the field toward real-time use of gaze as active or passive modality. When active, gaze can imbue interaction within the user’s egocentric peripersonal space, e.g., for selection. When passive, gaze serves as context for other interaction modalities, e.g., as cues. In both cases, system response needs to be immediate, i.e., real-time. In such scenarios, the system needs information not only from traditional gaze-related metrics such as “what is being fixated” but also from real-time dynamics of gaze just after the given fixation. Although recent advances in real-time metrics have appeared, thus far they have only been evaluated on data that was previously captured, i.e., re-streamed. What are needed are protocols designed to evaluate real-time metrics to validate their efficacy. In this position paper, we review two real-time metrics and suggest potential for future directions of their evaluation.

Traditional eye movement research has in large part been dependent on static, post-experimental analysis of aggregate first-order metrics (e.g., fixations, fixation durations, etc.). Advances in eye-tracking methodology call for dynamical evaluation of second-order metrics (e.g., \(\mathcal {K}\) or gaze entropy) from the time course of collected gaze and eventually in real time. We consider such analysis of these gaze-based indicators for their response during visual search performed by two distinct user groups: Healthy Controls (HC) or those with (Mild) Cognitive Impairment (CI). Analysis of the time course of gaze transition entropy and \(\mathcal {K}\) with Generalized Additive Models (GAMs) shows differing visual scanning strategies on two types of stimuli. On a jumbled image, the HC group adopted a more focal and less predictable strategy compared to the CI group. The effect was reversed on an image of a classical painting.

Effective error analysis is critical for the successful development and deployment of CVML models. One approach to understanding model errors is to summarize the common characteristics of error samples. This can be particularly challenging in tasks that utilize unstructured, complex data such as images, where patterns are not always obvious. Another method is to analyze error distributions across pre-defined categories, which requires analysts to hypothesize about potential error causes in advance. Forming such hypotheses without access to explicit labels or annotations makes it difficult to isolate meaningful subgroups or patterns, however, as analysts must rely on manual inspection, prior expertise, or intuition. This lack of structured guidance can hinder a comprehensive understanding of where models fail. To address these challenges, we introduce VibE, a semantic error analysis workflow designed to identify where and why computer vision and machine learning (CVML) models fail at the subgroup level, even when labels or annotations are unavailable. VibE incorporates several core features to enhance error analysis: semantic subgroup generation, semantic summarization, candidate issue proposals, semantic concept search, and interactive subgroup analysis. By leveraging large foundation models (such as CLIP and GPT-4) alongside visual analytics, VibE enables developers to semantically interpret and analyze CVML model errors. This interactive workflow helps identify errors through subgroup discovery, supports hypothesis generation with auto-generated subgroup summaries and suggested issues, and allows hypothesis validation through semantic concept search and comparative analysis. Through three diverse CVML tasks and in-depth expert interviews, we demonstrate how VibE can assist error understanding and analysis.

Abstract As advancements in robotics, autonomous driving, and spatial computing continue to unfold, a growing number of Computer Vision and Machine Learning (CVML) algorithms are incorporating three‐dimensional data into their frameworks. Debugging these 3D CVML models often requires going beyond traditional performance evaluation methods, necessitating a deeper understanding of an algorithm's behavior within its spatio‐temporal context. However, the lack of appropriate visualization tools presents a significant obstacle to effectively exploring 3D data and spatial features in relation to key performance indicators (KPIs). To address this challenge, we explore the application of Immersive Analytics (IA) methodologies to enhance the debugging process of 3D CVML models. Through in‐depth interviews with eight CVML engineers, we identify common tasks and challenges faced during the development of spatial algorithms, and establish a set of design principles for creating tools tailored to spatial model evaluation. Building on these insights, we propose a novel immersive analytics system for debugging an indoor localization algorithm. The system is built using web technologies and integrates WebXR to enable fluid transitions across the reality‐virtuality continuum. We conduct a qualitative study with six CVML engineers using our system on Apple Vision Pro, observing their analytical workflow as they debug an indoor localization sequence. We discuss the advantages of employing immersive analytics in the model evaluation workflow, emphasizing the role of seamlessly integrating 2D and 3D visualizations across varying levels of immersion to facilitate more effective model assessment. Finally, we reflect on the implementation trade‐offs and discuss the generalizability of our findings for future efforts in immersive 3D CVML model debugging.

Abstract While the interpretation of high‐dimensional datasets has become a necessity in most industries, the spatial visualization of higher‐dimensional geometry has mostly remained a niche research topic for mathematicians and physicists. Intermittent contributions to this field date back more than a century, and have had a non‐negligible influence on contemporary art and philosophy. However, most contributions have focused on the understanding of specific mathematical shapes, with few concrete applications. In this work, we attempt to revive the community's interest in visualizing higher dimensional geometry by shifting the focus from the visualization of abstract shapes to the design of a broader hyper‐universe concept, wherein 3D and 4D objects can coexist and interact with each other. Specifically, we discuss the content definition, authoring patterns, and technical implementations associated with the process of extending standard 3D applications as to support 4D mechanics. We operationalize our ideas through the introduction of a new hybrid 3D/4D videogame called Across Dimensions, which we developed in Unity3D through the integration of our own 4D plugin.

Immersive environments have gradually become standard for visualizing and analyzing large or complex datasets that would otherwise be cumbersome, if not impossible, to explore through smaller scale computing devices. However, this type of workspace often proves to possess limitations in terms of interaction, flexibility, cost and scalability. In this paper we introduce a novel immersive environment called Dataspace, which features a new combination of heterogeneous technologies and methods of interaction towards creating a better team workspace. Dataspace provides 15 high-resolution displays that can be dynamically reconfigured in space through robotic arms, a central table where information can be projected, and a unique integration with augmented reality (AR) and virtual reality (VR) headsets and other mobile devices. In particular, we contribute novel interaction methodologies to couple the physical environment with AR and VR technologies, enabling visualization of complex types of data and mitigating the scalability issues of existing immersive environments. We demonstrate through four use cases how this environment can be effectively used across different domains and reconfigured based on user requirements. Finally, we compare Dataspace with existing technologies, summarizing the trade-offs that should be considered when attempting to build better collaborative workspaces for the future.

Despite advances in augmented reality (AR), the process of creating meaningful experiences with this technology is still extremely challenging. Due to different tracking implementations and hardware constraints, developing AR applications either requires low-level programming skills, or is done through specific authoring tools that largely sacrifice the possibility of customizing the AR experience. Existing development workflows also do not support previewing or simulating the AR experience, requiring a lengthy process of trial and error by which content creators deploy and physically test applications in each iteration. To mitigate these limitations, we propose CAVE-AR, a novel virtual reality system for authoring, simulating and debugging custom augmented reality experiences. Available both as a standalone or a plug-in tool, CAVE-AR is based on the concept of representing in the same global reference system both in AR content and tracking information, mixing geographical information, architectural features, and sensor data to simulate the context of an AR experience. Thanks to its novel abstraction of existing tracking technologies, CAVE-AR operates independently of users' devices, and integrates with existing programming tools to provide maximum flexibility. Our VR application provides designers with ways to create and modify an AR application, even while others are in the midst of using it. CAVE-AR further allows the designer to track how users are behaving, preview what they are currently seeing, and interact with them through several different channels. To illustrate our proposed development workflow and demonstrate the advantages of our authoring system, we introduce two CAVE-AR use cases in which an augmented reality application is created and tested. In particular, we compare the CAVE-AR workflow to traditional development methods and demonstrate the importance of simulation and live application debugging.

In the past few years, augmented reality (AR) and virtual reality (VR) technologies have experienced terrific improvements in both accessibility and hardware capabilities, encouraging the application of these devices across various domains. While researchers have demonstrated the possible advantages of AR and VR for certain data science tasks, it is still unclear how these technologies would perform in the context of exploratory data analysis (EDA) at large. In particular, we believe it is important to better understand which level of immersion EDA would concretely benefit from, and to quantify the contribution of AR and VR with respect to standard analysis workflows.

Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data. However, reasoning dynamically about the results of a dimensionality reduction is difficult. Dimensionality-reduction algorithms use complex optimizations to reduce the number of dimensions of a dataset, but these new dimensions often lack a clear relation to the initial data dimensions, thus making them difficult to interpret. Here we propose a visual interaction framework to improve dimensionality-reduction based exploratory data analysis. We introduce two interaction techniques, forward projection and backward projection, for dynamically reasoning about dimensionally reduced data. We also contribute two visualization techniques, prolines and feasibility maps, to facilitate the effective use of the proposed interactions. We apply our framework to PCA and autoencoder-based dimensionality reductions. Through data-exploration examples, we demonstrate how our visual interactions can improve the use of dimensionality reduction in exploratory data analysis.

Abstract With the rapid commoditization of wearable sensors, detecting human movements from sensor datasets has become increasingly common over a wide range of applications. To detect activities, data scientists iteratively experiment with different classifiers before deciding which model to deploy. Effective reasoning about and comparison of alternative classifiers are crucial in successful model development. This is, however, inherently difficult in developing classifiers for sensor data, where the intricacy of long temporal sequences, high prediction frequency, and imprecise labeling make standard evaluation methods relatively ineffective and even misleading. We introduce Track Xplorer, an interactive visualization system to query, analyze, and compare the predictions of sensor‐data classifiers. Track Xplorer enables users to interactively explore and compare the results of different classifiers, and assess their accuracy with respect to the ground‐truth labels and video. Through integration with a version control system, Track Xplorer supports tracking of models and their parameters without additional workload on model developers. Track Xplorer also contributes an extensible algebra over track representations to filter, compose, and compare classification outputs, enabling users to reason effectively about classifier performance. We apply Track Xplorer in a collaborative project to develop classifiers to detect movements from multisensor data gathered from Parkinson's disease patients. We demonstrate how Track Xplorer helps identify early on possible systemic data errors, effectively track and compare the results of different classifiers, and reason about and pinpoint the causes of misclassifications.

The wide spread adoption of IoT technologies has resulted in generation of huge amount of data, or Big Data, which has to be collected, stored and processed through new techniques to produce value in the best possible way.Distributed computing frameworks such as Hadoop, based on the MapReduce paradigm, have been used to process such amounts of data by exploiting the computing power of many cluster nodes.Unfortunately, in many real big data applications the data to be processed reside in various computationally heterogeneous data centers distributed in different locations.In this context the Hadoop performance collapses dramatically.To face this issue, we developed a Hierarchical Hadoop Framework (H2F) capable of scheduling and distributing tasks among geographically distant clusters in a way that minimizes the overall jobs execution time.In this work the focus is put on the definition of a job scheduling system based on a one-point iterative search algorithm that increases the framework scalability while guaranteeing good job performance.

Effective big data analysis is one of the most notable research challenge of the latest few years. Hadoop, the most popular implementation of the MapReduce framework, has today become widespread used for processing large data sets using cloud resources. However, in many scenarios, data are geographically distributed over data centers and moving them to a single site for processing may result extremely expensive when not feasible at all. A key challenge for running applications in such a geographically distributed environment is how to efficiently schedule the computation over the different datacenters. In this work we present a job scheduler for a Hierarchical Hadoop Framework (H2F) that allows the management of multiple requests of job execution ensuring an efficient use of the available resources. Our experimental evaluations show that using H2F significantly improves processing time for geodistributed data sets with respect to a plain Hadoop system.

Big data analysis requires adequate infrastructure and programming paradigms capable of processing large amount of data. Hadoop, the most known open-source implementation of the MapReduce paradigm, is widely employed in big data analysis frameworks. However, in many recent application scenarios data are natively distributed over different geographic regions in data centers which are inter-connected through network links with very lower bandwidth than those of the computing environments where traditionally Hadoop deployments are supposed to work. In such a context, Hadoop applications perform very poorly. To cope with these issues, we developed a Hierarchical Hadoop Framework (H2F) specifically designed to work on geodistributed data. In this work, we compare the performance of H2F with that of a plain Hadoop implementation. First results show that for very large amount of data the H2F solution performs better than the Hadoop.

TEST 02 - Elsevier's Scopus, the largest abstract and citation database of peer-reviewed literature. Search and access research from the science, technology, medicine, social sciences and arts and humanities fields.

In the past two decades there has been a growing interest over the definition of new distributed computational paradigms capable to serve the need of manipulating and analyzing huge amounts of data. Among the others, the MapReduce outstands for popularity. Its open-source implementation Hadoop is widely used in academic environments and is also greatly supported by huge IT players. There are many application scenarios where the data to be manipulated resides on data centers which are heterogeneous in term of computing capacity and are geographically distant from each other's. Unfortunately, in this contexts Hadoop performs very poorly. In this paper we propose to leverage on a hierarchical computing framework to boost the Hadoop performance in geo-distributed computing environments. The framework we propose drains fresh information from the distributed computing context and exploits it to carry out a smart job scheduling strategy. In this work, the focus is put on the study and definition of the application profile of the jobs. We implemented a software prototype of the proposed hierarchical Hadoop framework. Tests run on the prototype proved the capability of the job scheduling system to compute the job's execution path and estimate its completion time.

The fourth industrial revolution related to the Internet of Things (IoT) is leading to the emergence of future smart cities and cyber-physical systems with a rapidly increasing of smart connected objects (such as personal devices, sensors, actuators). Therefore, companies such as Telcos, Cloud and Service Providers have to analyze a huge amount of data that probably lead to the reduction of available bandwidth and subsequent increase of network latency. In this context, Fog Computing and Mobile Edge Computing (MEC) can be suitable paradigms to solve this kind of problems. The exploitation of the heterogeneous environment allows a better performance for mission-critical and time-critical applications. In this paper we present a scenario that exploits the MECs in order to detect abnormal or critical events such as terrorist threats, natural and man-made disasters. The proposed solution allows cooperation among the Base Transceiver Stations (BTS) to rapidly notify the users which are close to the critical area.

TEST 02 - Elsevier's Scopus, the largest abstract and citation database of peer-reviewed literature. Search and access research from the science, technology, medicine, social sciences and arts and humanities fields.