Computer Sciences Commons^™

Application Of Retrograde Analysis To Fighting Games, Kristen Yu

Electronic Theses and Dissertations

With the advent of the fighting game AI competition, there has been recent interest in two-player fighting games. Monte-Carlo Tree-Search approaches currently dominate the competition, but it is unclear if this is the best approach for all fighting games. In this thesis we study the design of two-player fighting games and the consequences of the game design on the types of AI that should be used for playing the game, as well as formally define the state space that fighting games are based on. Additionally, we also characterize how AI can solve the game given a simultaneous action game model, …

[Accepted Article Manuscript Version (Postprint)] Distributed Data-Gathering And -Processing In Smart Cities: An Information-Centric Approach, Reza Tourani, Abderrahmen Mtibaa, Satyajayant Misra

Computer Science Faculty Works

The technological advancements along with the proliferation of smart and connected devices (things) motivated the exploration of the creation of smart cities aimed at improving the quality of life, economic growth, and efficient resource utilization. Some recent initiatives defined a smart city network as the interconnection of the existing independent and heterogeneous networks and the infrastructure. However, considering the heterogeneity of the devices, communication technologies, network protocols, and platforms the interoperability of these networks is a challenge requiring more attention. In this paper, we propose the design of a novel Information-Centric Smart City architecture (iSmart), focusing on the demand of …

A Truthful Auction Mechanism For Mobile Crowd Sensing With Budget Constraint, Yuanni Liu, Xiaodan Xu, Jianli Pan, Jianhui Zhang, Guofeng Zhao

Computer Science Faculty Works

The selfishness and randomness of users in the mobile crowd sensing network could cause them unwilling to participate in sensing activities and lead to lower completion rates of sensing tasks. In order to deal with these problems, this paper proposes a novel incentive mechanism based on a new auction model for mobile crowd sensing, which consists of two consecutive stages. In the first stage, a novel Incentive Method based on Reverse Auction for Location-aware sensing (IMRAL) is proposed to maximize user utility. By introducing a task-centric method to determine the winning bids, it can provide higher user utility and higher …

Distributed Data-Gathering And -Processing In Smart Cities: An Information-Centric Approach, Reza Tourani, Abderrahmen Mtibaa, Satyajayant Misra

Computer Science Faculty Works

The technological advancements along with the proliferation of smart and connected devices (things) motivated the exploration of the creation of smart cities aimed at improving the quality of life, economic growth, and efficient resource utilization. Some recent initiatives defined a smart city network as the interconnection of the existing independent and heterogeneous networks and the infrastructure. However, considering the heterogeneity of the devices, communication technologies, network protocols, and platforms the interoperability of these networks is a challenge requiring more attention. In this paper, we propose the design of a novel Information-Centric Smart City architecture (iSmart), focusing on the demand of …

[Accepted Article Manuscript Version (Postprint)] Identification And Parasocial Relationships With Characters From Star Wars: The Force Awakens., Alice Hall

Communication and Media Faculty Works

This study investigated identification and parasocial relationships (PSRs) with media characters by examining viewers’ responses to the movie Star Wars: The Force Awakens through an online survey of 113 audience members who saw the film in a theater within a month of its release. Participants reported stronger PSR and identification with the more familiar characters from the first trilogy than with the new characters introduced in the film, although the association with identification was limited to older participants. Star Wars fanship was associated with identification and PSR for old and new characters. Familiarity with the earlier films was associated with …

Knowledge-Enabled Entity Extraction, Hussein S. Al-Olimat

Browse all Theses and Dissertations

Information Extraction (IE) techniques are developed to extract entities, relationships, and other detailed information from unstructured text. The majority of the methods in the literature focus on designing supervised machine learning techniques, which are not very practical due to the high cost of obtaining annotations and the difficulty in creating high quality (in terms of reliability and coverage) gold standard. Therefore, semi-supervised and distantly-supervised techniques are getting more traction lately to overcome some of the challenges, such as bootstrapping the learning quickly. This dissertation focuses on information extraction, and in particular entities, i.e., Named Entity Recognition (NER), from multiple domains, …

Artificial Intelligence: How Knowledge Is Created, Transferred, And Used, Jörg Hellwig Phd, Sarah Huggett, Mark Siebert, Bamini Jayabalasingham Phd

Public Reports

This document summarizes Key Findings from the full report "Artificial Intelligence: how knowledge is created, transferred, and used", available alongside other relevant material on the Elsevier Artificial Intelligence resource centre.The RELX group has extensive data assets, powerful computing capabilities, and a vast technological talent base. These allow Elsevier to provide unique insights on AI through this report. We hope these will be of interest to research evaluators, research funders, policy makers, and researchers, as they seek to navigate this complex, evolving, and fast-growing field.

A Systematic Review Of Blockchain Research And Applications In Business, Prinsa Roka

Undergraduate Honors Theses

Blockchain, well-known as the Distributed Ledger Technology (DLT) behind cryptocurrencies such as Bitcoin, has attracted plenty of attention from both practitioners and academics and has begun to revolutionize the way businesses handle their day-to-day operations. DLT leads to many interesting new research topics in different business fields. In this study, we applied the systematic mapping method to review existing articles related to blockchain applications and research in different business areas (accounting, finance and banking, information systems, marketing and supply chain). Our goal is to understand the current applications and research status related to blockchain, so that we can identify research …

Interactive And Accessible Pdfs, Quality Blended Learning Consortium

Open Educational Resources

This tutorial introduces the users to the fundamental concepts on how to create interactive and accessible PDFs, as well as provides guidance on the tools to be used, best practices, and mistakes to avoid. The tutorial includes quizzes for self-assessment.

An International Comparison Of K-12 Computer Science Education Intended And Enacted Curricula, Katrina Falkner, Sue Sentance, Rebecca Vivian, Sarah Barksdale, Leonard Busuttil, Elizabeth Cole, Christine Liebe, Francesco Maiorana, Monica M. Mcgill, Keith Quille

Conference Papers

This paper presents an international study of K-12 Computer Science implementation across Australia, England, Ireland, Italy, Malta, Scotland and the United States. We present findings from a pilot study, comparing CS curriculum requirements (intended curriculum) captured through country reports, with what surveyed teachers (n=244) identify as enacting in their classroom (the enacted curriculum). We address the extent that teachers are implementing the intended curriculum as enacted curriculum, exploring specifically country differences in terms of programming languages and CS topics implemented. Our findings highlight the similarities and differences of intended and enacted CS curriculum within and across countries and the value …

An International Benchmark Study Of K-12 Computer Science Education In Schools, Katrina Falkner, Sue Sentance, Rebecca Vivian, Sarah Barksdale, Leonard Busuttil, Elizabeth Cole, Christine Liebe, Francesco Maiorana, Monica M. Mcgill, Keith Quille

Conference Papers

There has been a growing interest and increase in work shared about national K-12 Computer Science Education (CSED) curriculum and implementation efforts around the world. Much of this work focuses on curriculum analysis, country reports, experience reports and case studies. The K-12 CSED community would benefit from an international strategic effort to compare, contrast and monitor K-12 CSED over time, across multiple countries and regions, to understand pedagogy, practice, resources and experiences from the perspective of teachers working in classrooms. Furthermore, there is a need for validated and robust instruments that can support comparable investigations into the current state of …

Multi-Person Tracking By Multi-Scale Detection In Basketball Scenarios, Adria Arbués-Sanguesa, Gloria Haro, Coloma Ballester

Session 1: Active Vision, Tracking, Motion Analysis

Tracking data is a powerful tool for basketball teams in order to extract advanced semantic information and statistics that might lead to a performance boost. However, multi-person tracking is a challenging task to solve in single-camera video sequences, given the frequent occlusions and cluttering that occur in a restricted scenario. In this paper, a novel multi-scale detection method is presented, which is later used to extract geometric and content features, resulting in a multi-person video tracking system. Having built a dataset from scratch together with its ground truth (more than 10k bounding boxes), standard metrics are evaluated, obtaining notable results …

Untapped Potential Of Clinical Text For Opioid Surveillance, Amy L. Olex, Tamas Gal, Majid Afshar, Dmitriy Dligach, Niranjan Karnik, Travis Oakes, Brihat Sharma, Meng Xie, Bridget T. Mcinnes, Julian Solway, Abel Kho, William Cramer, F. Gerard Moeller

Wright Center for Clinical and Translational Research Works

Accurate surveillance is needed to combat the growing opioid epidemic. To investigate the potential volume of missed opioid overdoses, we compare overdose encounters identified by ICD-10-CM codes and an NLP pipeline from two different medical systems. Our results show that the NLP pipeline identified a larger percentage of OOD encounters than ICD-10-CM codes. Thus, incorporating sophisticated NLP techniques into current diagnostic methods has the potential to improve surveillance on the incidence of opioid overdoses.

The Ethics Of An Unlicensed Medical Practitioner, Charles C. Escott

Writing Across the Curriculum

For option A of this assignment, the prompt is that Harry, a manufacturer of medical equipment and an avid reader of medical textbooks, has developed a program that will allow its users to self-diagnose and self-treat their ailments, without a doctor’s help. Harry wants to sell his program to “ordinary folk” as a replacement for consulting licensed medical practitioners. An important point here is that Harry is not licensed to practice medicine and has only read books on the subject. The posed question is whether or not his program should be published (from an ethical standpoint—not necessarily a profit-driven one). …

Automatic Identification Of Individual Drugs In Death Certificates, Soon Jye Kho, Amit Sheth, Olivier Bodenreider

Kno.e.sis Publications

Background:

Establishing trends of drug overdoses requires the identification of individual drugs in death certificates, not supported by coding with the International Classification of Diseases. However, identifying drug mentions from the literal portion of death certificates remains challenging due to the variability of drug names.

Objectives:

To automatically identify individual drugs in death certificates.

Methods:

We use RxNorm to collect variants for drug names (generic names, synonyms, brand names) and we algorithmically generate common misspellings. We use this automatically compiled list to identify drug mentions from 703,106 death certificates and compare the performance of our automated approach to that of …

Made Simple With Sivvu, Esther Cha, Douglas A. Vander Griend

Summer Research

To further the advancement of science, newer and better ways to regulate as well as optimize complex systems are continuously sought after. The previous efforts of this project have demonstrated the ability of characterizing selfassembling supramolecular systems in astounding detail. Although these systems were initially designed with a single chemical target, this project has allowed discovery of how homogenous solutions always contain additional assemblages. In this project, different systems are studied with UV-Vis, CD, NMR, and Mass Spec. The necessary methods that are used to conduct this research include analysis of spectrophotometric titrations as well as the utilization of computational …

Radically Simplifying Gated Recurrent Architectures Without Loss Of Performance, Jonathan Boardman, Ying Xie

Published and Grey Literature from PhD Candidates

Long Short-Term Memory (LSTM) units are a family of Recurrent Neural Network (RNN) architectures that have proven incredibly effective at learning from sequence data. They are also extremely complex, making them expensive to train and difficult to understand. A recent trend towards simplification has produced the Gated Recurrent Unit (GRU) and the Minimal Gated Unit (MGU), both of which perform as well as the LSTM (or better) on a variety of tasks. The MGU is one of the simplest gated recurrent architectures at the moment. Our study demonstrates that it is possible to radically simplify the MGU without significant loss …

Squared Distance Matrix Of A Weighted Tree, Ravindra B. Bapat

Journal Articles

Let T be a tree with vertex set f1;: :: ; ng such that each edge is assigned a nonzero weight. The squared distance matrix of T; denoted by is the n n matrix with (i; j)-element d(i; j)2; where d(i; j) is the sum of the weights of the edges on the (ij)-path. We obtain a formula for the determinant of A formula for 1 is also obtained, under certain conditions. The results generalize known formulas for the unweighted case.

General Game Playing As A Bandit-Arms Problem: A Multiagent Monte-Carlo Solution Exploiting Nash Equilibria, Brandon Mathewe Banda

Honors Papers

This project approaches general game playing in a unique way by combining popular methods of stochastic tree searching with a Multiagent system and a unique algorithm that I call the Wise Explorer algorithm. The goal of the system is to explore the worst possible branches of the game first to rule them out, followed by an in-depth search on the most promising branches. The system constantly refers to the data it collects during its extensive search, and it outputs a strategic move for any given state of a game. In essence, if you’re ever in a bind during a game …

Programming Safety Tips: Why You Should Use Immutable Objects Or How To Create Programs With Bugs That Can Never Be Found Or Fixed., Charles W. Kann

Programming Tips and Tricks

Program safety deals with how to make programs as error free as possible. The hardest errors in a program for a programmer to find are often errors in using memory. There are two reasons for this. The first is that errors in accessing memory almost never show problems in the proximate area of the program where the error is made. The error has no apparent impact when it is made, but often causes catastrophic results to occur much later in the program, in areas of the program unrelated to memory error that caused it.

The second reason memory errors are …

Visual Entailment Task For Visually-Grounded Language Learning, Ning Xie, Farley Lai, Derek Doran, Asim Kadav

Computer Science and Engineering Faculty Publications

We introduce a new inference task - Visual Entailment (VE) - which differs from traditional Textual Entailment (TE) tasks whereby a premise is defined by an image, rather than a natural language sentence as in TE tasks. A novel dataset SNLI-VE (publicly available at https://github.com/necla-ml/SNLI-VE) is proposed for VE tasks based on the Stanford Natural Language Inference corpus and Flickr30k. We introduce a differentiable architecture called the Explainable Visual Entailment model (EVE) to tackle the VE problem. EVE and several other state-of-the-art visual question answering (VQA) based models are evaluated on the SNLI-VE dataset, facilitating grounded language understanding and providing …

Physics's Need For Interval Uncertainty And How It Explains Why Physical Space Is (At Least) 3-Dimensional, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

One of the fundamental problems of modern physics is the problem of divergence: e.g., when we try to compute the overall energy of the electric field generated by a charged elementary particle, we get a physically meaningless infinite value. In this paper, we show that one way to avoid these infinities is to take into account that measurements are always imprecise -- and thus, we never get the exact values of the physical quantities, only intervals of possible values. We also show that 3-dimensional space is the simplest one in which such interval uncertainty is inevitable. This may explain why …

Probabilistic Record Linkage With Elliptic Curve Operations, Shreya Dhiren Patel

Electronic Theses and Dissertations

Federated query processing for an electronic health record infrastructure enables large epidemiology studies using data integrated from geographically dispersed medical institutions. However, government imposed privacy regulations prohibit disclosure of patient's health record outside the context of clinical care, thereby making it difficult to determine which records correspond to the same entity in the process of query aggregation.

Privacy-preserving record linkage is an actively pursued research area to facilitate the linkage of database records under the constraints of regulations that do not allow the linkage agents to learn sensitive identities of record owners. In earlier works, scalability has been shown to …

Kidled: A Colorful Approach To Children's Activity Awareness, Ankita Samariya, Anud Sharma, Margiawan Fitriani, Tucker Ferguson, Jerry Alan Fails

Computer Science Faculty Publications and Presentations

Obesity in children is a growing cause of concern as it affects more than 18% of children in the United States. Sedentary behaviour is one of the contributors to childhood obesity. Technological interventions like activity trackers and fitness games have been introduced to motivate both children and adults to be physically active. Most of these technologies encourage activity by making them aware of their activity levels. While awareness of current activity levels may help motivating adults, it can be difficult for children to understand their activity levels in terms of number of steps (the most common method used by adults). …

Investigating The Social And Temporal Aspects Of Children’S Physical Activity Games, Ankita Samariya, Jerry Alan Fails, Derek Hansen

Computer Science Faculty Publications and Presentations

There are a variety of fitness technologies such as activity trackers, exergames and mobile applications available to promote physical activity. Based on our previous research, we found that children prefer having social interaction, a narrative and flexibility while interacting with such technologies. Other research has shown that persuasive displays encouraged adults towards physical activity. In this research, we present the initial results from a user study conducted on 16 children (ages 6-11) who used the Kidfit suite, a collection of mobile applications that combine and utilize the elements found from previous research to promote activity in children.

Predicting Human Interpretations Of Affect And Valence In A Social Robot, David Mcneill, Casey Kennington

Computer Science Faculty Publications and Presentations

In this paper we seek to understand how people interpret a social robot’s performance of an emotion, what we term ‘affective display,’ and the positive or negative valence of that affect. To this end, we tasked annotators with observing the Anki Cozmo robot perform its over 900 pre-scripted behaviors and labeling those behaviors with 16 possible affective display labels (e.g., interest, boredom, disgust, etc.). In our first experiment, we trained a neural network to predict annotated labels given multimodal information about the robot’s movement, face, and audio. The results suggest that pairing affects to predict the valence between them is …

Ua66/15/1 Ogden College Of Science & Engineering Mathematics & Computer Science Events, Wku Archives

WKU Archives Collection Inventories

Records related to events hosted by Mathematics & Computer Science.

Ua66/3 Ogden College Of Science & Engineering Computer Science, Wku Archives

WKU Archives Collection Inventories

Records created by and about the Department of Computer Science.

Files are arranged in the following subseries:

1. Administration
2. Publications
3. Student Organizations

Introductory R For Water Resources - Fall 2019 - University Of North Carolina At Chapel Hill, David Gorelick, Gregory Characklis

All ECSTATIC Materials

This is all course material for R for Researchers, a one-credit course taught at UNC Chapel Hill in Fall 2019 to introduce upperclassmen and graduate students to the R programming language and apply learned skills in basic water resources applications, as well as other (semi-related) topics of interest to students.

Lecture notes were distributed before (as a subset of full lecture notes) and after lectures, and lectures involved collaborative coding exercises with students in class without any powerpoint material. Course material here includes:

Syllabus: rough schedule and description of lectures

Lectures: pdf lecture notes with embedded code, including …

Parameter Estimation Of Stochastic Models Against Probabilistic Temporal Logic Behavioral Specifications, Arfeen Khalid

Electronic Theses and Dissertations

The inherent behavioral variability exhibited by stochastic systems makes it a challenging task for human experts to manually analyze them. Computational modeling of such systems helps in investigating and predicting the behaviors of their underlying processes but at the same time introduces the presence of several unknown parameters. A key challenge faced in this scenario is to determine the values of these unknown parameters against known behavioral specifications. The solutions that have been presented so far estimate the parameters of a given model against a single specification whereas a correct model is expected to satisfy all the behavioral specifications when …