Graphics and Human Computer Interfaces Commons^™

A Reliable And Efficient Wireless Sensor Network System For Water Quality Monitoring, Dung Nguyen, Phu Huu Phung

Computer Science Faculty Publications

Wireless sensor networks (WSNs) are strongly useful to monitor physical and environmental conditions to provide realtime information for improving environment quality. However, deploying a WSN in a physical environment faces several critical challenges such as high energy consumption, and data loss.In this work, we have proposed a reliable and efficient environmental monitoring system in ponds using wireless sensor network and cellular communication technologies. We have designed a hardware and software ecosystem that can limit the data loss yet save the energy consumption of nodes. A lightweight protocol acknowledges data transmission among the nodes. Data are transmitted to the cloud using …

Object Detection Meets Knowledge Graphs, Yuan Fang, Kingsley Kuan, Jie Lin, Cheston Tan, Vijay Chandrasekhar

Research Collection School Of Computing and Information Systems

Object detection in images is a crucial task in computer vision, with important applications ranging from security surveillance to autonomous vehicles. Existing state-of-the-art algorithms, including deep neural networks, only focus on utilizing features within an image itself, largely neglecting the vast amount of background knowledge about the real world. In this paper, we propose a novel framework of knowledge-aware object detection, which enables the integration of external knowledge such as knowledge graphs into any object detection algorithm. The framework employs the notion of semantic consistency to quantify and generalize knowledge, which improves object detection through a re-optimization process to achieve …

Bridge Text And Knowledge By Learning Multi-Prototype Entity Mention Embedding, Yixin Cao, Lifu Huang, Heng Ji, Xu Chen, Juanzi Li

Research Collection School Of Computing and Information Systems

Integrating text and knowledge into a unified semantic space has attracted significant research interests recently. However, the ambiguity in the common space remains a challenge, namely that the same mention phrase usually refers to various entities. In this paper, to deal with the ambiguity of entity mentions, we propose a novel Multi-Prototype Mention Embedding model, which learns multiple sense embeddings for each mention by jointly modeling words from textual contexts and entities derived from a knowledge base. In addition, we further design an efficient language model based approach to disambiguate each mention to a specific sense. In experiments, both qualitative …

Formresnet: Formatted Residual Learning For Image Restoration, Jianbo Jiao, Wei-Chih Tu, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we propose a deep CNN to tackle the image restoration problem by learning the structured residual. Previous deep learning based methods directly learn the mapping from corrupted images to clean images, and may suffer from the gradient exploding/vanishing problems of deep neural networks. We propose to address the image restoration problem by learning the structured details and recovering the latent clean image together, from the shared information between the corrupted image and the latent image. In addition, instead of learning the pure difference (corruption), we propose to add a 'residual formatting layer' to format the residual to …

Learning To Hallucinate Face Images Via Component Generation And Enhancement, Yibing Song, Jiawei Zhang, Shengfeng He, Linchao Bao, Qingxiong Yang

Research Collection School Of Computing and Information Systems

We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods.

Editable View Optimized Tone Mapping For Viewing High Dynamic Range Panoramas On Head Mounted Display, Yuan Li

Boise State University Theses and Dissertations

Head mounted displays are characterized by relatively low resolution and low dynamic range. These limitations significantly reduce the visual quality of photo-realistic captures on such displays. This thesis presents an interactive view optimized tone mapping technique for viewing large sized high dynamic range panoramas up to 16384 by 8192 on head mounted displays. This technique generates a separate file storing pre-computed view-adjusted mapping function parameters. We define this technique as ToneTexture. The use of a view adjusted tone mapping allows for expansion of the perceived color space available to the end user. This yields an improved visual appearance of …

The Role Of Knowledge Sharing Via Organizational Social Media In The Workplace, Murad A. Moqbel, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Although a plethora of studies have been recently conducted on organizational social media, little research has specifically examined how organizational social media can contribute to organizational workers’ performance through knowledge sharing. The objective of this research is to fill this gap by investigating the role of knowledge sharing in organizational social media use and its effect on in-role and innovative performance through the lens of social capital and social cognitive theories. Hypotheses were developed and a survey study is proposed.

A Pattern Approach To Examine The Design Space Of Spatiotemporal Visualization, Chen Guo

Department of Computer Graphics Technology Degree Theses

Pattern language has been widely used in the development of visualization systems. This dissertation applies a pattern language approach to explore the design space of spatiotemporal visualization. The study provides a framework for both designers and novices to communicate, develop, evaluate, and share spatiotemporal visualization design on an abstract level. The touchstone of the work is a pattern language consisting of fifteen design patterns and four categories. In order to validate the design patterns, the researcher created two visualization systems with this framework in mind. The first system displayed the daily routine of human beings via a polygon-based visualization. The …

Touchscreen Smartphone User Interfaces For Older Adults, Ai Sano

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Today the world is experiencing the rapid growth of the older population. The number of older adults who own digital devices such as smartphones is increasing as well. The current smartphone user interfaces, however, appear not optimized for older adults. When designing smartphone user interfaces for older adults, we must consider their age-related physical and cognitive changes, which most likely affect their user experience. The present paper explores smartphone user interface guidelines for older adults and heuristics for evaluating the usability of Android launchers for older adults as well as a research study that developed an Android launcher for older …

An Overview Of Modern Global Illumination, Skye A. Antinozzi

Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal

Advancements in graphical hardware call for innovative solutions, which can improve the realism of computer generated lighting. These innovative solutions aim to generate state of the art computer generated lighting through a combination of intelligent global illumination models and the use of modern hardware. The solution described in this paper achieves global illumination by ray tracing over geometry within a 3D scene from distributed light field probes and proceeds to shade the scene with a deferred renderer. Such a solution provides the flexibility and robustness that many other global illumination models have previously lacked while still achieving realistic lighting that …

Deep Learning On Lie Groups For Skeleton-Based Action Recognition, Zhiwu Huang, C. Wan, T. Probst, Gool L. Van

Research Collection School Of Computing and Information Systems

In recent years, skeleton-based action recognition has become a popular 3D classification problem. State-of-the-art methods typically first represent each motion sequence as a high-dimensional trajectory on a Lie group with an additional dynamic time warping, and then shallowly learn favorable Lie group features. In this paper we incorporate the Lie group structure into a deep network architecture to learn more appropriate Lie group features for 3D action recognition. Within the network structure, we design rotation mapping layers to transform the input Lie group features into desirable ones, which are aligned better in the temporal domain. To reduce the high feature …

Sparsity Based Reflection Removal Using External Patch Search, Renjie Wan, Boxin Shi, Ah-Hwee Tan, Alex C. Kot

Research Collection School Of Computing and Information Systems

Reflection removal aims at separating the mixture of the desired background scenes and the undesired reflections, when the photos are taken through the glass. It has both aesthetic and practical applications which can largely improve the performance of many multimedia tasks. Existing reflection removal approaches heavily rely on scene priors such as separable sparse gradients brought by different levels of blur, and they easily fail when such priors are not observed in many real scenes. Sparse representation models and nonlocal image priors have shown their effectiveness in image restoration with self similarity. In this work, we propose a reflection removal …

Effect Of Timing And Source Of Online Product Recommendations: An Eye-Tracking Study, Yan Shi, Qing Zeng, Fiona Fui-Hoon Nah, Chuan-Hoo Tan, Choon Ling Sia, Keng Siau, Jiaqi Yan

Research Collection School Of Computing and Information Systems

Online retail business has become an emerging market for almost all business owners. Online recommender systems provide better service to consumers during their decision making processes. In this study, a controlled lab experiment was conducted to assess the effect of recommendation timing (early, mid, and late) and recommendation source (expert reviews vs. consumer reviews) on online consumers’ interest and attention. Eye-tracking data was extracted from the experiment and analyzed. The results suggest that consumers show more interest in recommendation based on consumer reviews than expert reviews. Earlier recommendations do not receive greater attention than later recommendations.

Viral Marketing For Smart Cities: Influencers In Social Network Communities, Madhura Kaple, Ketki Kulkarni, Katerina Potika

Faculty Publications, Computer Science

Social networks are used by cities primarily for announcing local-area events, but also for increasing engagement of citizens in votes and elections. Given the current plethora of heterogeneous social networks, city administrators can benefit from social networks to promote initiatives, which are important to a current smart city as well use them to discover future needs in order to manage resources more efficiently. Our focus in this paper is how we can adapt commercial and viral marketing techniques to smart city systems to influence the behavior, opinion and choices of citizens in order to improve their well being and that …

Institutional Research And Advanced Analytics, Mary Kathryn Starkey, Shelby Albers

Research Data and Scholarly Communications Committee Workshops

Tableau empowers everyone to see and understand their data. The Institutional Research & Advanced Analytics (IRAA) team will deliver an engaging one-hour demonstration that covers the ins and outs of Tableau Desktop and Tableau Server. We will also show you University of Kentucky data that is currently available to you, as well as where to find and how to access said data.

The presentation slides are available by clicking the Download button on the right. The video and audio files of this workshop are listed as additional files below and are available for download.

Library Guides: An Aggregation Of User Research From 1998 To 2017, David Vess

Libraries

A truly comprehensive search tool for resources provided by libraries will continue to be a distant dream until daunting technical challenges are addressed. A Google-like search experience is desirable in some contexts, but a case can be made that hiding subject-specific article databases behind a comprehensive search tool is a disservice to researchers.

Librarians have a long history of addressing the complex landscape of the various resources they offer by crafting guides to library collections. These guides provide direct links to resources while educating inexperienced researchers about discipline-specific databases. Unfortunately, this solution creates more complexities in the research resource landscape. …

An Evaluation Of On-Screen Keyboards For First Time Single Switch Users, Paul Ahern, Rupert Westrup

The ITB Journal

This paper presents an evaluation of three designs for on-screen keyboard layouts for use by Single Switch Users (SSUs). SSUs are those users who have a disability which means that they are able to activate a switch into an "on" or "off'' position but are not able to locate or position a particular switch. The first keyboard layout design was alphabetically based, the second design was based upon the most frequently occurring letters in the English alphabet and the third design was the standard QWERTY layout found on most keyboards. The research shows that there is no significant difference in …

Procedurally Generating Genetic Keys, Adam A. Levasseur

Computer Engineering

This project presents a method for creating multi-part models based on input keys to generate new, variant models via genetic algorithms. By utilizing 3D models as modular parts, this method allows for the generation of a unique, compound model based on one or multiple input keys. This paper explains the process of creating and testing such generation styles using simple geometry to create more complex, compound models.

Eulerian On Lagrangian Cloth Simulation, Kyle C. Piddington

Master's Theses

This thesis introduces a novel Eulerian-on-Lagrangian (EoL) approach for simulating cloth. This approach allows for the simulation of traditionally difficult cloth scenarios, such as draping and sliding cloth over sharp features like the edge of a table. A traditional Lagrangian approach models a cloth as a series of connected nodes. These nodes are free to move in 3d space, but have difficulty with sliding over hard edges. The cloth cannot always bend smoothly around these edges, as motion can only occur at existing nodes. An EoL approach adds additional flexibility to a Lagrangian approach by constructing special Eulerian on Lagrangian …

P4sinc – An Execution Policy Framework For Iot Services In The Edge, Phu Huu Phung, Hong-Linh Truong, Divya Teja Yasoju

Computer Science Faculty Publications

Internet of Things (IoT) services are increasingly deployed at the edge to access and control Things. The execution of such services needs to be monitored to provide information for security, service contract, and system operation management. Although different techniques have been proposed for deploying and executing IoT services in IoT gateways and edge servers, there is a lack of generic policy frameworks for instrumentation and assurance of various types of execution policies for IoT services. In this paper, we present P4SINC as an execution policy framework that covers various functionalities for IoT services deployed in software-defined machines in IoT infrastructures. …