Graphics and Human Computer Interfaces Commons^™

Evolutionary Design Of Search And Triage Interfaces For Large Document Sets, Jonathan A. Demelo

Electronic Thesis and Dissertation Repository

This dissertation is concerned with the design of visual interfaces for searching and triaging large document sets. Data proliferation has generated new and challenging information-based tasks across various domains. Yet, as the document sets of these tasks grow, it has become increasingly difficult for users to remain active participants in the information-seeking process, such as when searching and triaging large document sets. During information search, users seek to understand their document set, align domain knowledge, formulate effective queries, and use those queries to develop document set mappings which help generate encounters with valued documents. During information triage, users encounter the …

Calibration Between Eye Tracker And Stereoscopic Vision System Employing A Linear Closed-Form Perspective-N-Point (Pnp) Algorithm, Mohammad Karami

Electronic Thesis and Dissertation Repository

In many advanced driver assistance systems (ADAS) applications, it is essential to figure out where gaze of driver locates in image area of stereoscopic vision system. This problem, which involves a cross calibration between the stereo vision system and eye tracker, is a challenging task since the two systems are not consistent in modality and do not share a common image area. The eye tracker system provides a 3D gaze vector which describes the direction of driver’s 3D line of gaze, while the stereoscopic vision system provides a depth image frame. In this thesis, this crosscalibration was performed with a …

Making Sense Of Online Public Health Debates With Visual Analytics Systems, Anton Ninkov

Electronic Thesis and Dissertation Repository

Online debates occur frequently and on a wide variety of topics. Particularly, online debates about various public health topics (e.g., vaccines, statins, cannabis, dieting plans) are prevalent in today’s society. These debates are important because of the real-world implications they can have on public health. Therefore, it is important for public health stakeholders (i.e., those with a vested interest in public health) and the general public to have the ability to make sense of these debates quickly and effectively. This dissertation investigates ways of enabling sense-making of these debates with the use of visual analytics systems (VASes). VASes are computational …

Simulation Approaches To X-Ray C-Arm-Based Interventions, Daniel R. Allen

Electronic Thesis and Dissertation Repository

Mobile C-Arm systems have enabled interventional spine procedures, such as facet joint injections, to be performed minimally-invasively under X-ray or fluoroscopy guidance. The downside to these procedures is the radiation exposure the patient and medical staff are subject to, which can vary greatly depending on the procedure as well as the skill and experience of the team. Standard training methods for these procedures involve the use of a physical C-Arm with real X-rays training on either cadavers or via an apprenticeship-based program. Many guidance systems have been proposed in the literature which aim to reduce the amount of radiation exposure …

Triaging Twitter Users: An Exploratory Visual Analytics System, Parinaz Nasr Esfahani

Electronic Thesis and Dissertation Repository

Twitter is one of the most popular microblogging and social networking services. Many people from a wide range of backgrounds use Twitter to contribute their thoughts on different topics through postings, known as ``tweets”. Analysts collect and analyze tweets to extract knowledge. To rely on tweets, it is crucial to assess Twitter users’ credibility. In recent years, researchers have proposed various techniques, especially data analytics models, for evaluating Twitter users and analyzing their behaviour; however, these techniques do not engage analysts in the process, leading to a lack of understanding and trust in results. In this thesis, an exploratory visual …

Design Of Interactive Visualizations For Next-Generation Ultra-Large Communication Networks, Wenjun Chen

Electronic Thesis and Dissertation Repository

With the increasing size and complexity of next-generation communication networks, it is critical to utilize interactive information visualization to support the network monitoring, planning, and management. Effectively visualizing large-scale networks has been considered difficult with traditional methods because of the high link density and complicated node relationship. Given the limited screen space, it is essential to explore how to present ultra-large-scale network data efficiently that can assist Internet Service Provider’s (ISP) network planning and management activities. This work proposes a design of the real-time interactive visualization system that combines the idea of progressive disclosure and multiple panels to elegantly visualize …

Edge-Cloud Iot Data Analytics: Intelligence At The Edge With Deep Learning, Ananda Mohon M. Ghosh

Electronic Thesis and Dissertation Repository

Rapid growth in numbers of connected devices, including sensors, mobile, wearable, and other Internet of Things (IoT) devices, is creating an explosion of data that are moving across the network. To carry out machine learning (ML), IoT data are typically transferred to the cloud or another centralized system for storage and processing; however, this causes latencies and increases network traffic. Edge computing has the potential to remedy those issues by moving computation closer to the network edge and data sources. On the other hand, edge computing is limited in terms of computational power and thus is not well suited for …

A Visual Analytics System For Investigating Multimorbidity Using Supervised Machine Learning, Maede Sadat Nouri

Electronic Thesis and Dissertation Repository

Patterns of multimorbidity are complex and difficult to summarise using static visualization techniques like tables and charts. We present a visual analytics system with the goal of facilitating the process of making sense of data collected from patients with multimorbidity. The system reveals underlying patterns in the data visually and interactively, which enables users to easily assess both prevalence and correlation estimates of different chronic diseases among multimorbid patients with varying characteristics. To do so, the system uses count-based conditional probability, binary logistic regression, softmax regression and decision tree models to dynamically compute and visualize prevalence and correlation estimates for …

The Design Of Interactive Visualizations And Analytics For Public Health Data, Oluwakemi Ola

Electronic Thesis and Dissertation Repository

Public health data plays a critical role in ensuring the health of the populace. Professionals use data as they engage in efforts to improve and protect the health of communities. For the public, data influences their ability to make health-related decisions. Health literacy, which is the ability of an individual to access, understand, and apply health data, is a key determinant of health. At present, people seeking to use public health data are confronted with a myriad of challenges some of which relate to the nature and structure of the data. Interactive visualizations are a category of computational tools that …

Patch-Based Denoising Algorithms For Single And Multi-View Images, Monagi H. Alkinani

Electronic Thesis and Dissertation Repository

In general, all single and multi-view digital images are captured using sensors, where they are often contaminated with noise, which is an undesired random signal. Such noise can also be produced during transmission or by lossy image compression. Reducing the noise and enhancing those images is among the fundamental digital image processing tasks. Improving the performance of image denoising methods, would greatly contribute to single or multi-view image processing techniques, e.g. segmentation, computing disparity maps, etc. Patch-based denoising methods have recently emerged as the state-of-the-art denoising approaches for various additive noise levels. This thesis proposes two patch-based denoising methods for …

Multi-View Ontology Explorer (Moe): Interactive Visual Exploration Of Ontologies, Zhao Lin

Electronic Thesis and Dissertation Repository

An ontology is an explicit specification of a conceptualization. This specification consists of a common vocabulary and information structure of a domain. Ontologies have applications in many fields to semantically link information in a standardized manner. In these fields, it is often crucial for both expert and non-expert users to quickly grasp the contents of an ontology; and to achieve this, many ontology tools implement visualization components. There are many past works on ontology visualization, and most of these tools are adapted from tree and graph based visualization techniques (e.g. treemaps, node-link graphs, and 3D interfaces). However, due to the …

Interactive Visualization For Deep Organizational Data, Arash Khosravi

Electronic Thesis and Dissertation Repository

During the last decade, there has been a growing interest in investigating how and why people use organizational data to solve problems, make decisions, and perform other cognitive activities, especially in the social network, healthcare, and education domains. Working with organizational data is challenging because of the complex and multi-structured nature of it. One way to support cognitive activities with organizational data is through the use of interactive visualization tools that provide different representations and mechanisms for interacting with deep layers of the data. In this research, we have deep organizational data which is mainly about collaborations inside universities. The …

An Investigation Of Cognitive Implications In The Design Of Computer Games, Robert Haworth

Electronic Thesis and Dissertation Repository

Computer games have been touted for their ability to engage players in cognitive activities (e.g., decision making, learning, planning, problem solving). By ‘computer game’ we mean any game that uses computational technology as its platform, regardless of the actual hardware or software; games on personal computers, tablets, game consoles, cellphones, or specialized equipment can all be called computer games. However, there remains much uncertainty regarding how to design computer games so that they support, facilitate, and promote the reflective, effortful, and conscious performance of cognitive activities. The goal of this dissertation is to relieve some of this uncertainty, so that …

A Software Design Pattern Based Approach To Auto Dynamic Difficulty In Video Games, Muhammad Iftekher Chowdhury

Electronic Thesis and Dissertation Repository

From the point of view of skill levels, reflex speeds, hand-eye coordination, tolerance for frustration, and motivations, video game players may vary drastically. Auto dynamic difficulty (ADD) in video games refers to the technique of automatically adjusting different aspects of a video game in real time, based on the player’s ability and emergence factors in order to provide the optimal experience to users from such a large demography and increase replay value. In this thesis, we describe a collection of software design patterns for enabling auto dynamic difficulty in video games. We also discuss the benefits of a design pattern …

Extracting Vessel Structure From 3d Image Data, Yuchen Zhong

Electronic Thesis and Dissertation Repository

This thesis is focused on extracting the structure of vessels from 3D cardiac images. In many biomedical applications it is important to segment the vessels preserving their anatomically-correct topological structure. That is, the final result should form a tree. There are many technical challenges when solving this image analysis problem: noise, outliers, partial volume. In particular, standard segmentation methods are known to have problems with extracting thin structures and with enforcing topological constraints. All these issues explain why vessel segmentation remains an unsolved problem despite years of research.

Our new efforts combine recent advances in optimization-based methods for image analysis …

Accessibility Of E-Commerce Websites For Vision Impaired Persons, Roopa Bose

Electronic Thesis and Dissertation Repository

In this thesis accessibility problems with websites for vision-impaired persons are discussed in detail. General accessibility problems and those specific to e-commerce websites,especially on-line shopping websites are discussed. Accessibility problems are analyzed from the perspective of a screen reader user. As a solution for the accessibility problems identified, the WCAG 2.0 guidelines are reviewed and new changes are proposed to improve the existing guidelines. Enhanced solutions using tactile media capable of providing a better web browsing experience for vision-impaired persons are also discussed.

A Modular Approach To The Development Of Interactive Augmented Reality Applications., Nelson J. Andre

Electronic Thesis and Dissertation Repository

Augmented reality (AR) technologies are becoming increasingly popular as a result of the increase in the power of mobile computing devices. Emerging AR applications have the potential to have an enormous impact on industries such as education, healthcare, research, training and entertainment. There are currently a number of augmented reality toolkits and libraries available for the development of these applications; however, there is currently no standard tool for development. In this thesis we propose a modular approach to the organization and development of AR systems in order to enable the creation novel AR experiences. We also investigate the incorporation of …

Detecting Multilingual Lines Of Text With Fusion Moves, Igor Milevskiy

Electronic Thesis and Dissertation Repository

This thesis proposes an optimization-based algorithm for detecting lines of text in images taken by hand-held cameras. The majority of existing methods for this problem assume alphabet-based texts (e.g. in Latin or Greek) and they use heuristics specific to such texts: proximity between letters within one line, larger distance between separate lines, etc. We are interested in a more challenging problem where images combine alphabet and logographic characters from multiple languages where typographic rules vary a lot (e.g. English, Korean, and Chinese). Significantly higher complexity of fitting multiple lines of text in different languages calls for an energy-based formulation combining …

Redesign Of Johar: A Framework For Developing Accessible Applications, Oladapo Oyebode

Electronic Thesis and Dissertation Repository

As the population of disabled people continues to grow, designing accessible applications is still a challenge, since most applications are incompatible with assistive technologies used by disabled people to interact with the computer. This accessibility issue is usually caused by the reluctance of software engineers or developers to include complete accessibility features in their applications, which in turn is often due to the extra cost and development effort required to dynamically adapt applications to a wide range of disabilities. Our aim to resolve accessibility issues led to the design and implementation of the "Johar" framework, which facilitates the development of …

Representation, Recognition And Collaboration With Digital Ink, Rui Hu

Electronic Thesis and Dissertation Repository

Pen input for computing devices is now widespread, providing a promising interaction mechanism for many purposes. Nevertheless, the diverse nature of digital ink and varied application domains still present many challenges. First, the sampling rate and resolution of pen-based devices keep improving, making input data more costly to process and store. At the same time, existing applications typically record digital ink either in proprietary formats, which are restricted to single platforms and consequently lack portability, or simply as images, which lose important information. Moreover, in certain domains such as mathematics, current systems are now achieving good recognition rates on individual …

Cognitive Activity Support Tools: Design Of The Visual Interface, Paul Parsons

Electronic Thesis and Dissertation Repository

This dissertation is broadly concerned with interactive computational tools that support the performance of complex cognitive activities, examples of which are analytical reasoning, decision making, problem solving, sense making, forecasting, and learning. Examples of tools that support such activities are visualization-based tools in the areas of: education, information visualization, personal information management, statistics, and health informatics. Such tools enable access to information and data and, through interaction, enable a human-information discourse. In a more specific sense, this dissertation is concerned with the design of the visual interface of these tools. This dissertation presents a large and comprehensive theoretical framework to …

Vehicular Instrumentation And Data Processing For The Study Of Driver Intent, Taha Kowsari

Electronic Thesis and Dissertation Repository

The primary goal of this thesis is to provide processed experimental data needed to determine whether driver intentionality and driving-related actions can be predicted from quantitative and qualitative analysis of driver behaviour. Towards this end, an instrumented experimental vehicle capable of recording several synchronized streams of data from the surroundings of the vehicle, the driver gaze with head pose and the vehicle state in a naturalistic driving environment was designed and developed. Several driving data sequences in both urban and rural environments were recorded with the instrumented vehicle. These sequences were automatically annotated for relevant artifacts such as lanes, vehicles …

Ratio-Based Edge Detection Inspired Speckle Reducing Anisotropic Diffusion, Asaduzzaman Babu

Electronic Thesis and Dissertation Repository

Speckle Reducing Anisotropic Diffusion, SRAD, is a multiplicative speckle noise reduction method. In highly speckled environment, SRAD occasionally produces over-smoothed, dislocated/broadened edge lines and inadequate de-noising on homogeneous image regions where the speckles are well developed. Moreover, the performance of SRAD is highly dependent on the initial selection of a good homogeneous area. To overcome these weaknesses, we propose two different ratio-based edge detection inspired extensions to SRAD. One of the proposed extensions incorporates an edge-sensitive boosting factor to guide the gradient and Laplacian operator based edge detector of SRAD. The edge-sensitive boosting factor is defined by the global edge …

A Support System For Graphics For Visually Impaired People, Hao Xu

Electronic Thesis and Dissertation Repository

As the Internet plays an important role in today’s society, graphics is widely used to present, convey and communicate information in many different areas. Complex information is often easier to understand and analyze by graphics. Even though graphics plays an important role, accessibility support is very limited for web graphics. Web graphics accessibility is not only for people with disabilities, but also for people who want to get and use information in ways different from the ones originally intended.

One of the problems regarding graphics for blind people is that we have few data on how a blind person draws …

Automatic Foreground Initialization For Binary Image Segmentation, Wei Li

Electronic Thesis and Dissertation Repository

Foreground segmentation is a fundamental problem in computer vision. A popular approach for foreground extraction is through graph cuts in energy minimization framework. Most existing graph cuts based image segmentation algorithms rely on user’s initialization. In this work, we aim to find an automatic initialization for graph cuts. Unlike many previous methods, no additional training dataset is needed. Collecting a training set is not only expensive and time consuming, but it also may bias the algorithm to the particular data distribution of the collected dataset. We assume that the foreground differs significantly from the background in some unknown feature space …

Interactive Augmented Reality As A Support Tool For Parkinson’S Disease Rehabilitation Programs, Andrés Ayala García

Electronic Thesis and Dissertation Repository

In this thesis, an augmented reality system is proposed as an alternative to create multiple interactive virtual environments that might later be used in Parkinson’s Disease rehabilitation programs. The main objective of this thesis is to develop a Wearable Tangible Augmented Reality Environment focused on providing the sense of presence required to effectively immerse patients so that they are able to perform different tasks in context–specific scenarios. By using our system, patients are able to freely navigate different virtual environments. Moreover, by segmenting and then overlaying users’ hands and objects of interest above the 3D environment, patients have the ability …

3d Velocity Retrieval And Storm Tracking Using Multiple Radars, Yong Zhang

Electronic Thesis and Dissertation Repository

Severe weather forecasting is one of the most important and urgent tasks in the meteorology field. This thesis builds on previous work by Barron and Mercer and their graduate students, concerning the use of 3D optical flow to retrieve 3D wind velocity from 3D Doppler radial velocity datasets and tracking 3D severe weather storms using fuzzy points realized as ellipsoids to represent storms and a fuzzy algebra machinery in a relaxation labeling framework to track storms in Doppler precipitation datasets.

We first extend the original 3D optical flow (both least squares and regularization methods) for recovering 3D wind velocity from …

Classic Mosaics And Visual Correspondence Via Graph-Cut Based Energy Optimization, Yu Liu

Electronic Thesis and Dissertation Repository

Computer graphics and computer vision were traditionally two distinct research fields focusing on opposite topics. Lately, they have been increasingly borrowing ideas and tools from each other. In this thesis, we investigate two problems in computer vision and graphics that rely on the same tool, namely energy optimization with graph cuts.

In the area of computer graphics, we address the problem of generating artificial classic mosaics, still and animated. The main purpose of artificial mosaics is to help a user to create digital art. First we reformulate our previous static mosaic work in a more principled global optimization framework. Then, …