Graphics and Human Computer Interfaces Commons^™

Poster Abstract: Data Communication Using Switchable Privacy Glass, Changshuo Hu, Dong Ma, Mahbub Hassan, Wen Hu

Research Collection School Of Computing and Information Systems

Switchable privacy glass can electronically change its state between opaque and transparent. In this work, we propose to exploit the electronic configurability of switchable glass to modulate natural light, which can be demodulated by a nearby receiver with light sensing capability to realise data communication over natural light. A key advantage is that no energy is used to generate light, as it simply modulates the existing light in the nature. We demonstrate that the proposed data communication using switchable glass modulation can achieve 33.33 bits per second communication with a bit rate below 1% under a wide range of ambient …

Reinforced Negative Sampling Over Knowledge Graph For Recommendation, Xiang Wang, Yaokun Xu, Xiangnan He, Yixin Cao, Meng Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Properly handling missing data is a fundamental challenge in recommendation. Most present works perform negative sampling from unobserved data to supply the training of recommender models with negative signals. Nevertheless, existing negative sampling strategies, either static or adaptive ones, are insufficient to yield high-quality negative samples — both informative to model training and reflective of user real needs. In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples. Towards this end, we develop a new negative sampling model, Knowledge Graph Policy …

Techniques To Visualize Occluded Graph Elements For 2.5d Map Editing, Kazuyuki Fujita, Daigo Hayashi, Kotaro Hara, Kazuki Takashima, Yoshifumi Kitamura

Research Collection School Of Computing and Information Systems

We propose an interface with two novel techniques to visualize occluded graph nodes and edges that help the user edit map data with a 2.5D geographical structure (e.g., multi-floor indoor maps). We first design a visualization technique —Repel Signification— that employs micro-animation to signify the graph elements that are overlapping with each other (and potentially erroneous). We also design a technique that enables the user to edit the occluded components with Expansion Interaction, which simultaneously visualizes both in-floor and across-floor occluded connections between the map elements. The combination of the two methods would enable the map editors (non-experts) to effectively …

The Impact Of Changing The Size Of Aircraft Radar Displays On Visual Search In The Cockpit, Justin R. Marsh

Theses and Dissertations

Advances in sensor technology have enabled our fighter aircraft to find, fix, track, target, engage (F2T2E) at greater distances, providing the operator with more data within the battlefield. Modern aircraft are designed with larger displays while our legacy aircraft are being retrofitted with larger cockpit displays to enable display of the increased data. While this modification has been shown to enable improvements in human performance of many cockpit tasks, this effect is often not measured nor fully understood at a more generalizable level. This research outlines an approach to comparing human performance across two display sizes in future F-16 cockpits. …

Electronic Image Detectability Under Varying Illumination Conditions, Jeremy J. Miller

Theses and Dissertations

Light in the built environment plays an essential role in the vision and the health of humans through non-visual receptors in the eyes. Unfortunately, image analysts and other Air Force personnel who engage in the detection of objects on softcopy displays are often required to work in very dimly-lit or dark environments as higher illumination reduces the contrast of displayed information. Literature has shown that increases in light exposure improves circadian rhythm entrainment and reduces the negative health consequences of insufficient lighting. This research examines the effects of indoor lighting to determine if increases in ambient illumination or changes to …

Image Enhanced Event Detection In News Articles, Meihan Tong, Shuai Wang, Yixin Cao, Bin Xu, Juaizi Li, Lei Hou, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Event detection is a crucial and challenging sub-task of event extraction, which suffers from a severe ambiguity issue of trigger words. Existing works mainly focus on using textual context information, while there naturally exist many images accompanied by news articles that are yet to be explored. We believe that images not only reflect the core events of the text, but are also helpful for the disambiguation of trigger words. In this paper, we first contribute an image dataset supplement to ED benchmarks (i.e., ACE2005) for training and evaluation. We then propose a novel Dual Recurrent Multimodal Model, DRMM, to conduct …

Zero-Shot Ingredient Recognition By Multi-Relational Graph Convolutional Network, Jingjing Chen, Liangming Pan, Zhipeng Wei, Xiang Wang, Chong-Wah Ngo, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recognizing ingredients for a given dish image is at the core of automatic dietary assessment, attracting increasing attention from both industry and academia. Nevertheless, the task is challenging due to the difficulty of collecting and labeling sufficient training data. On one hand, there are hundred thousands of food ingredients in the world, ranging from the common to rare. Collecting training samples for all of the ingredient categories is difficult. On the other hand, as the ingredient appearances exhibit huge visual variance during the food preparation, it requires to collect the training samples under different cooking and cutting methods for robust …

Gdface: Gated Deformation For Multi-View Face Image Synthesis, Xuemiao Xu, Keke Li, Cheng Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Photorealistic multi-view face synthesis from a single image is an important but challenging problem. Existing methods mainly learn a texture mapping model from the source face to the target face. However, they fail to consider the internal deformation caused by the change of poses, leading to the unsatisfactory synthesized results for large pose variations. In this paper, we propose a Gated Deformable Face Synthesis Network to model the deformation of faces that aids the synthesis of the target face image. Specifically, we propose a dual network that consists of two modules. The first module estimates the deformation of two views …

Example-Based Colourization Via Dense Encoding Pyramids, Chufeng Xiao, Chu Han, Zhuming Zhang, Jing Qin, Tien-Tsin Wong, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

We propose a novel deep example-based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large-scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi-scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both …

Accessibility Of Deepfakes, Andrew L. Collings

Cybersecurity Undergraduate Research Showcase

The danger posed by falsified media, commonly referred to as deepfakes, has been well researched and documented. The software Faceswap to was used to swap the faces of two politician (Joe Biden and Donald Trump). The testing was performed using an affordable consumer GPU (an AMD Radeon RX 570) over 100,000 iterations. The process and results for the two attempts with the best results (and largest differences) were recorded. The result was ultimately unconvincing, while the software was able to recreate the facial structure the lighting and skin tone did not blend at all.

Building Something With The Raspberry Pi, Richard Kordel

Harrisburg University Presidential Research Grants

In 2017 Ryan Korn and I submitted a grant proposal in the annual Harrisburg University President’s Grant process. Our proposal was to partner with a local high school to install a classroom of 20 Raspberry Pi’s, along with the requisite peripherals. In that classroom students would be challenged to design something that combined programming with physical computing. In our presentation to the school we suggested that this project would give students the opportunity to be “amazing.”

As part of the grant, the top three students would be given scholarships to HU and the top five finalists would all be permitted …

Repurposing Visual Input Modalities For Blind Users: A Case Study Of Word Processors, Hae-Na Lee, Vikas Ashok, I.V. Ramakrishnan

Computer Science Faculty Publications

Visual 'point-and-click' interaction artifacts such as mouse and touchpad are tangible input modalities, which are essential for sighted users to conveniently interact with computer applications. In contrast, blind users are unable to leverage these visual input modalities and are thus limited while interacting with computers using a sequentially narrating screen-reader assistive technology that is coupled to keyboards. As a consequence, blind users generally require significantly more time and effort to do even simple application tasks (e.g., applying a style to text in a word processor) using only keyboard, compared to their sighted peers who can effortlessly accomplish the same tasks …

Rotate-And-Press: A Non-Visual Alternative To Point-And-Click, Hae-Na Lee, Vikas Ashok, I. V. Ramakrishnan

Computer Science Faculty Publications

Most computer applications manifest visually rich and dense graphical user interfaces (GUIs) that are primarily tailored for an easy-and-efficient sighted interaction using a combination of two default input modalities, namely the keyboard and the mouse/touchpad. However, blind screen-reader users predominantly rely only on keyboard, and therefore struggle to interact with these applications, since it is both arduous and tedious to perform the visual 'point-and-click' tasks such as accessing the various application commands/features using just keyboard shortcuts supported by screen readers.

In this paper, we investigate the suitability of a 'rotate-and-press' input modality as an effective non-visual substitute for the visual …

Svat4: A Computer Program For Visualization And Analysis Of Crystal Structures, Xingzhong Li

Nebraska Center for Materials and Nanoscience: Faculty Publications

SVAT4 is a computer program for interactive visualization of three-dimensional crystal structures, including chemical bonds and magnetic moments. A wide range of functions, e.g. revealing atomic layers and polyhedral clusters, are available for further structural analysis. Atomic sizes, colors, appearance, view directions and view modes (orthographic or perspective views) are adjustable. Customized work for the visualization and analysis can be saved and then reloaded. SVAT4 provides a template to simplify the process of preparation of a new data file. SVAT4 can generate high-quality images for publication and animations for presentations. The usability of SVAT4 is broadened by a software suite …

Nnv: The Neural Network Verification Tool For Deep Neural Networks And Learning-Enabled Cyber-Physical Systems, Hoang-Dung Tran, Xiaodong Yang, Diego Manzanas Lopez, Patrick Musau, Luan Viet Nguyen, Weiming Xiang, Stanley Bak, Taylor T. Johnson

Computer Science Faculty Publications

This paper presents the Neural Network Verification (NNV) software tool, a set-based verification framework for deep neural networks (DNNs) and learning-enabled cyber-physical systems (CPS). The crux of NNV is a collection of reachability algorithms that make use of a variety of set representations, such as polyhedra, star sets, zonotopes, and abstract-domain representations. NNV supports both exact (sound and complete) and over-approximate (sound) reachability algorithms for verifying safety and robustness properties of feed-forward neural networks (FFNNs) with various activation functions. For learning-enabled CPS, such as closed-loop control systems incorporating neural networks, NNV provides exact and over-approximate reachability analysis schemes for linear …

Intelligent Cinematic Camera Control For Real-Time Graphics Applications, Ian Harris Meeder

Master's Theses

E-sports is currently estimated to be a billion dollar industry which is only growing in size from year to year. However the cinematography of spectated games leaves much to be desired. In most cases, the spectator either gets to control their own freely-moving camera or they get to see the view that a specific player sees. This thesis presents a system for the generation of cinematically-pleasing views for spectating real-time graphics applications. A custom real-time engine has been built to demonstrate the effect of this system on several different game modes with varying visual cinematic constraints, such as the rule …

Security Camera Using Raspberry Pi, Tejendra Khatri

Student Academic Conference

Making a security camera using raspberry pi utilizing OpenCV for facial recognition, upper body recognition or full-body recognition

Navigating Immersive And Interactive Vr Environments With Connected 360° Panoramas, Samuel Cosgrove

Electronic Theses and Dissertations, 2020-2023

Emerging research is expanding the idea of using 360-degree spherical panoramas of real-world environments for use in "360 VR" experiences beyond video and image viewing. However, most of these experiences are strictly guided, with few opportunities for interaction or exploration. There is a desire to develop experiences with cohesive virtual environments created with 360 VR that allow for choice in navigation, versus scripted experiences with limited interaction. Unlike standard VR with the freedom of synthetic graphics, there are challenges in designing appropriate user interfaces (UIs) for 360 VR navigation within the limitations of fixed assets. To tackle this gap, we …

“Distance Learning” In The Ninth Century?: Micro-Cluster Analysis Of The Epistolary Network Of Alcuin After 796, William James Mattingly

Theses and Dissertations--History

Scholars of eighth- and ninth-century education have assumed that intellectuals did not write works of Scriptural interpretation until that intellectual had a firm foundation in the seven liberal arts.This ensured that anyone who embarked on work of Scriptural interpretation would have the required knowledge and methods to read and interpret Scripture correctly. The potential for theological error and the transmission of those errors was too great unless the interpreter had the requisite training. This dissertation employs computistical methods, specifically the techniques of social network mapping and cluster analysis, to study closely the correspondence of Alcuin, a late-eighth- and early-ninth-century scholar …

Needfinding, Devorah Kletenik

Open Educational Resources

This activity guides students through the process needfinding to identify areas of need for their creation of a technology for the "public good." Students will conduct contextual inquiry to identify the needs of their target audience.

Personas, Scenarios And Storyboards, Devorah Kletenik

Open Educational Resources

This activity guides students towards the creation of personas, scenarios and storyboards for a product/website that they are creating.

Public Interest Technology: Coding For The Public Good, Devorah Kletenik

Open Educational Resources

These slides are used to guide a discussion with students introducing them to the notion of public interest technology and coding for the public good. The lesson is intended to spark a discussion with students about different sorts of technology and their societal ramifications.

Accessibility: The Whys And The Hows, Devorah Kletenik

Open Educational Resources

This presentation introduces Computer Science students to the notion of accessibility: developing software for people with disabilities. This lesson provides a discussion of why accessibility is important (including the legal, societal and ethical benefits) as well as an overview of different types of impairments (visual, auditory, motor, neurological/cognitive) and how developers can make their software accessible to users with those disabilities. This lesson includes videos and links to readings and tutorials for students.

Coding For The Public Good: Front-End Website Design And Development, Devorah Kletenik

Open Educational Resources

This activity helps student design and develop a front-end of a website, from wireframes through HTML/CSS/Javascript. It includes design questions for students, including the invocation of Ben Schneiderman's eight golden rules for interface design.

Note: this activity assumes prior knowledge of web development. Since this activity is designed for an HCI course, with a focus on interface design, students are not expected to create a back-end for it. This activity can obviously be modified for a full-stack experience.

Accessibility Evaluation, Devorah Kletenik

Open Educational Resources

This activity guides students through the evaluation of a website that they have created to see if it is accessible for users with disabilities. Students will simulate a number of different disabilities (e.g. visual impairments, color blindness, auditory impairments, motor impairments) to see if their website is accessible; they will also use automated W3 and WAVE tools to evaluate their sites. Students will consider the needs of users with disabilities by creating a persona and scenario of a user with disabilities interacting with their site. Finally, students will write up recommendations to change their site and implement the changes.

V-Slam And Sensor Fusion For Ground Robots, Ejup Hoxha

Dissertations and Theses

In underground, underwater and indoor environments, a robot has to rely solely on its on-board sensors to sense and understand its surroundings. This is the main reason why SLAM gained the popularity it has today. In recent years, we have seen excellent improvement on accuracy of localization using cameras and combinations of different sensors, especially camera-IMU (VIO) fusion. Incorporating more sensors leads to improvement of accuracy,but also robustness of SLAM. However, while testing SLAM in our ground robots, we have seen a decrease in performance quality when using the same algorithms on flying vehicles.We have an additional sensor for ground …

Automatic Gaze Classification For Aviators: Using Multi-Task Convolutional Networks As A Proxy For Flight Instructor Observation, Justin Wilson, Sandro Scielzo, Sukumaran Nair, Eric C. Larson

International Journal of Aviation, Aeronautics, and Aerospace

In this work, we investigate how flight instructors observe aviator scan patterns and assign quality to an aviator's gaze. We first establish the reliability of instructors to assign similar quality to an aviator's scan patterns, and then investigate methods to automate this quality using machine learning. In particular, we focus on the classification of gaze for aviators in a mixed-reality flight simulation. We create and evaluate two machine learning models for classifying gaze quality of aviators: a task-agnostic model and a multi-task model. Both models use deep convolutional neural networks to classify the quality of pilot gaze patterns for 40 …

Interactions Between Humans, Virtual Agent Characters And Virtual Avatars, Tamara Griffith

Electronic Theses and Dissertations, 2020-2023

Simulations allow people to experience events as if they were happening in the real world in a way that is safer and less expensive than live training. Despite improvements in realism in simulated environments, one area that still presents a challenge is interpersonal interactions. The subtleties of what makes an interaction rich are difficult to define. We may never fully understand the complexity of human interchanges, however there is value in building on existing research into how individuals react to virtual characters to inform future investments. Virtual characters can either be automated through computational processes, referred to as agents, or …

Toward Efficient Automation Of Interpretable Machine Learning Boosting, Nathan Neuhaus

All Master's Theses

Developing efficient automated methods for Interpretable Machine Learning (IML) is an important and long-term goal in the field of Artificial Intelligence. Currently the Machine Learning landscape is dominated by Neural Networks (NNs) and Support Vector Machines (SVMs), models which are often highly accurate. Despite high accuracy, such models are essentially “black boxes” and therefore are too risky for situations like healthcare where real lives are at stake. In such situations, so called “glass-box” models, such as Decision Trees (DTs), Bayesian Networks (BNs), and Logic Relational (LR) models are often preferred, however can succumb to accuracy limitations. Unfortunately, having to choose …

Neighbourhood Structure Preserving Cross-Modal Embedding For Video Hyperlinking, Yanbin Hao, Chong-Wah Ngo, Benoit Huet

Research Collection School Of Computing and Information Systems

Video hyperlinking is a task aiming to enhance the accessibility of large archives, by establishing links between fragments of videos. The links model the aboutness between fragments for efficient traversal of video content. This paper addresses the problem of link construction from the perspective of cross-modal embedding. To this end, a generalized multi-modal auto-encoder is proposed.& x00A0;The encoder learns two embeddings from visual and speech modalities, respectively, whereas each of the embeddings performs self-modal and cross-modal translation of modalities. Furthermore, to preserve the neighbourhood structure of fragments, which is important for video hyperlinking, the auto-encoder is devised to model data …