Computer Sciences Commons^™

Fusion-Net: Integration Of Dimension Reduction And Deep Learning Neural Network For Image Classification, Mohammad Masum, Philippe Laval

Published and Grey Literature from PhD Candidates

Building a deep network using original digital images requires learning many parameters which may reduce the accuracy rates. The images can be compressed by using dimension reduction methods and extracted reduced features can be feeding into a deep network for classification. Hence, in the training phase of the network, the number of parameters will be decreased. Principal Component Analysis is a well-known dimension reduction technique that leverage orthogonal linear transformation of the original data. In this paper, we propose a neural network-based framework, named Fusion-Net, which implements PCA on an image dataset (CIFAR-10) and then a neural network applies on …

Strategies To Mitigate The Effects Of Identity Theft In The Hospitality Industry, Patricia Lee Jirsa

Walden Dissertations and Doctoral Studies

Leaders in the U.S. hospitality industry experience significant losses in profitability, increased mitigation cost, and reduced revenues because of business and consumer identity theft. Grounded in the fraud triangle theory and the fraud diamond theory, the purpose of this qualitative multiple-case study was to explore strategies leaders in the hospitality industry use to mitigate identity theft. A purposeful sample of 5 leaders of 5 different hospitality businesses in Montana participated in the study. Data were collected through semistructured interviews, member checking, and a review of company documents. During data analysis using Yin’s 5-step process, 3 key themes emerged: a new …

Finalcache: Eviction Based On Implicit Entry Reachability, Adrian Veliz

Open Access Theses & Dissertations

Software caches for garbage collected systems are unaware which cache entries are referenced by a client program. Lacking this key information, software caches cannot determine the cache’s contribution to the program’s memory footprint. Furthermore, their eviction heuristics must rely on access history as a proxy for usage. Divergence between usage and access history can undermine the intention of eviction thereby resulting in problematic cache behavior.

This dissertation proposes designs for a novel family of “usage-based” software cache informed of entry reachability by the automatic memory management system. Unlike extant software caches, usage-based caches can accurately determine their memory footprint because …

Towards Making Videos Accessible For Low Vision Screen Magnifier Users, Ali Selman Aydin, Shirin Feiz, Vikas Ashok, Iv Ramakrishnan

Computer Science Faculty Publications

People with low vision who use screen magnifiers to interact with computing devices find it very challenging to interact with dynamically changing digital content such as videos, since they do not have the luxury of time to manually move, i.e., pan the magnifier lens to different regions of interest (ROIs) or zoom into these ROIs before the content changes across frames.

In this paper, we present SViM, a first of its kind screen-magnifier interface for such users that leverages advances in computer vision, particularly video saliency models, to identify salient ROIs in videos. SViM's interface allows users to zoom in/out …

Search Results: Predicting Ranking Algorithms With User Ratings And User-Driven Data, Gary Michael Taylor

Walden Dissertations and Doctoral Studies

The purpose of this correlational quantitative study was to examine the possible relationship between user-driven parameters, user ratings, and ranking algorithms. The study’s population consisted of students and faculty in the information technology (IT) field at a university in Huntington, WV. Arrow’s impossibility theorem was used as the theoretical framework for this study. Complete survey data were collected from 47 students and faculty members in the IT field, and a multiple regression analysis was used to measure the correlations between the variables. The model was able to explain 85% of the total variability in the ranking algorithm. The overall model …

Using Prosody To Spot Location Mentions, Gerardo Cervantes

Open Access Theses & Dissertations

Identifying location mentions in speech is important for many information retrieval and information extraction tasks; here I explore the use of prosody for location spotting. While previous work has explored the use of prosody for spotting named entities, including locations, the specific value of prosody for finding locations in spontaneous speech has not been measured. Using the Switchboard corpus and LSTM modeling I obtain results indicating that prosody is useful in spotting location mentions. Further, I identify specific prosodic

features that tend to mark locations in American English.

Compound Vision Approach For Autonomous Vehicles Navigation, Michael Mikhael

Open Access Theses & Dissertations

An analogy can be made between the sensing that occurs in simple robots and drones and that in insects and crustaceans, especially in basic navigation requirements. Thus, an approach in robots/drones based on compound eye vision could be useful. In this research, several image processing algorithms were used to detect and track moving objects starting with images upon which a grid (compound eye image) was superimposed, including contours detection, the second moments of those contours along with the grid applied to the original image, and Fourier Transforms and inverse Fourier Transforms. The latter also provide information about scene or camera …

Autonomous Trading Strategies For Dynamic Energy Markets, Moinul Morshed Porag Chowdhury

Open Access Theses & Dissertations

With increasing energy demand and an intermittent supply of renewable energy sources, our current energy grid needs a transformation towards a more robust, reliable energy trading architecture. The smart grid promises this architecture as the future of the present energy market, where traders will use digital technologies to automate the management of power delivery. It will improve many issues of the current energy grid such as sustainable, clean, renewable, reliable and secure energy supply, customer participation in markets, distributed generation, and transparency in energy trading. Using autonomous trading agents, we can bridge several dynamic energy markets and ensure an efficient …

Glacier Segmentation In Satellite Images For Hindu Kush Himalaya Region, Bibek Aryal

Open Access Theses & Dissertations

Climate change poses a risk to individuals whose livelihoods depend on the health of glacier ecosystems. Monitoring glaciers in the Himalayan Hindu Kush (HKH) region is of high importance especially when we consider the impact of recent climate change on them. Our work aims to provide an automated method to outline glaciers using machine learning techniques and publicly available remote sensing imagery.In this work, we present ways to delineate glaciers from Landsat-7 imagery using various machine learning and computer vision techniques. The multi-step methodology that we present in this work is generalizable across different types of satellite and overhead imagery, …

“Sorry I Didn’T Hear You.” The Ethics Of Voice Computing And Ai In High Risk Mental Health Populations, Fazal Khan, Christopher Villongco

Scholarly Works

This article examines the ethical and policy implications of using voice computing and artificial intelligence to screen for mental health conditions in low income and minority populations. Mental health is unequally distributed among these groups, which is further exacerbated by increased barriers to psychiatric care. Advancements in voice computing and artificial intelligence promise increased screening and more sensitive diagnostic assessments. Machine learning algorithms have the capacity to identify vocal features that can screen those with depression. However, in order to screen for mental health pathology, computer algorithms must first be able to account for the fundamental differences in vocal characteristics …

Real-Time Urban Weather Observations For Urban Air Mobility, Kevin A. Adkins, Mustafa Akbas, Marc Compere

International Journal of Aviation, Aeronautics, and Aerospace

Cities of the future will have to overcome congestion, air pollution and increasing infrastructure cost while moving more people and goods smoothly, efficiently and in an eco-friendly manner. Urban air mobility (UAM) is expected to be an integral component of achieving this new type of city. This is a new environment for sustained aviation operations. The heterogeneity of the urban fabric and the roughness elements within it create a unique environment where flight conditions can change frequently across very short distances. UAM vehicles with their lower mass, more limited thrust and slower speeds are especially sensitive to these conditions. Since …

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 …

Predicting Drug Misuse Status Using Machine Learning On Electronic Health Records, Robert Arnold Kania

Master's Theses

Substance misuse is a major problem in the world. in 2014, as many as 52,404 deaths in the US were caused by drug overdoses. in 2001, the monetary cost of drug misuse has been estimated to be 414 billion dollars. in this work, we explore the use of different machine learning algorithms in the prediction of cocaine misuse using structured and unstructured data found in electronic health records. These records contain various attributes that can help with this prediction, including but not limited to chart text data, previous diagnoses of certain diseases and information about the area the patient lives …

Wayfinder Application For Autistic Occupational Assistance, Nathaniel Edward Hishon

Master's Theses

Employment among autistic individuals is an area of noted difficulty, with an employment rate well below the general population [1]. Several barriers attributed to autistic unemployment, including difficulties communicating with employers and social interactions with coworkers, obsessive adherence to routine, and trouble organizing and completing workplace tasks, are also attributed to challenges in maintaining employment [2]. Several studies have concluded that long-term employment support is necessary to acquire and maintain autistic employment [3]. The noted benefit of intensive job training, such as access to job coaches, indicates the need for further support to help autistic individuals complete workplace tasks and …

A Mathematical Analysis Of The Game Of Santorini, Carson Clyde Geissler

Senior Independent Study Theses

Santorini is a two player combinatorial board game. Santorini bears resemblance to the graph theory game of Geography, a game of moving and deleting vertices on a graph. We explore Santorini with game theory, complexity theory, and artificial intelligence. We present David Lichtenstein’s proof that Geography is PSPACE-hard and adapt the proof for generalized forms of Santorini. Last, we discuss the development of an AI built for a software implementation of Santorini and present a number of improvements to that AI.

Cheat Detection Using Machine Learning Within Counter-Strike: Global Offensive, Harry Dunham

Senior Independent Study Theses

Deep learning is becoming a steadfast means of solving complex problems that do not have a single concrete or simple solution. One complex problem that fits this description and that has also begun to appear at the forefront of society is cheating, specifically within video games. Therefore, this paper presents a means of developing a deep learning framework that successfully identifies cheaters within the video game CounterStrike: Global Offensive. This approach yields predictive accuracy metrics that range between 80-90% depending on the exact neural network architecture that is employed. This approach is easily scalable and applicable to all types of …

Computer Vision Gesture Recognition For Rock Paper Scissors, Nicholas Hunter

Senior Independent Study Theses

This project implements a human versus computer game of rock-paper-scissors using machine learning and computer vision. Player’s hand gestures are detected using single images with the YOLOv3 object detection system. This provides a generalized detection method which can recognize player moves without the need for a special background or lighting setup. Additionally, past moves are examined in context to predict the most probable next move of the system’s opponent. In this way, the system achieves higher win rates against human opponents than by using a purely random strategy.

Virtual Reality Environment Recreation, Ryan Douglas

Williams Honors College, Honors Research Projects

This project will consist of a virtual reality based program that is capable of showing the user both the modern day state of a site of historic or archaeological significance, along with a recreation of what said site or area may have looked like in the past, primarily during the time that gave the site its historical significance. The virtual reality program itself is to be run on modern day Windows hardware and used with the VIVE virtual reality head-mounted display and controllers. Alongside the completed program, the creation of the environments themselves will be documented, resulting in an organized …

Developing A Uas-Deployable Methane Sensor Using Low-Cost Modular Open-Source Components, Gavin Demali

Williams Honors College, Honors Research Projects

This project aimed to develop a methane sensor for deployment on an unmanned aerial system (UAS), or drone, platform. This design is centered around low cost, commercially available modular hardware components and open source software libraries. Once successfully developed, this system was deployed at the Bath Nature Preserve in Bath Township, Summit County Ohio in order to detect any potential on site fugitive methane emissions in the vicinity of the oil and gas infrastructure present. The deliverables of this project (i.e. the data collected at BNP) will be given to the land managers there to better inform future management and …

Budget Remote Access Vpn & Nas, Dylan J. Simmons

Williams Honors College, Honors Research Projects

In the modern business environment, many companies use a VPN service, in order to allow employees to work from home, while maintaining a secure connection to the network and blocking out any hackers. The main goal of this project is to create a VPN service into a secured network and allow the users to access their folders on the network drive. However, smaller businesses can't afford to spend a fortune on these necessities. For this reason, this project will utilize open source, or free software and firmware that any company would be able to run, no matter the budget. By …

Telecommunications Database, Tristan Hess

Williams Honors College, Honors Research Projects

The final goal of this project was to create a web application that is specifically tailored to make management of data for the Telecommunications department easier. The software that the department uses for phone service generates monthly reports that cannot be stored into their current database system. The Telecommunications Database project is a four-tier web application that was developed to store the monthly report information and alleviate the burden of manually searching through the reports for information. The web application implements basic database functionality for searching, inserting, updating, and deleting data contained in the monthly reports. Advanced searching functionality and …

Invariance And Invertibility In Deep Neural Networks, Han Zhang

Theses and Dissertations

Machine learning is concerned with computer systems that learn from data instead of being explicitly programmed to solve a particular task. One of the main approaches behind recent advances in machine learning involves neural networks with a large number of layers, often referred to as deep learning. In this dissertation, we study how to equip deep neural networks with two useful properties: invariance and invertibility. The first part of our work is focused on constructing neural networks that are invariant to certain transformations in the input, that is, some outputs of the network stay the same even if the input …

Multi-Label Classification Models For Heterogeneous Data: An Ensemble-Based Approach., Jose Maria Moyano Murillo

Theses and Dissertations

In recent years, the multi-label classification gained attention of the scientific community given its ability to solve real-world problems where each instance of the dataset may be associated with several class labels simultaneously, such as multimedia categorization or medical problems.

The first objective of this dissertation is to perform a thorough review of the state-of-the-art ensembles of multi-label classifiers (EMLCs). Its aim is twofold: 1) study state-of-the-art ensembles of multi-label classifiers and categorize them proposing a novel taxonomy; and 2) perform an experimental study to give some tips and guidelines to select the method that perform the best according to …

Connectiveity And Structures Of Coloring Graphs, Xin Yutong

Honors Theses

Reconfiguration problems have been studied and applied to solve problems in various areas, including Math, Computer Science, and Chemistry. Due to the close relatedness between coloring graphs and reconfiguration problems, the connectivity and structure of coloring graphs give valuable information to a solution set of the corresponding reconfiguration problem. In this paper we will discuss 2--connectedness and cut-vertices of coloring graphs, and forbidden structures on a coloring graph wit cut-vertices.

Biasing Medial Axis Rapidly-Exploring Random Trees With Safe Hyperspheres, David Qin

Honors Theses

Motion planning is a challenging and widely researched problem in robotics. Motion planning algorithms aim to not only nd unobstructed paths, but also to construct paths with certain qualities, such as maximally avoiding obstacles to improve path safety. One such solution is a Rapidly-Exploring Random Tree (RRT) variant called Medial Axis RRT that generates the safest possible paths, but does so slowly. This paper introduces a RRT variant called Medial Axis Ball RRT (MABallRRT) that uses the concept of clearance -- a robot's distance from its nearest obstacle -- to efficiently construct a roadmap with safe paths. The safety of …

Fast Medial Axis Sampling For Use In Motion Planning, Hanglin Zhou

Honors Theses

Motion planning is a difficult but important problem in robotics. Research has tended toward approximations and randomized algorithms, like sampling-based planning. Probabilistic RoadMaps (PRMs) are one common sampling-based planning approach, but they lack safety guarantees. One main approach, Medial Axis PRM (MAPRM) addressed this deficiency by generating robot configurations as far away from the obstacles as possible, but it introduced an extensive computational burden. We present two techniques, Medial Axis Bridge and Medial Axis Spherical Step, to reduce the computational cost of sampling in MAPRM and additionally propose recycling previously computed clearance information to reduce the cost of connection in …

Computer-Assisted Coloring-Graph Generation And Structural Analysis, Wesley Su

Honors Theses

Graphs are a well studied construction in discrete math, with one of the most common areas of study being graph coloring. The graph coloring problem asks for a color to be assigned to each vertex in a graph such that no two adjacent vertices share a color. An assignment of k colors that meets these criteria is called a k-coloring. The coloring graph Ck(G) is defined as the graph where every vertex represents a valid k-coloring of graph G and edges exist between colorings that di↵er by one vertex. We call graph G the base graph of the k-coloring graph …

Cybersecurity Education Through Technological And Engineering Literacy Standards, Philip A. Reed, Steven A. Barbato

STEMPS Faculty Publications

No abstract provided.

Courcelle's Theorem: Overview And Applications, Samuel Frederic Barr

Honors Papers

Courcelle's Theorem states that any graph property expressible in monadic second order logic can be decidedin O(f(k)n) for graphs of treewidth k. This paper gives a broad overview of how this theorem is proved and outlines tools available to help express graph properties in monadic second order logic.

Data For The Review Of Gamified Fitness Tracker Apps, Aatish Neupane, Derek Hansen, Anud Sharma, Jerry Alan Fails

ScholarsArchive Data

This is a supplemental dataset to a paper that reviews 103 gamified fitness tracker apps and analyzes the presence and usage of various game elements. This dataset contains the list of those apps that were reviewed. It also contains the coding that represents the presence of difference game elements.