We present TSR-TVD, a novel deep learning framework that generates temporal super-resolution (TSR) of time-varying data (TVD) using adversarial learning. TSR-TVD is the first work that applies the ...recurrent generative network (RGN), a combination of the recurrent neural network (RNN) and generative adversarial network (GAN), to generate temporal high-resolution volume sequences from low-resolution ones. The design of TSR-TVD includes a generator and a discriminator. The generator takes a pair of volumes as input and outputs the synthesized intermediate volume sequence through forward and backward predictions. The discriminator takes the synthesized intermediate volumes as input and produces a score indicating the realness of the volumes. Our method handles multivariate data as well where the trained network from one variable is applied to generate TSR for another variable. To demonstrate the effectiveness of TSR-TVD, we show quantitative and qualitative results with several time-varying multivariate data sets and compare our method against standard linear interpolation and solutions solely based on RNN or CNN.
Rainbow color scheme is popularly used across the board in many scientific disciplines for visualizing data, yet heavily debated in visualization literature. In this paper, we first report an ...interdisciplinary visualization survey examining the prevalence rainbow color scheme use in scientific publications including a temporal analysis. Then we consolidate findings from empirical studies on the subject to better understand why and precisely when the rainbow color scheme might impair human performance with visualizations. Consequently, we systematically document and analyze the consequences of using the rainbow color scheme based on over 37,000 figures in 11,808 papers in information visualization, neuroscience, hydrology, geography, remote sensing and planetary science. Our findings reveal that while the rainbow scheme appears less and less in visualization-related publications, it remains popular in other scientific domains including remote sensing and planetary sciences (strikingly fourteen times more frequent in remote sensing and planetary sciences than in information visualization outlets). We also find that conflicting findings about human performance with the rainbow color scheme is most likely explained by what the users are asked to do with it (i.e., task type). We detail and typify tasks used in the related empirical work in an effort to organize the current understanding on the subject, and translate it to practicable recommendations. We believe our review and analyses bring clarity and nuance to “the rainbow debate” and enable better-informed visualization advice.
Alternative Splicing (AS) is an essential mechanism for eukaryotes. However, the consequences of deleting a single exon can be dramatic for the organism and can lead to cancer in humans. ...Additionally, alternative 5′ and 3′ splice sites, which define the boundaries of exons, also play key roles to human disorders. Therefore, Investigating AS events is crucial for understanding the molecular basis of human diseases and developing therapeutic strategies. Workflow for AS event analysis can be sampling followed by data analysis with bioinformatics to identify the different AS events in the control and case samples, data visualization for curation, and selection of relevant targets for experimental validation. The raw output of the analysis software does not favor the inspection of events by bioinformaticians requiring custom scripts for data visualization. In this work, we propose the Geneapp application with three modules: GeneappScript, GeneappServer, and GeneappExplorer. GeneappScript is a wrapper that assists in identifying AS in samples compared in two different approaches, while GeneappServer integrates data from AS analysis already performed by the user. In GeneappExplorer, the user visualizes the previous dataset by exploring AS events in genes with functional annotation. This targeted screens that Geneapp allows to perform helps in the identification of targets for experimental validation to confirm the hypotheses under study. The Geneapp is freely available for non-commercial use at https://geneapp.net to advance research on AS for bioinformatics.
•Geneapp assists in the generation and visualization of Alternative Splicing data.•Includes the script to run differential AS discovery pipeline on Debian distros.•Integrates AS results at the genomic, transcriptomic, and proteomic level.•Case study shows how to gain insights in AS research with human dataset.
On the whole, the field of data visualization is white. Contemporary views of historical data visualization tend to trace back to a few iconic visuals tied to European wars and conquests. The modern ...explosion of the field has been centered around the ideas of white men, as if they invented data visualization. Yet, Indigenous populations world-wide have been incorporating data visualization into their record keeping for centuries before anyone had heard of Edward Tufte. In this article, three Indigenous evaluators (Mohican/Munsee, Cherokee, and Tlingit) along with a non-Indigenous co-conspirator, will discuss their journeys creating space to weave together Western notions of data visualization best practices and Indigenous ways of knowing and storytelling. The authors focus their evaluative work on the support of Indigenous communities and will reflect on what has worked in communicating data, what hasn't, and how far data visualization has to go in all four directions.
Recent Advances in Open Set Recognition: A Survey Geng, Chuanxing; Huang, Sheng-Jun; Chen, Songcan
IEEE transactions on pattern analysis and machine intelligence,
10/2021, Volume:
43, Issue:
10
Journal Article
Peer reviewed
Open access
In real-world recognition/classification tasks, limited by various objective factors, it is usually difficult to collect training samples to exhaust all classes when training a recognizer or ...classifier. A more realistic scenario is open set recognition (OSR), where incomplete knowledge of the world exists at training time, and unknown classes can be submitted to an algorithm during testing, requiring the classifiers to not only accurately classify the seen classes, but also effectively deal with unseen ones. This paper provides a comprehensive survey of existing open set recognition techniques covering various aspects ranging from related definitions, representations of models, datasets, evaluation criteria, and algorithm comparisons. Furthermore, we briefly analyze the relationships between OSR and its related tasks including zero-shot, one-shot (few-shot) recognition/learning techniques, classification with reject option, and so forth. Additionally, we also review the open world recognition which can be seen as a natural extension of OSR. Importantly, we highlight the limitations of existing approaches and point out some promising subsequent research directions in this field.
Across scientific disciplines, there is a rapidly growing recognition of the need for more statistically robust, transparent approaches to data visualization. Complementary to this, many scientists ...have called for plotting tools that accurately and transparently convey key aspects of statistical effects and raw data with minimal distortion. Previously common approaches, such as plotting conditional mean or median barplots together with error-bars have been criticized for distorting effect size, hiding underlying patterns in the raw data, and obscuring the assumptions upon which the most commonly used statistical tests are based. Here we describe a data visualization approach which overcomes these issues, providing maximal statistical information while preserving the desired 'inference at a glance' nature of barplots and other similar visualization devices. These "raincloud plots" can visualize raw data, probability density, and key summary statistics such as median, mean, and relevant confidence intervals in an appealing and flexible format with minimal redundancy. In this tutorial paper, we provide basic demonstrations of the strength of raincloud plots and similar approaches, outline potential modifications for their optimal use, and provide open-source code for their streamlined implementation in R, Python and Matlab ( https://github.com/RainCloudPlots/RainCloudPlots). Readers can investigate the R and Python tutorials interactively in the browser using Binder by Project Jupyter.
Single-cell transcriptomics yields ever growing data sets containing RNA expression levels for thousands of genes from up to millions of cells. Common data analysis pipelines include a dimensionality ...reduction step for visualising the data in two dimensions, most frequently performed using t-distributed stochastic neighbour embedding (t-SNE). It excels at revealing local structure in high-dimensional data, but naive applications often suffer from severe shortcomings, e.g. the global structure of the data is not represented accurately. Here we describe how to circumvent such pitfalls, and develop a protocol for creating more faithful t-SNE visualisations. It includes PCA initialisation, a high learning rate, and multi-scale similarity kernels; for very large data sets, we additionally use exaggeration and downsampling-based initialisation. We use published single-cell RNA-seq data sets to demonstrate that this protocol yields superior results compared to the naive application of t-SNE.
Target selection is one of essential operation made available by interaction techniques in virtual reality (VR) environments. However, effectively positioning or selecting occluded objects is ...under-investigated in VR, especially in the context of high-density or a high-dimensional data visualization with VR. In this paper, we propose ClockRay , an occluded-object selection technique that can maximize the intrinsic human wrist rotation skills through the integration of emerging ray selection techniques in VR environments. We describe the design space of the ClockRay technique and then evaluate its performance in a series of user studies. Drawing on the experimental results, we discuss the benefits of ClockRay compared to two popular ray selection techniques - RayCursor and RayCasting . Our findings can inform the design of VR-based interactive visualization systems for high-density data.