Interactive machine learning (ML) systems are difficult to design because of the “Two Black Boxes” problem that exists at the interface between human and machine. Many algorithms that are used in interactive ML systems are black boxes that are presented to users, while the human cognition represents a second black box that can be difficult for the algorithm to interpret. These black boxes create cognitive gaps between the user and the interactive ML model. In this paper, we identify several cognitive gaps that exist in a previously-developed interactive visual analytics (VA) system, Andromeda, but are also representative of common problems in other VA systems. Our goal with this work is to open both black boxes and bridge these cognitive gaps by making usability improvements to the original Andromeda system. These include designing new visual features to help people better understand how Andromeda processes and interacts with data, as well as improving the underlying algorithm so that the system can better implement the intent of the user during the data exploration process. We evaluate our designs through both qualitative and quantitative analysis, and the results confirm that the improved Andromeda system outperforms the original version in a series of high-dimensional data analysis tasks.

Abstract In the study of complex physical systems, scientists use simulations to study the effects of different models and parameters. Seeking to understand the influence and relationships among multiple dimensions, they typically run many simulations and vary the initial conditions in what are known as ‘ensembles’. Ensembles are then a number of runs that are each multi‐dimensional and multi‐variate. In order to understand the connections between simulation parameters and patterns in the output data, we have been developing an approach to the visual analysis of scientific data that merges human expertise and intuition with machine learning and statistics. Our approach is manifested in a new visualization tool, GLEE (Graphically‐Linked Ensemble Explorer), that allows scientists to explore, search, filter and make sense of their ensembles. GLEE uses visualization and semantic interaction (SI) techniques to enable scientists to find similarities and differences between runs, find correlation(s) between different parameters and explore relations and correlations across and between different runs and parameters. Our approach supports scientists in selecting interesting subsets of runs in order to investigate and summarize the factors and statistics that show variations and consistencies across different runs. In this paper, we evaluate our tool with experts to understand its strengths and weaknesses for optimization and inverse problems.

Immersive environments have been successfully applied to a broad range of safety training in high-risk domains. However, very little research has used these systems to evaluate the risk-taking behavior of construction workers. In this study, we investigated the feasibility and usefulness of providing passive haptics in a mixed-reality environment to capture the risk-taking behavior of workers, identify at-risk workers, and propose injury-prevention interventions to counteract excessive risk-taking and risk-compensatory behavior. Within a mixed-reality environment in a CAVE-like display system, our subjects installed shingles on a (physical) sloped roof of a (virtual) two-story residential building on a morning in a suburban area. Through this controlled, within-subject experimental design, we exposed each subject to three experimental conditions by manipulating the level of safety intervention. Workers' subjective reports, physiological signals, psychophysical responses, and reactionary behaviors were then considered as promising measures of Presence. The results showed that our mixed-reality environment was a suitable platform for triggering behavioral changes under different experimental conditions and for evaluating the risk perception and risk-taking behavior of workers in a risk-free setting. These results demonstrated the value of immersive technology to investigate natural human factors.

In this workshop, communications systems and wireless communications educators will experience and provide feedback on remote laboratory exercises and tutorials that employ an Internet-accessible, software-defined radio (SDR) based testbed. The tutorials introduce and demonstrate concepts relevant to spectrum sharing, cognitive radio, and other radio / wireless communications applications that involve spectrum agility. Students run, modify, and / or configure code for cognitive engines or adaptive controllers that make real-time modifications to radio waveform parameters such as operating frequency, transmitting power, signal bandwidth, modulation, and error correction. The controllers make adaptations to optimize over-the-air operation in challenging signal environments. The resulting radio link performance is measured using an experiment management framework and can be visualized using a web interface that displays performance metrics as well as three-dimensional and two-dimensional waterfall plots. In the process of working through the exercises, students learn to use the above tools, which also enable them to design and perform original experiments. This workshop will be valuable for anyone teaching or studying wireless communications or using interactive remote laboratories and tutorials to teach technical concepts.

The design of Virginia Tech's (VT) Study Hall emerges from the current cognitive neuroscience understanding of memory as a spatially mediated encoding process. The driving questions are: Does the sense of spatial navigation generated by an immersive virtual experience aid in memory formation? Does virtual spatial navigation, when paired with learning cues, enhance information encoding relative to nonspatial and nonvirtual processes? A pilot study was executed comparing recall on non-navigational memorization processes to processes involving mental and virtual navigation and we are currently running a full study to see if we can replicate these effects with a more demanding memory task and refined study design.

Crash warning systems are designed to help avoid vehicle accidents by notifying drivers of potential hazards. In typical crash warning systems, primary warning information is provided through visual, audible and/or haptic cues. In general, the use of crash warning systems results in safer driving. However, driver vehicle interfaces that employ visual warning elements, such as text messages appearing on the center console display and blindspot detection icons in side view mirrors, may take drivers' eyes off the road momentarily, and may lead to divided attention, distracted driving and increased crash risks. To address this, we propose an augmented reality (AR) head-up display interface for crash warning systems that displays visual cues on the drivers' view of the road, with the ultimate goal of increasing driver awareness and safety. In this paper, we describe a simulator-based comparative user study to begin understanding the effect of AR interface design features on driver performance, mental workload, and preferences. Our results support the hypothesis that head-up AR display interfaces for crash warning systems have potential safety benefits and a high likelihood of driver acceptance.

Abstract This paper describes our recent experimental evaluation of Information‐Rich Virtual Environment (IRVE) interfaces. To explore the depth cue/visibility tradeoff between annotation schemes, we design and evaluate two information layout techniques to support search and comparison tasks. The techniques provide different depth and association cues between objects and their labels: labels were displayed either in the virtual world relative to their referent (Object Space) or on an image plane workspace (Viewport Space). The Software Field of View (SFOV) was controlled to 60° or 100° of vertical angle and two groups were tested: those running on a single monitor and those on a tiled nine‐panel display. Users were timed, tracked for correctness, and gave ratings for both difficulty and satisfaction on each task. Significant advantages were found for the Viewport interface, and for high SFOV. The interactions between these variables suggest special design considerations to effectively support search and comparison performance across monitor configurations and projection distortions. Copyright © 2006 John Wiley & Sons, Ltd.

This paper describes our recent experimental evaluation of Information-Rich Virtual Environment (IRVE) interfaces. To explore the depth cue/visibility tradeoff between annotation schemes, we design and evaluate two information layout techniques to support search and comparison tasks. The techniques provide different depth and association cues between objects and their labels: labels were displayed either in the virtual world relative to their referent (Object Space) or on an image plane workspace (Viewport Space). The Software Field of View (SFOV) was controlled to 60 or 100 degrees of vertical angle and two groups were tested: those running on a single monitor and those on a tiled nine-panel display. Users were timed, tracked for correctness, and gave ratings for both difficulty and satisfaction on each task. Significant advantages were found for the Viewport interface, and for high SFOV. The interactions between these variables suggest special design considerations to effectively support search and comparison performance across monitor configurations and projection distortions.

Virtual environments (VEs) allow users to experience and interact with a rich sensory environment, but most virtual worlds contain only sensory information similar to that which we experience in the physical world. Information-rich virtual environments (IRVEs) combine the power of VEs and information visualization, augmenting VEs with additional abstract information such as text, numbers, or graphs. IRVEs can be useful in many contexts, such as education, medicine, or construction. In our work, we are developing a theoretical foundation for the study of IRVEs and tools for their development and evaluation. We present a working definition of IRVEs, a discussion of information display and interaction in IRVEs. We also describe a software framework for IRVE development and a testbed enabling evaluation of text display techniques for IRVEs. Finally, we present a research agenda for this area.