Computer Science Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/2756

Browse

Subject: search.filters.subject.Information Science

Search Results

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Understanding Scientific Literature Networks: Case Study Evaluations of Integrating Visualizations and Statistics
    (2011) Gove, Robert Paul; Shneiderman, Ben; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Investigators frequently need to quickly learn new research domains in order to advance their research. This thesis presents five contributions to understanding how software helps researchers explore scientific literature networks. (1) A taxonomy which summarizes capabilities in existing bibliography tools, revealing patterns of capabilities by system type. (2) Six participants in two user studies evaluate Action Science Explorer (ASE), which is designed to create surveys of scientific literature and integrates visualizations and statistics. Users found document-level statistics and attribute rankings to be convenient when beginning literature exploration. (3) User studies also identify users' questions when exploring academic literature, which include examining the evolution of a field, identifying author relationships, and searching for review papers. (4) The evaluations suggest shortcomings of ASE, and this thesis outlines improvements to ASE and lists user requirements for bibliographic exploration. (5) I recommend strategies for evaluating bibliographic exploration tools based on experiences evaluating ASE.
  • Thumbnail Image
    Item
    Combining Evidence from Unconstrained Spoken Term Frequency Estimation for Improved Speech Retrieval
    (2008-11-21) Olsson, James Scott; Oard, Douglas W; Applied Mathematics and Scientific Computation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation considers the problem of information retrieval in speech. Today's speech retrieval systems generally use a large vocabulary continuous speech recognition system to first hypothesize the words which were spoken. Because these systems have a predefined lexicon, words which fall outside of the lexicon can significantly reduce search quality---as measured by Mean Average Precision (MAP). This is particularly important because these Out-Of-Vocabulary (OOV) words are often rare and therefore good discriminators for topically relevant speech segments. The focus of this dissertation is on handling these out-of-vocabulary query words. The approach is to combine results from a word-based speech retrieval system with those from vocabulary-independent ranked utterance retrieval. The goal of ranked utterance retrieval is to rank speech utterances by the system's confidence that they contain a particular spoken word, which is accomplished by ranking the utterances by the estimated frequency of the word in the utterance. Several new approaches for estimating this frequency are considered, which are motivated by the disparity between reference and errorfully hypothesized phoneme sequences. The first method learns alternate pronunciations or degradations from actual recognition hypotheses and incorporates these variants into a new generative estimator for term frequency. A second method learns transformations of several easily computed features in a discriminative model for the same task. Both methods significantly improved ranked utterance retrieval in an experimental validation on new speech. The best of these ranked utterance retrieval methods is then combined with a word-based speech retrieval system. The combination approach uses a normalization learned in an additive model, which maps the retrieval status values from each system into estimated probabilities of relevance that are easily combined. Using this combination, much of the MAP lost because of OOV words is recovered. Evaluated on a collection of spontaneous, conversational speech, the system recovers 57.5\% of the MAP lost on short (title-only) queries and 41.3\% on longer (title plus description) queries.
  • Thumbnail Image
    Item
    Supporting Exploratory Web Search With Meaningful and Stable Categorized Overviews
    (2006-04-28) Kules, Bill; Shneiderman, Ben; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation investigates the use of categorized overviews of web search results, based on meaningful and stable categories, to support exploratory search. When searching in digital libraries and on the Web, users are challenged by the lack of effective overviews. Adding categorized overviews to search results can provide substantial benefits when searchers need to explore, understand, and assess their results. When information needs are evolving or imprecise, categorized overviews can stimulate relevant ideas, provoke illuminating questions, and guide searchers to useful information they might not otherwise find. When searchers need to gather information from multiple perspectives or sources, categorized overviews can make those aspects visible for interactive filtering and exploration. However, they add visual complexity to the interface and increase the number of tactical decisions to be made while examining search results. Two formative studies (N=18 and N=12) investigated how searchers use categorized overviews in the domain of U.S. government web search. A third study (N=24) evaluated categorized overviews of general web search results based on thematic, geographic, and government categories. Participants conducted four exploratory searches during a two hour session to generate ideas for newspaper articles about specified topics. Results confirmed positive findings from the formative studies, showing that subjects explored deeper while feeling more organized and satisfied, but did not find objective differences in the outcomes of the search task. Results indicated that searchers use categorized overviews based on thematic, geographic, and organizational categories to guide the next steps in their searches. This dissertation identifies lightweight search actions and tactics made possible by adding a categorized overview to a list of web search results. It describes a design space for categorized overviews of search results, and presents a novel application of the brushing and linking technique to enrich search result interfaces with lightweight interactions. It proposes a set of principles, refined by the studies, for the design of exploratory search interfaces, including "Organize overviews around meaningful categories," "Clarify and visualize category structure," and "Tightly couple category labels to search result list." These contributions will be useful to web search researchers and designers, information architects and web developers.
  • Thumbnail Image
    Item
    Interactive Sonification of Abstract Data - Framework, Design Space, Evaluation, and User Tool
    (2006-04-24) Zhao, Haixia; Shneiderman, Ben; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    For people with visual impairments, sound is an important information channel. The traditional accommodation for visually impaired users to access data is to rely on screen readers to speak the data in tabular forms. While speech can accurately describe information, such data presentation tends to be long and hard to realize complex information. This is particularly true in exploratory data analysis in which users often need to examine the data from different aspects. Sonification, the use of non-speech sound, has shown to help data comprehension. Previous data sonifications focus on data to sound attribute mapping and typically lack support for task-oriented data interaction. This dissertation makes four contributions. (1) An Action-by-Design-Component (ADC) framework guides auditory interface designs for exploratory data analysis. The framework characterizes data interaction in the auditory mode as a set of Auditory Information Seeking Actions (AISA). It also discusses design considerations for a set of Design Components to support AISAs, contrasted with actions in visualizations. (2) Applying the framework to geo-referenced statistical data, I explore its design space. Through user evaluations, effective design options were identified and insights were obtained regarding human ability to perceive complex information, especially those with spatial structures, from interactive sounds. (3) A tool, iSonic, was developed, with synchronized visual and auditory displays. Forty-two hours of case studies with seven blind users show that iSonic enables them to effectively explore data in highly coordinated map and table views without special devices, to find facts and discover data trends even in unfamiliar geographical contexts. Preliminary algorithms are also described to automatically generate geographical region spatial sweep orders for arbitrary maps. (4) The application to geo-referenced data demonstrated that the ADC framework provided a rich set of task-oriented actions (AISAs) that were effective for blind users to accomplish complex tasks with multiple highly coordinated data views. It also showed that some widely used techniques in visualization can adapt to the auditory mode. By applying the framework to scatterplots and line graphs, I show that the framework could be generalized and lead to the design of a unified auditory workspace for general exploratory data analysis.
  • Thumbnail Image
    Item
    Algorithms and evaluation for object detection and tracking in computer vision
    (2005-08-01) Kim, Kyungnam; Davis, Larry; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Vision-based object detection and tracking, especially for video surveillance applications, is studied from algorithms to performance evaluation. This dissertation is composed of four topics: (1) Background Modeling and Detection, (2) Performance Evaluation of Sensitive Target Detection, (3) Multi-view Multi-target Multi-Hypothesis Segmentation and Tracking of People, and (4) A Fine-Structure Image/Video Quality Measure. First, we present a real-time algorithm for foreground-background segmentation. It allows us to capture structural background variation due to periodic-like motion over a long period of time under limited memory. Our codebook-based representation is efficient in memory and speed compared with other background modeling techniques. Our method can handle scenes containing moving backgrounds or illumination variations, and it achieves robust detection for different types of videos. In addition to the basic algorithm, three features improving the algorithm are presented - Automatic Parameter Estimation, Layered Modeling/Detection and Adaptive Codebook Updating. Second, we introduce a performance evaluation methodology called Perturbation Detection Rate (PDR) analysis for measuring performance of foreground-background segmentation. It does not require foreground targets or knowledge of foreground distributions. It measures the sensitivity of a background subtraction algorithm in detecting possible low contrast targets against the background as a function of contrast. We compare four background subtraction algorithms using the methodology. Third, a multi-view multi-hypothesis approach to segmenting and tracking multiple persons on a ground plane is proposed. The tracking state space is the set of ground points of the people being tracked. During tracking, several iterations of segmentation are performed using information from human appearance models and ground plane homography. Two innovations are made in this chapter - (1) To more precisely locate the ground location of a person, all center vertical axes of the person across views are mapped to the top-view plane to find the intersection point. (2) To tackle the explosive state space due to multiple targets and views, iterative segmentation-searching is incorporated into a particle filtering framework. By searching for people's ground point locations from segmentations, a set of a few good particles can be identified, resulting in low computational cost. In addition, even if all the particles are away from the true ground point, some of them move towards the true one through the iterated process as long as they are located nearby. Finally, an objective no-reference measure is presented to assess fine-structure image/video quality. The proposed measure using local statistics reflects image degradation well in terms of noise and blur.
  • Thumbnail Image
    Item
    Zoomable User Interfaces for the Authoring and Delivery of Slide Presentations
    (2003-10-27) Good, Lance Everett; Bederson, Benjamin B; Stefik, Mark J; Computer Science
    Millions of slide presentations are being authored and delivered with computer software every day. Yet much of the computer's power for these tasks remains untapped. Existing interaction techniques leave presenters wrestling with limited size computer displays to get meaningful overviews of their work. Without these overviews, they have trouble finding patterns in their data and experimenting with alternate organizations. They also have difficulty communicating the structure of large or complex talks to the audience and keeping the audience oriented during unexpected transitions between ideas. A natural solution is Zoomable User Interfaces (ZUIs) since they offer the capability to view information at multiple levels of detail and smoothly transition between ideas. This work presents two ZUIs, Niagara and CounterPoint, for authoring and delivering slide presentations. Niagara is a ZUI workspace for authoring presentation content with techniques to improve authoring in the zoomable environment. Empirical evaluations of ZUI-based authoring tools revealed performance improvements and subjective preferences over folder-based interfaces for organization tasks. Users were 30% faster with ZUIs than with folders in completing a simplified shape organization task. Some classes of users were also faster with ZUIs than with folders in completing a text-based organization task. Users performing both tasks exhibited a strong preference for ZUIs over folders. CounterPoint provides a number of features to simplify the creation and delivery of ZUI presentations. The effects of these presentations on the audience were evaluated in a controlled comparison of presentations with slides only, slides with spatial layouts, and slides with spatial layouts and animation. The study revealed a strong subjective preference and higher ratings of organization for presentations with spatial layout. Feedback was also gathered from presenters who used CounterPoint to deliver over 100 real-world presentations. They indicated that CounterPoint helped them communicate overviews and multi-level presentation structures. More experienced CounterPoint presenters also found that CounterPoint helped them keep the audience oriented when navigating the presentation in response to audience feedback.