Computer Sciences Commons^™

Deep Learning Detection In The Visible And Radio Spectrums, Greg Clancy Murray

Graduate Theses, Dissertations, and Problem Reports (ETD)

Deep learning models with convolutional neural networks are being used to solve some of the most difficult problems in computing today. Complicating factors to the use and development of deep learning models include lack of availability of large volumes of data, lack of problem specific samples, and the lack variations in the specific samples available. The costs to collect this data and to compute the models for the task of detection remains a inhibitory condition for all but the most well funded organizations. This thesis seeks to approach deep learning from a cost reduction and hybrid perspective — incorporating techniques …

Efficacy Of Reported Issue Times As A Means For Effort Estimation, Paul Phillip Maclean

Graduate Theses, Dissertations, and Problem Reports (ETD)

Software effort is a measure of manpower dedicated to developing and maintaining and software. Effort estimation can help project managers monitor their software, teams, and timelines. Conversely, improper effort estimation can result in budget overruns, delays, lost contracts, and accumulated Technical Debt (TD). Issue Tracking Systems (ITS) have become mainstream project management tools, with over 65,000 companies using Jira alone. ITS are an untapped resource for issue resolution effort research. Related work investigates issue effort for specific issue types, usually Bugs or similar. They model their developer-documented issue resolution times using features from the issues themselves. This thesis explores a …

Exploring Cyberterrorism, Topic Models And Social Networks Of Jihadists Dark Web Forums: A Computational Social Science Approach, Vivian Fiona Guetler

Graduate Theses, Dissertations, and Problem Reports (ETD)

This three-article dissertation focuses on cyber-related topics on terrorist groups, specifically Jihadists’ use of technology, the application of natural language processing, and social networks in analyzing text data derived from terrorists' Dark Web forums. The first article explores cybercrime and cyberterrorism. As technology progresses, it facilitates new forms of behavior, including tech-related crimes known as cybercrime and cyberterrorism. In this article, I provide an analysis of the problems of cybercrime and cyberterrorism within the field of criminology by reviewing existing literature focusing on (a) the issues in defining terrorism, cybercrime, and cyberterrorism, (b) ways that cybercriminals commit a crime in …

Application Of Artificial Intelligence For Co2 Storage In Saline Aquifer (Smart Proxy For Snap-Shot In Time), Marwan Mohammed Alnuaimi

Graduate Theses, Dissertations, and Problem Reports (ETD)

In recent years, artificial intelligence (AI) and machine learning (ML) technology have grown in popularity. Smart Proxy Models (SPM) are AI/ML based data-driven models which have proven to be quite crucial in petroleum engineering domain with abundant data, or operations in which large surface/ subsurface volume of data is generated. Climate change mitigation is one application of such technology to simulate and monitor CO2 injection into underground formations.

The goal of the SPM developed in this study is to replicate the results (in terms of pressure and saturation outputs) of the numerical reservoir simulation model (CMG) for CO2 injection into …

Generation Of High Performing Morph Datasets, Kelsey Lynn O'Haire

Graduate Theses, Dissertations, and Problem Reports (ETD)

Facial recognition systems play a vital role in our everyday lives. We rely on this technology from menial tasks to issues as vital as national security. While strides have been made over the past ten years to improve facial recognition systems, morphed face images are a viable threat to the reliability of these systems. Morphed images are generated by combining the face images of two subjects. The resulting morphed face shares the likeness of the contributing subjects, confusing both humans and face verification algorithms. This vulnerability has grave consequences for facial recognition systems used on international borders or for law …

Strategy: A Business And Cybersecurity Intertwined Necessity, Sharon L. Burton

Publications

Strategy development and application continue to shift. Evolving leadership with well-informed judgment relating to generating sound strategy within the realm of cybersecurity strengthening methods remains perplexing in this COVID-19 pandemic epoch. Investigated in this paper is the shaping of this context regarding the leadership position to study spats, procedures, and the way that this data clarifies the organization and outcomes of cybersecurity awareness, proficiency, know-how, practice, actions, purposes, harmonization, in addition to know-how immersion. This investigation’s documentation is geared toward the expansion of the context and semi-structured purposive sampling interview outcomes as this context is rationalized via the proper instrument …

Interpretable Machine Learning For Self-Service High-Risk Decision Making, Charles Recaido

All Master's Theses

This research contributes to interpretable machine learning via visual knowledge discovery in General Line Coordinates (GLC). The concepts of hyperblocks as interpretable dataset units and GLC are combined to create a visual self-service machine learning model. Two variants of GLC known as Dynamic Scaffold Coordinates (DSC) are proposed. DSC1 and DSC2 can map in a lossless manner multiple dataset attributes to a single two-dimensional (X, Y) Cartesian plane using a dynamic scaffolding graph construction algorithm.

Hyperblock analysis is used to determine visually appealing dataset attribute orders and to reduce line occlusion. It is shown that hyperblocks can generalize decision tree …

Morphologic Clustering Of Earcanals Using Deep Learning Algorithm To Design Artificial Ears Dedicated To Earplugs Attenuation Measurement, Bastien Poissenot-Arrigoni, Chun Hong Law, Djamal Berbiche, Franck Sgard, Olivier Doutres

Études primaires

Designing earplugs adapted for the widest number of earcanals requires acoustical test fixtures (ATFs) geometrically representative of the population. Most existing ATFs are equipped with unique sized straight cylindrical earcanals, considered representative of average human morphology, and are therefore unable to assess how earplugs can fit different earcanal morphologies. In this study, a methodology to cluster earcanals as a function of their morphologies with the objective of designing artificial ears dedicated to sound attenuation measurement is developed and applied to a sample of Canadian workers’ earcanals. The earcanal morphologic indicators that correlate with the attenuations of six models of commercial …

Application Of Artificial Intelligence And Machine Learning For Hiv Prevention Interventions, Yang Xiang, Jingcheng Du, Kayo Fujimoto, Fang Li, John Schneider, Cui Tao

Faculty, Staff and Student Publications

In 2019, the US Government announced its goal to end the HIV epidemic within 10 years, mirroring the initiatives set forth by UNAIDS. Public health prevention interventions are a crucial part of this ambitious goal. However, numerous challenges to this goal exist, including improving HIV awareness, increasing early HIV infection detection, ensuring rapid treatment, optimising resource distribution, and providing efficient prevention services for vulnerable populations. Artificial intelligence has had a pivotal role in revolutionising health care and has shown great potential in developing effective HIV prevention intervention strategies. Although artificial intelligence has been used in a few HIV prevention intervention …

Using Data Science Tools For Investigating Chat Logs From The Conti Ransomware Group, Boyan Kostadinov, Joseph Liu, Julio Rayme

Publications and Research

The main goal of this paper is to showcase some results from a comprehensive data analysis that we did on the cache of chat logs from the notorious ransomware group Conti. The chat logs were made publicly available on February 27, 2022. They were translated from Russian into English, and contain 393 json files with chat logs from the instant messaging service Jabber. We employ a variety of modern data science tools for text mining, natural language processing, network analysis and geospatial analysis to investigate the Conti chat logs so that we can understand the command and control structure of …

Editorial, Michael E. Whitman, Herbert J. Mattord, Hossain Shahriar

Journal of Cybersecurity Education, Research and Practice

Since 2016, it has been the mission of the Journal of Cybersecurity Education, Research, and Practice (JCERP) to be a premier outlet for high-quality information security and cybersecurity-related articles of interest to teaching faculty and students. This is the 13^th edition of the (JCERP) and, as ever, we are seeking authors who produce high-quality research and practice-oriented articles focused on the development and delivery of information security and cybersecurity curriculum, innovation in applied scholarship, and industry best practices in information security and cybersecurity in the enterprise for double-blind review and publication. The journal invites submissions on Information Security, Cybersecurity, …

Poor Man’S Trace Cache: A Variable Delay Slot Architecture, Tino C. Moore

Dissertations, Master's Theses and Master's Reports

We introduce a novel fetch architecture called Poor Man’s Trace Cache (PMTC). PMTC constructs taken-path instruction traces via instruction replication in static code and inserts them after unconditional direct and select conditional direct control transfer instructions. These traces extend to the end of the cache line. Since available space for trace insertion may vary by the position of the control transfer instruction within the line, we refer to these fetch slots as variable delay slots. This approach ensures traces are fetched along with the control transfer instruction that initiated the trace. Branch, jump and return instruction semantics as well as …

Novel Secure Outsourcing Of Modular Inversion For Arbitrary And Variable Modulus, Chengliang Tian, Jia Yu, Hanlin Zhang, Haiyang Xue, Cong Wang, Kui Ren

Research Collection School Of Computing and Information Systems

In cryptography and algorithmic number theory, modular inversion is viewed as one of the most common and time-consuming operations. It is hard to be directly accomplished on resource-constrained clients (e.g., mobile devices and IC cards) since modular inversion involves a great amount of operations on large numbers in practice. To address the above problem, this paper proposes a novel unimodular matrix transformation technique to realize secure outsourcing of modular inversion. This technique makes our algorithm achieve several amazing properties. First, to the best of our knowledge, it is the first secure outsourcing computation algorithm that supports arbitrary and variable modulus, …

Just-In-Time Defect Prediction On Javascript Projects: A Replication Study, Chao Ni, Xin Xia, David Lo, Xiaohu Yang, Ahmed E. Hassan

Research Collection School Of Computing and Information Systems

Change-level defect prediction is widely referred to as just-in-time (JIT) defect prediction since it identifies a defect-inducing change at the check-in time, and researchers have proposed many approaches based on the language-independent change-level features. These approaches can be divided into two types: supervised approaches and unsupervised approaches, and their effectiveness has been verified on Java or C++ projects. However, whether the language-independent change-level features can effectively identify the defects of JavaScript projects is still unknown. Additionally, many researches have confirmed that supervised approaches outperform unsupervised approaches on Java or C++ projects when considering inspection effort. However, whether supervised JIT defect …

Beyond Triplet Loss: Person Re-Identification With Fine-Grained Difference-Aware Pairwise Loss, Cheng Yan, Guansong Pang, Xiao Bai, Changhong Liu, Xin Ning, Jun Zhou

Research Collection School Of Computing and Information Systems

Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences …

Forecasting Bitcoin, Ethereum And Litecoin Prices Using Machine Learning, Sai Prabhu Jaligama

Graduate Research Theses & Dissertations

This research aims to predict the cryptocurrencies Bitcoin, Litecoin and Ethereum using Time Series Modelling with daily data of closing price from 16th of October 2018 to 9th of September 2021for a total of 1073 days. Augmented Dickey Fuller test was first used to check stationarity of the time series, then two forecasting algorithms called ARIMA, and PROPHET were used to make predictions. The findings show similar results for both the models for each of Bitcoin, Ethereum and Litecoin. The results achieved show modelling cryptocurrencies which are volatile using a single variable produces satisfying results.

Engagement Detection Using Prosodic Cues: An Approach For Measuring Child Emotional Engagement Level In Child-Robot Interaction Scenario, Mustafa Oztoprak

Graduate Research Theses & Dissertations

The ultimate goal of advanced child-robot interaction is to develop a high-level intelligencecommunication channel in a closed-loop configuration with the child as the focal point of the instructional scenario. This goal can be met by establishing efficient sensing mechanisms on the robot’s side, such as automatic engagement measuring, which will allow the robot to alter its behavior or even the instructional scenario’s execution.Recent researches, regarding engagement recognition systems mostly based on facial or multi-modal features.We would like to investigate this topic using prosodic cues only. We believe speech characteristics are more likely to be related to child speaker engagement level.This …

Monitoring Plants Growth In Indoor Vertical Farms Using Computer Vision And Ai Techniques, Bhama Krishna Pillutla

Graduate Research Theses & Dissertations

Climatic conditions like temperature, drought, and heavy metals disturb plant cell structures and, ultimately, plant growth that significantly affects crop production. Due to increasing climate change, maize crop yields are projected to decline by 24% by the end of century. With the increase in food demands and decrease in agricultural land and water resources, the space for effective farming is left much desired. Though limited to a few crops at this moment, Indoor Vertical Farming is one technique that requires much less land space, water, soil, and sunlight when compared to traditional farming. Vertical farming allows artificial control of temperature, …

Modeling And Visualization Of Long-Term Public Opinion On Covid-19 Vaccine, Ashiqur Rahman

Graduate Research Theses & Dissertations

The coronavirus pandemic created significant dependence on social media. While the social web was crucial in spreading timely information and informing the public, misinformation has also spread with little to no oversight. Several works have focused on identifying misinformation and topic analysis in COVID-19 (SARS-COV-2) tweets. While most of the previous studies focus on a shorter time frame, we analyzed a larger dataset starting from the beginning of the pandemic until the end of December 2021. Our work focuses on a novel area that identifies the motivating and demotivating topics of COVID-19 vaccination and analyzes these topics based on time, …

Covidalert - A Wristwatch-Based System To Alert Users From Face Touching, Mrinmoy Roy

Graduate Research Theses & Dissertations

Worldwide 219 million people have been infected and 4.5 million have lost their lives in ongoing Covid-19 pandemic. Until vaccines became widely available, precautions and safety measures like wearing masks, physical distancing, avoiding face touching were some of the primary means to curb the spread of virus. Face touching is a compulsive human behavior that can not be prevented without constantly making a conscious effort, even then it is inevitable. To address this problem, we have designed a smartwatch-based solution, CovidAlert, that leverages Random Forest algorithm trained on accelerometer and gyroscope data from the smartwatch to detect hand transition to …

Modeling The Broader Impact Of Science And Health Using Social Media, Abdul Rahman Shaikh

Graduate Research Theses & Dissertations

Research and development have always initiated innovation and breakthroughs in technology. These technological advancements in recent years have provided a global medium for research to be disseminated through online platforms. These web-based platforms and the interactions that take place on them affect the dissemination, impact, and perception of online information. This thesis investigates the broader impact of science and health using social media posts, online patents, videos, and images by building machine learning and topic models. First, this study predicts patent citations to scientific research and identifies important factors essential to economic impact. We found that the citation of research …

Digital Forensics For Mobility As A Service Platform: Analysis Of Uber Application On Iphone And Cloud, Nina Matulis, Umit Karabiyik

Annual ADFSL Conference on Digital Forensics, Security and Law

Uber is a ride-hailing smartphone application (app) that allows users to order a ride in a highly efficient manner. The Uber app provides Mobility as a Service and allows users to easily order a ride in a private car with just a few clicks. Uber stores large amounts of data on both the mobile device the app is being used on, and in the cloud. Examples of this data include geolocation data, date/time, origin/destination addresses, departure/arrival times, and distance. Uber geolocation data has been previously researched to investigate the privacy of the Uber app; however, there is minimal research relating …

Smart Home Forensics: Identifying Ddos Attack Patterns On Iot Devices, Samuel Ho, Hope Greeson, Umit Karabiyik

Annual ADFSL Conference on Digital Forensics, Security and Law

Smart homes are becoming more common as more people integrate IoT devices into their home environment. As such, these devices have access to personal data on their homeowners’ networks. One of the advantages of IoT devices is that they are compact. However, this limits the incorporation of security measures in their hardware. Misconfigured IoT devices are commonly the target of malicious attacks. Additionally, distributed denial-of-service attacks are becoming more common due to applications and software that provides users with easy-to-use user interfaces. Since one vulnerable device is all an attacker needs to launch an attack on a network, in regards …

Developing A Virtual Modular Synthesizer For Sound Waves And Midi, Margaret Jagger

Senior Independent Study Theses

Modular synthesis involves the alteration and modification of digital sound signals. Thus, this modular synthesizer allows a user the option of supplying their own MIDI-compatible controller to serve as an input source, or to use the built-in pure sound waves instead. Either input will be fed into the domain-specific language SuperCollider and altered, with specific sound modifications dependent on the input source used. Using theoretical knowledge of the physics behind the motion of sound waves, various modules and functionalities are created. Then, with SuperCollider, these modules are implemented into a synthesizer which accepts either pure sound waves or MIDI as …

Randomness Distillation To Improve Key Quality For Context-Based Authentication Schemes, Jackson West

Master's Theses

Context-based authentication is a method for transparently validating another device’slegitimacy to join a network based on location. Devices can pair with one another by continuously harvesting environmental noise to generate a random key with no user involvement. However, there are gaps in our understanding of the theoretical limitations of environmental noise harvesting, making it difficult for researchers to build efficient algorithms for sampling environmental noise and distilling keys from that noise. This work explores the information-theoretic capacity of context-based authentication mechanisms to generate random bit strings from environmental noise sources with known properties. Using only mild assumptions about the source …

Sensitivity Of Lidar Derived Fuel Cells To Fire Modeling At Laboratory Scale, Anthony Albert Marcozzi

Graduate Student Theses, Dissertations, & Professional Papers

Computational models of wildfires are an important tool for fire managers and scientists. However, fuel inputs to wildfire models can be difficult to represent with sufficient detail to be both computationally efficient and representative of observations. Recent advances in fuel mapping with airborne and terrestrial laser scanning (LIDAR) techniques present new opportunities to capture variation in fuels within a tree canopy and on a landscape. In this paper, we develop a technique for building 3D representations of vegetation from point clouds created by Terrestrial Laser Scans (TLS). Our voxel based approach can be extended to represent heterogeneous crown fuels as …

Lasso: Listing All Subset Sums Obediently For Evaluating Unbounded Subset Sums, Christopher N. Burgoyne, Travis J. Wheeler

Graduate Student Theses, Dissertations, & Professional Papers

In this study we present a novel algorithm, LASSO, for solving the unbounded and bounded subset sum problem. The LASSO algorithm was designed to solve the unbounded SSP quickly and to return all subsets summing to a target sum. As speed was the highest priority, we benchmarked the run time performance of LASSO against implementations of some common approaches to the bounded SSP, as well as the only comparable implementation for solving the unbounded SSP that we could find. In solving the bounded SSP, our algorithm had a significantly faster run time than the competing algorithms when the target sum …

A Non-Deterministic Deep Learning Based Surrogate For Ice Sheet Modeling, Hannah Jordan

Graduate Student Theses, Dissertations, & Professional Papers

Surrogate modeling is a new and expanding field in the world of deep learning, providing a computationally inexpensive way to approximate results from computationally demanding high-fidelity simulations. Ice sheet modeling is one of these computationally expensive models, the model used in this study currently requires between 10 and 20 minutes to complete one simulation. While this process is adequate for certain applications, the ability to use sampling approaches to perform statistical inference becomes infeasible. This issue can be overcome by using a surrogate model to approximate the ice sheet model, bringing the time to produce output down to a tenth …

Information Communication And Technology Strategies For Improving Nonprofit Organizations’ Effectiveness, Richard T. Evans

Walden Dissertations and Doctoral Studies

AbstractSome nonprofit organization leaders lack strategies to incorporate information communication and technology (ICT) into the business operations of organizations. A nonprofit organization lacking strategies involving integrating technology into their business operations decreases the likelihood of being efficient, productive, and effective. Grounded in the information technology (IT) competency model, the purpose of this qualitative single case study was to explore the ICT strategies of a nonprofit organization leader in the south suburbs of Chicago. Data were collected through semi-structured interviews, direct observations, and reviews of organizational documents. The Marshall and Rossman seven-step process was used to analyze data. Three themes emerged …

Exploring Critical Success Factors For Implementing It Modernization Systems In Michigan State Agencies, Luc Armand Kamdem

Walden Dissertations and Doctoral Studies

Since 2001, most government organizations’ IT modernization programs had failed because of ineffective implementation strategies from IT leaders. The research problem was the absence of effective strategies to modernize IT legacy systems. The purpose of this qualitative single case study was to explore effective IT modernization strategies to revolutionize IT legacy systems. The researcher sought to answer how organizations create effective strategies to modernize IT legacy systems. The study used purposeful sampling, including 13 IT leaders, IT technicians, and customers based on their experience in implementing successful IT modernization programs’ strategies. Data were collected using semi-structured interviews and agency documentation. …