Series
Doctor of Philosophy with a Major in Computer Science

Permanent Link
https://hdl.handle.net/1853/72276
Series Type
Degree Series
Description
Associated Organization(s)
Associated Organization(s)

Filters

2004 - 2009 25
25
25
25
Reset filters

Settings
End date: 2009 × Start date: 2000 × Type: Text ×

Publication Search Results

Now showing 1 - 10 of 25
  • Thumbnail Image
    Item
    Storytelling for digital photographs: supporting the practice, understanding the benefit
    (Georgia Institute of Technology, 2009-08-25) Landry, Brian Michael
    The emergence of digital capture and editing technologies make providing a more detailed and coherent description of the experiences depicted in photos possible. Through the combination of photos, music and voice, people can compose digital stories of their life experiences. However, communicating an experience using photos to people who do not share the experience, and are not co-located is a difficult endeavor, even with effective digital editing tools. In this dissertation, I studied the online photo communication challenges that have arisen as a result of the transition from film to digital photography. I detail my studies of consumer desires and barriers related to online photo communication. Also, I present the design and user evaluation of the Storytellr system, which addresses those desires and barriers. The Storytellr system integrates storytelling activities with traditional photo activities to reduce the challenges of online photo communication. Through this work I contribute to the understanding of the challenges encountered by consumers who desire to engage in sharing life stories through photos over distance. I also contribute a method - integrating storytelling activities into photo activities - for enabling people to overcome those challenges using a process they find satisfying, and that produces an outcome that satisfies authors and viewers alike.
  • Thumbnail Image
    Item
    Collaborative annotation, analysis, and presentation interfaces for digital video
    (Georgia Institute of Technology, 2009-07-06) Diakopoulos, Nicholas A.
    Information quality corresponds to the degree of excellence in communicating knowledge or intelligence and encompasses aspects of validity, accuracy, reliability, bias, transparency, and comprehensiveness among others. Professional news, public relations, and user generated content alike all have their own subtly different information quality concerns. With so much recent growth in online video, it is also apparent that more and more consumers will be getting their information from online videos and that understanding the information quality of video becomes paramount for a consumer wanting to make decisions based on it. This dissertation explores the design and evaluation of collaborative video annotation and presentation interfaces as motivated by the desire for better information quality in online video. We designed, built, and evaluated three systems: (1) Audio Puzzler, a puzzle game which as a by-product of play produces highly accurate time-stamped transcripts of video, (2) Videolyzer, a video annotation system designed to aid bloggers and journalists collect, aggregate, and share analyses of information quality of video, and (3) Videolyzer CE, a simplified video annotation presentation which syndicates the knowledge collected using Videolyzer to a wider range of users in order to modulate their perceptions of video information. We contribute to knowledge of different interface methods for collaborative video annotation and to mechanisms for enhancing accuracy of objective metadata such as transcripts as well as subjective notions of information quality of the video itself.
  • Thumbnail Image
    Item
    Supporting human interpretation and analysis of activity captured through overhead video
    (Georgia Institute of Technology, 2009-07-06) Romero, Mario
    Many disciplines spend considerable resources studying behavior. Tools range from pen-and-paper observation to biometric sensing. A tool's appropriateness depends on the goal and justification of the study, the observable context and feature set of target behaviors, the observers' resources, and the subjects' tolerance to intrusiveness. We present two systems: Viz-A-Vis and Tableau Machine. Viz-A-Vis is an analytical tool appropriate for onsite, continuous, wide-coverage and long-term capture, and for objective, contextual, and detailed analysis of the physical actions of subjects who consent to overhead video observation. Tableau Machine is a creative artifact for the home. It is a long-lasting, continuous, interactive, and abstract Art installation that captures overhead video and visualizes activity to open opportunities for creative interpretation. We focus on overhead video observation because it affords a near one-to-one correspondence between pixels and floor plan locations, naturally framing the activity in its spatial context. Viz-A-Vis is an information visualization interface that renders and manipulates computer vision abstractions. It visualizes the hidden structure of behavior in its spatiotemporal context. We demonstrate the practicality of this approach through two user studies. In the first user study, we show an important search performance boost when compared against standard video playback and against the video cube. Furthermore, we determine a unanimous user choice for overviewing and searching with Viz-A-Vis. In the second study, a domain expert evaluation, we validate a number of real discoveries of insightful environmental behavior patterns by a group of senior architects using Viz-A-Vis. Furthermore, we determine clear influences of Viz-A-Vis over the resulting architectural designs in the study. Tableau Machine is a sensing, interpreting, and painting artificial intelligence. It is an Art installation with a model of perception and personality that continuously and enduringly engages its co-occupants in the home, creating an aura of presence. It perceives the environment through overhead cameras, interprets its perceptions with computational models of behavior, maps its interpretations to generative abstract visual compositions, and renders its compositions through paintings. We validate the goal of opening a space for creative interpretation through a study that included three long-term deployments in real family homes.
  • Thumbnail Image
    Item
    Understanding the social navigation user experience
    (Georgia Institute of Technology, 2009-07-06) Goecks, Jeremy
    A social navigation system collects data from its users--its community--about what they are doing, their opinions, and their decisions, aggregates this data, and provides the aggregated data--community data--back to individuals so that they can use it to guide behavior and decisions. In this thesis, I document my investigation of the user experience for social navigation systems that employ activity data. I make three contributions in this thesis. First, I synthesize social navigation systems research with research in social influence, advice-taking, and informational cascades to construct hypotheses about the social navigation user experience. These hypotheses posit that community data from a social navigation system exerts informational influence on users, that users egocentrically discount community data, that herding in social navigation systems can be characterized as informational cascades, and that the size and unanimity of the community data correspond to the strength of the community data's influence. The second contribution of this thesis is an experiment that evaluates the hypotheses about the social navigation user experience; this experiment investigated how a social navigation system can support online charitable giving decisions. The experiment's results support the majority of the hypotheses about the social navigation user experience and provide mixed evidence for the other hypotheses. The implications that arise from the experiment's findings compromise the final contribution of this thesis. These implications concern improving the design of social navigation systems and developing a general framework for evaluating the social influence of social navigation systems.
  • Thumbnail Image
    Item
    Visual search interfaces for online digital repositories
    (Georgia Institute of Technology, 2009-06-29) Clarkson, Edward Cantey
    This work presents our research into visualization for digital repository search interfaces, motivated by the prevalence of existing hierarchical data structures and the general lack of contextualization present in existing systems. We develop the ResultMap concept, a treemap-based visualization that we have applied to keyword search engine and faceted classification data environments, and present the results of their empirical evaluation, which show limited objective and subjective benefits for some users and no detrimental effects in any cases. We organize this work as follows: Chapter 1 provides an introduction to our problem area, motivates our general approach of leveraging hierarchical structure (via ResultMaps) for context, and proposes a thesis statement and corresponding research questions. Chapter 2 discusses related work, and includes a survey and design characterization of faceted navigation tools. Chapter 3 defines the key visual and interactive features of the ResultMap concept and justifies their basic design. Chapter 4 presents our implementation and evaluation of ResultMaps applied to digital library search engine result pages (SERPs). Chapter 5 consists of two major portions: a presentation of formal data and query models for faceted environments, and our implementation and evaluation of ResultMaps in a faceted UI context. In Chapter 6 we conclude--based on our results from Chapter 4 and Chapter 5--with a set of principles for designing both visual search interfaces themselves and designing their evaluation. We finish with suggestions for future research in this area.
  • Thumbnail Image
    Item
    Exploring and visualizing the impact of multiple shared displays on collocated meeting practices
    (Georgia Institute of Technology, 2009-05-18) Plaue, Christopher M.
    A tremendous amount of information is produced in the world around us, both as a product of our daily lives and as artifacts of our everyday work. An emerging area of Human-Computer Interaction (HCI) focuses on helping individuals manage this flood of information. Prior research shows that multiple displays can improve an individual user's ability to deal with large amounts of information, but it is unclear whether these advantages extend for teams of people. This is particularly relevant as more employees are spending large portions of their workdays in meetings My contribution to HCI research is empirical fieldwork and laboratory studies investigating how multiple shared displays improve aspects of teamwork. In particular, I present an insight-based evaluation method for analyzing how teams collaborate on a data-intensive sensemaking task. Using this method, I show how the presence and location of multiple shared displays impacted the meeting process with respect to performance, collaboration, and satisfaction. I also illustrate how multiple shared displays engaged team members who might not have otherwise contributed to the collaboration process. Finally, I present Mimosa, a software tool developed to visualize large volumes of time series data. Mimosa combines aspects of information visualization with data analysis, facilitating a deep and iterative exploration of relationships within large datasets.
  • Thumbnail Image
    Item
    Multi-tree Monte Carlo methods for fast, scalable machine learning
    (Georgia Institute of Technology, 2009-01-09) Holmes, Michael P.
    As modern applications of machine learning and data mining are forced to deal with ever more massive quantities of data, practitioners quickly run into difficulty with the scalability of even the most basic and fundamental methods. We propose to provide scalability through a marriage between classical, empirical-style Monte Carlo approximation and deterministic multi-tree techniques. This union entails a critical compromise: losing determinism in order to gain speed. In the face of large-scale data, such a compromise is arguably often not only the right but the only choice. We refer to this new approximation methodology as Multi-Tree Monte Carlo. In particular, we have developed the following fast approximation methods: 1. Fast training for kernel conditional density estimation, showing speedups as high as 10⁵ on up to 1 million points. 2. Fast training for general kernel estimators (kernel density estimation, kernel regression, etc.), showing speedups as high as 10⁶ on tens of millions of points. 3. Fast singular value decomposition, showing speedups as high as 10⁵ on matrices containing billions of entries. The level of acceleration we have shown represents improvement over the prior state of the art by several orders of magnitude. Such improvement entails a qualitative shift, a commoditization, that opens doors to new applications and methods that were previously invisible, outside the realm of practicality. Further, we show how these particular approximation methods can be unified in a Multi-Tree Monte Carlo meta-algorithm which lends itself as scaffolding to the further development of new fast approximation methods. Thus, our contribution includes not just the particular algorithms we have derived but also the Multi-Tree Monte Carlo methodological framework, which we hope will lead to many more fast algorithms that can provide the kind of scalability we have shown here to other important methods from machine learning and related fields.
  • Thumbnail Image
    Item
    Infrastructure mediated sensing
    (Georgia Institute of Technology, 2008-07-08) Patel, Shwetak Naran
    Ubiquitous computing application developers have limited options for a practical activity and location sensing technology that is easy-to-deploy and cost-effective. In this dissertation, I have developed a class of activity monitoring systems called infrastructure mediated sensing (IMS), which provides a whole-house solution for sensing activity and the location of people and objects. Infrastructure mediated sensing leverages existing home infrastructure (e.g, electrical systems, air conditioning systems, etc.) to mediate the transduction of events. In these systems, infrastructure activity is used as a proxy for a human activity involving the infrastructure. A primary goal of this type of system is to reduce economic, aesthetic, installation, and maintenance barriers to adoption by reducing the cost and complexity of deploying and maintaining the activity sensing hardware. I discuss the design, development, and applications of various IMS-based activity and location sensing technologies that leverage the following existing infrastructures: wireless Bluetooth signals, power lines, and central heating, ventilation, and air conditioning (HVAC) systems. In addition, I show how these technologies facilitate automatic and unobtrusive sensing and data collection for researchers or application developers interested in conducting large-scale in-situ location-based studies in the home.
  • Thumbnail Image
    Item
    Using observations to recognize the behavior of interacting multi-agent systems
    (Georgia Institute of Technology, 2008-05-19) Feldman, Adam Michael
    Behavioral research involves the study of the behaviors of one or more agents (often animals) in order to better understand the agents' thoughts and actions. Identifying subject movements and behaviors based upon those movements is a critical, time-consuming step in behavioral research. To successfully perform behavior analysis, three goals must be met. First, the agents of interest are observed, and their movements recorded. Second, each individual must be uniquely identified. Finally, behaviors must be identified and recognized. I explore a system that can uniquely identify and track agents, then use these tracks to automatically build behavioral models and recognize similar behaviors in the future. I address the tracking and identification problems using a combination of laser range finders, active RFID sensors, and probabilistic models for real-time tracking. The laser range component adds environmental flexibility over vision based systems, while the RFID tags help disambiguate individual agents. The probabilistic models are important to target identification during the complex interactions with other agents of similar appearance. In addition to tracking, I present work on automatic methods for generating behavioral models based on supervised learning techniques using the agents' tracked data. These models can be used to classify new tracked data and identify the behavior exhibited by the agent, which can then be used to help automate behavior analysis.
  • Thumbnail Image
    Item
    Exploring user interface challenges in supporting activity-based knowledge work practices
    (Georgia Institute of Technology, 2008-05-19) Voida, Stephen
    The venerable desktop metaphor is beginning to show signs of strain in supporting modern knowledge work. Traditional desktop systems were not designed to support the sheer number of simultaneous windows, information resources, and collaborative contexts that have become commonplace in contemporary knowledge work. Even though the desktop has been slow to evolve, knowledge workers still consistently manage multiple tasks, collaborate effectively among colleagues or clients, and manipulate information most relevant to their current task by leveraging the spatial organization of their work area. The potential exists for desktop workspaces to better support these knowledge work practices by leveraging the unifying construct of activity. Semantically-meaningful activities, conceptualized as a collection of tools (applications, documents, and other resources) within a social and organizational context, offer an alternative orientation for the desktop experience that more closely corresponds to knowledge workers' objectives and goals. In this research, I unpack some of the foundational assumptions of desktop interface design and propose an activity-centered model for organizing the desktop interface based on empirical observations of real-world knowledge work practice, theoretical understandings of cognition and activity, and my own experiences in developing two prototype systems for extending the desktop to support knowledge work. I formalize this analysis in a series of key challenges for the research and development of activity-based systems. In response to these challenges, I present the design and implementation of a third research prototype, the Giornata system, that emphasizes activity as a primary organizing principle in GUI-based interaction, information organization, and collaboration. I conclude with two evaluations of the system. First, I present findings from a longitudinal deployment of the system among a small group of representative knowledge workers; this deployment constitutes one of the first studies of how activity-based systems are adopted and appropriated in a real-world context. Second, I provide an assessment of the technologies that enable and those that pose barriers to the development of activity-based computing systems.