complexity. This also in practice speeds up the computation enabling the use of ID for exploring large contour ensembles or in contexts requiring multiple depth evaluations like clustering. In a series of experiments on synthetic data and case studies with meteorological and segmentation data, we evaluate ID's performance and demonstrate its capabilities for the visual analysis of contour ensembles.
Language	English
Publishing date	2024-01-05
Publishing country	United States
Document type	Journal Article
ISSN	1941-0506
ISSN (online)	1941-0506
DOI	10.1109/TVCG.2024.3350076
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Strategies towards Fully Recyclable Commercial Epoxy Resins: Diels-Alder Structures in Sustainable Composites.

Vidal, Julio / Hornero, Carlos / De la Flor, Silvia / Vilanova, Anna / Dieste, Jose Antonio / Castell, Pere

Polymers

2024 Volume 16, Issue 8

Abstract: The Diels-Alder equilibrium is a widely known process in chemistry that can be used to provide a thermoset structure with recyclability and reprocessability mechanisms. In this study, a commercial epoxy resin is modified through the integration of ... ...

Abstract	The Diels-Alder equilibrium is a widely known process in chemistry that can be used to provide a thermoset structure with recyclability and reprocessability mechanisms. In this study, a commercial epoxy resin is modified through the integration of functional groups into the network structure to provide superior performance. The present study has demonstrated that it is possible to adapt the curing process to efficiently incorporate these moieties in the final structure of commercial epoxy-based resins. It also evaluates the impact that they have on the final properties of the cured composites. In addition, different approaches have been studied for the incorporation of the functional group, adjusting and adapting the stoichiometry of the system components due to the differences in reactivity caused by the presence of the incorporated reactive groups, with the objective of maintaining comparable ratios of epoxy/amine groups in the formulation. Finally, it has been demonstrated that although the Diels-Alder equilibrium responds under external conditions, such as temperature, different sets of parameters and behaviors are to be expected as the structures are integrated into the thermoset, generating new equilibrium temperatures. In this way, the present research has explored sustainable strategies to enable the recyclability of commercial thermoset systems through crosslinking control and its modification.
Language	English
Publishing date	2024-04-09
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2527146-5
ISSN	2073-4360 ; 2073-4360
ISSN (online)	2073-4360
ISSN	2073-4360
DOI	10.3390/polym16081024
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Diffusion MRI visualization.

Schultz, Thomas / Vilanova, Anna

NMR in biomedicine

2018 Volume 32, Issue 4, Page(s) e3902

Abstract: Modern diffusion magnetic resonance imaging (dMRI) acquires intricate volume datasets and biological meaning can only be found in the relationship between its different measurements. Suitable strategies for visualizing these complicated data have been ... ...

Abstract	Modern diffusion magnetic resonance imaging (dMRI) acquires intricate volume datasets and biological meaning can only be found in the relationship between its different measurements. Suitable strategies for visualizing these complicated data have been key to interpretation by physicians and neuroscientists, for drawing conclusions on brain connectivity and for quality control. This article provides an overview of visualization solutions that have been proposed to date, ranging from basic grayscale and color encodings to glyph representations and renderings of fiber tractography. A particular focus is on ongoing and possible future developments in dMRI visualization, including comparative, uncertainty, interactive and dense visualizations.
MeSH term(s)	Color ; Diffusion Magnetic Resonance Imaging ; Diffusion Tensor Imaging ; Humans
Language	English
Publishing date	2018-02-27
Publishing country	England
Document type	Journal Article ; Review
ZDB-ID	1000976-0
ISSN	1099-1492 ; 0952-3480
ISSN (online)	1099-1492
ISSN	0952-3480
DOI	10.1002/nbm.3902
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.A 2869: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Article ; Online: Stabilization and visual analysis of video-recorded sailing sessions.

Reichert, Gijs M W / Pieras, Marcos / Marroquim, Ricardo / Vilanova, Anna

Visual computing for industry, biomedicine, and art

2021 Volume 4, Issue 1, Page(s) 26

Abstract: One common way to aid coaching and seek to improve athletes' performance is by recording training sessions for posterior analysis. In the case of sailing, coaches record videos from another boat, but usually rely on handheld devices, which may lead to ... ...

Abstract	One common way to aid coaching and seek to improve athletes' performance is by recording training sessions for posterior analysis. In the case of sailing, coaches record videos from another boat, but usually rely on handheld devices, which may lead to issues with the footage and missing important moments. On the other hand, by autonomously recording the entire session with a fixed camera, the analysis becomes challenging owing to the length of the video and possible stabilization issues. In this work, we aim to facilitate the analysis of such full-session videos by automatically extracting maneuvers and providing a visualization framework to readily locate interesting moments. Moreover, we address issues related to image stability. Finally, an evaluation of the framework points to the benefits of video stabilization in this scenario and an appropriate accuracy of the maneuver detection method.
Language	English
Publishing date	2021-10-19
Publishing country	Germany
Document type	Journal Article
ISSN	2524-4442
ISSN (online)	2524-4442
DOI	10.1186/s42492-021-00093-x
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Harassment disparities and risk profile within lesbian, gay, bisexual and transgender Spanish adult population: Comparisons by age, gender identity, sexual orientation, and perpetration context.

Devís-Devís, José / Pereira-García, Sofía / Valencia-Peris, Alexandra / Vilanova, Anna / Gil-Quintana, Javier

Frontiers in public health

2022 Volume 10, Page(s) 1045714

Abstract: Lesbian, Gay, Bisexual and Transgender (LGBT) harassment disparities have become a public health issue due to discrimination and the effects on these people's health and wellbeing. The purpose was to compare harassment disparities within the Spanish ... ...

Abstract	Lesbian, Gay, Bisexual and Transgender (LGBT) harassment disparities have become a public health issue due to discrimination and the effects on these people's health and wellbeing. The purpose was to compare harassment disparities within the Spanish adult LGBT population according to age, gender identity, sexual orientation and the context of perpetration and to describe the harassment risk profile. A sample of 1,051 LGBT adults participated in a cross-sectional study. Frequencies, percentages and Chi-square tests of independence for stablishing significant differences (
MeSH term(s)	Young Adult ; Humans ; Female ; Male ; Transgender Persons ; Gender Identity ; Cross-Sectional Studies ; Sexual and Gender Minorities ; Sexual Behavior
Language	English
Publishing date	2022-12-15
Publishing country	Switzerland
Document type	Journal Article ; Research Support, Non-U.S. Gov't
ZDB-ID	2711781-9
ISSN	2296-2565 ; 2296-2565
ISSN (online)	2296-2565
ISSN	2296-2565
DOI	10.3389/fpubh.2022.1045714
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: PanVA: Pangenomic Variant Analysis.

van den Brandt, Astrid van den / Jonkheer, Eef M / van Workum, Dirk-Jan M / van de Wetering, Huub / Smit, Sandra / Vilanova, Anna

IEEE transactions on visualization and computer graphics

2023 Volume PP

Abstract: Genomics researchers increasingly use multiple reference genomes to comprehensively explore genetic variants underlying differences in detectable characteristics between organisms. Pangenomes allow for an efficient data representation of multiple related ...

Abstract	Genomics researchers increasingly use multiple reference genomes to comprehensively explore genetic variants underlying differences in detectable characteristics between organisms. Pangenomes allow for an efficient data representation of multiple related genomes and their associated metadata. However, current visual analysis approaches for exploring these complex genotype-phenotype relationships are often based on single reference approaches or lack adequate support for interpreting the variants in the genomic context with heterogeneous (meta)data. This design study introduces PanVA, a visual analytics design for pangenomic variant analysis developed with the active participation of genomics researchers. The design uniquely combines tailored visual representations with interactions such as sorting, grouping, and aggregation, allowing users to navigate and explore different perspectives on complex genotype-phenotype relations. Through evaluation in the context of plants and pathogen research, we show that PanVA helps researchers explore variants in genes and generate hypotheses about their role in phenotypic variation.
Language	English
Publishing date	2023-06-02
Publishing country	United States
Document type	Journal Article
ISSN	1941-0506
ISSN (online)	1941-0506
DOI	10.1109/TVCG.2023.3282364
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images

Vieth, Alexander / Vilanova, Anna / Lelieveldt, Boudewijn / Eisemann, Elmar / Höllt, Thomas

2022

Abstract: High-dimensional imaging is becoming increasingly relevant in many fields from astronomy and cultural heritage to systems biology. Visual exploration of such high-dimensional data is commonly facilitated by dimensionality reduction. However, common ... ...

Abstract	High-dimensional imaging is becoming increasingly relevant in many fields from astronomy and cultural heritage to systems biology. Visual exploration of such high-dimensional data is commonly facilitated by dimensionality reduction. However, common dimensionality reduction methods do not include spatial information present in images, such as local texture features, into the construction of low-dimensional embeddings. Consequently, exploration of such data is typically split into a step focusing on the attribute space followed by a step focusing on spatial information, or vice versa. In this paper, we present a method for incorporating spatial neighborhood information into distance-based dimensionality reduction methods, such as t-Distributed Stochastic Neighbor Embedding (t-SNE). We achieve this by modifying the distance measure between high-dimensional attribute vectors associated with each pixel such that it takes the pixel's spatial neighborhood into account. Based on a classification of different methods for comparing image patches, we explore a number of different approaches. We compare these approaches from a theoretical and experimental point of view. Finally, we illustrate the value of the proposed methods by qualitative and quantitative evaluation on synthetic data and two real-world use cases. Comment: 10 pages main paper, 8 pages supplemental material. To appear at IEEE 15th Pacific Visualization Symposium 2022
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
Subject code	006
Publishing date	2022-02-18
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED