Selecting the appropriate dimensionality reduction (DR) technique and determining its optimal hyperparameter settings that maximize the accuracy of the output projections typically involves extensive trial and error, often resulting in unnecessary computational overhead. To address this challenge, we propose a dataset-adaptive approach to DR optimization guided by structural complexity metrics. These metrics quantify the intrinsic complexity of a dataset, predicting whether higher-dimensional spaces are necessary to represent it accurately. Since complex datasets are often inaccurately represented in two-dimensional projections, leveraging these metrics enables us to predict the maximum achievable accuracy of DR techniques for a given dataset, eliminating redundant trials in optimizing DR. We introduce the design and theoretical foundations of these structural complexity metrics. We quantitatively verify that our metrics effectively approximate the ground truth complexity of datasets and confirm their suitability for guiding dataset-adaptive DR workflow. Finally, we empirically show that our dataset-adaptive workflow significantly enhances the efficiency of DR optimization without compromising accuracy.

Precise measurements from sensors are crucial, but data is usually collected from low-cost, low-tech systems, which are often inaccurate. Thus, they require further calibrations. To that end, we first identify three requirements for effective calibration under practical low-tech sensor conditions. Based on the requirements, we develop a model called TESLA, Transformer for effective sensor calibration utilizing logarithmic-binned attention. TESLA uses a high-performance deep learning model, Transformers, to calibrate and capture non-linear components. At its core, it employs logarithmic binning, to minimize attention complexity. TESLA achieves consistent real-time calibration, even with longer sequences and finer-grained time series in hardware-constrained systems. Experiments show that TESLA outperforms existing novel deep learning and newly crafted linear models in accuracy, calibration speed, and energy efficiency.

International audience

Interactive visualization editors empower users to author visualizations without writing code, but do not provide guidance on the art and craft of effective visual communication. In this article, we explore the potential of using an off-the-shelf large language models (LLMs) to provide actionable and customized feedback to visualization designers. Our implementation, Visualizationary, demonstrates how ChatGPT can be used for this purpose through two key components: a preamble of visualization design guidelines and a suite of perceptual filters that extract salient metrics from a visualization image. We present findings from a longitudinal user study involving 13 visualization designers-6 novices, 4 intermediates, and 3 experts-who authored a new visualization from scratch over several days. Our results indicate that providing guidance in natural language via an LLM can aid even seasoned designers in refining their visualizations.

We present drillboards, a technique for adaptive visualization dashboards consisting of a hierarchy of coordinated charts that the user can drill down to reach a desired level of detail depending on their expertise, interest, and desired effort. This functionality allows different users to personalize the same dashboard to their specific needs and expertise. The technique is based on a formal vocabulary of chart representations and rules for merging multiple charts of different types and data into single composite representations. The drillboard hierarchy is created by iteratively applying these rules starting from a baseline dashboard, with each consecutive operation yielding a new dashboard with fewer charts and progressively more abstract and simplified views. We also present an authoring tool for building drillboards and show how it can be applied to an agricultural dataset with hundreds of expert users. Our evaluation asked three domain experts to author drillboards for their own datasets, which we then showed to casual end-users with favorable outcomes.

The advent of low-cost, accessible, and high-performance augmented reality (AR) has shed light on a situated form of analytics where in-situ visualizations embedded in the real world can facilitate sensemaking based on the user's physical location. In this work, we identify prior literature in this emerging field with a focus on situated analytics. After collecting 47 relevant situated analytics systems, we classify them using a taxonomy of three dimensions: situating triggers, view situatedness, and data depiction. We then identify four archetypical patterns in our classification using an ensemble cluster analysis. We also assess the level which these systems support the sensemaking process. Finally, we discuss insights and design guidelines that we learned from our analysis.

Designing a visualization is often a process of iterative refinement where the designer improves a chart over time by adding features, improving encodings, and fixing mistakes. However, effective design requires external critique and evaluation. Unfortunately, such critique is not always available on short notice and evaluation can be costly. To address this need, we present Perceptual Pat, an extensible suite of AI and computer vision techniques that forms a virtual human visual system for supporting iterative visualization design. The system analyzes snapshots of a visualization using an extensible set of filters—including gaze maps, text recognition, color analysis, etc—and generates a report summarizing the findings. The web-based Pat Design Lab provides a version tracking system that enables the designer to track improvements over time. We validate Perceptual Pat using a longitudinal qualitative study involving 4 professional visualization designers that used the tool over a few days to design a new visualization.

Abstract As visualization makes the leap to mobile and situated settings, where data is increasingly integrated with the physical world using mixed reality, there is a corresponding need for effectively managing the immersed user's view of situated visualizations. In this paper we present an analysis of view management techniques for situated 3D visualizations in handheld augmented reality: a shadowbox, a world‐in‐miniature metaphor, and an interactive tour. We validate these view management solutions through a concrete implementation of all techniques within a situated visualization framework built using a web‐based augmented reality visualization toolkit, and present results from a user study in augmented reality accessed using handheld mobile devices.

Visual perception is a key component of data visualization. Much prior empirical work uses eye movement as a proxy to understand human visual perception. Diverse apparatus and techniques have been proposed to collect eye movements, but there is still no optimal approach. In this paper, we review 30 prior works for collecting eye movements based on three axes: (1) the tracker technology used to measure eye movements; (2) the image stimulus shown to participants; and (3) the collection methodology used to gather the data. Based on this taxonomy, we employ a webcam-based eyetracking approach using task-specific visualizations as the stimulus. The low technology requirement means that virtually anyone can participate, thus enabling us to collect data at large scale using crowdsourcing: approximately 12,000 samples in total. Choosing visualization images as stimulus means that the eye movements will be specific to perceptual tasks associated with visualization. We use these data to propose a SCANNER DEEPLY, a virtual eyetracker model that, given an image of a visualization, generates a gaze heatmap for that image. We employ a computationally efficient, yet powerful convolutional neural network for our model. We compare the results of our work with results from the DVS model and a neural network trained on the Salicon dataset. The analysis of our gaze patterns enables us to understand how users grasp the structure of visualized data. We also make our stimulus dataset of visualization images available as part of this paper's contribution.