Computer Sciences Commons^™

Interpretable Machine Learning Model For Clinical Decision Making, Ali El-Sharif

CCAC Theses and Dissertations

Despite machine learning models being increasingly used in medical decision-making and meeting classification predictive accuracy standards, they remain untrusted black-boxes due to decision-makers' lack of insight into their complex logic. Therefore, it is necessary to develop interpretable machine learning models that will engender trust in the knowledge they generate and contribute to clinical decision-makers intention to adopt them in the field.

The goal of this dissertation was to systematically investigate the applicability of interpretable model-agnostic methods to explain predictions of black-box machine learning models for medical decision-making. As proof of concept, this study addressed the problem of predicting the risk …

Investigating The User Experience With A 3d Virtual Anatomy Application, Winnyanne Kunkle

CCAC Theses and Dissertations

Decreasing hours dedicated to teaching anatomy courses and declining use of human cadavers have spurred the need for innovative solutions in teaching anatomy in medical schools. Advancements in virtual reality (VR), 3D visualizations, computer graphics, and medical graphic images have enabled the development of highly interactive 3D virtual applications. Over recent years, variations of interactive systems on computer-mediated environments have been used as supplementary resource for learners. However, despite the growing sophistication of these resources for learning anatomy, studies show that students predominantly prefer traditional methods of learning and hands-on cadaver-based learning over computer-mediated platforms.

There is limited research on …

Development Of A Social Engineering Exposure Index (Sexi) Using Open-Source Personal Information, William Shawn Wilkerson

CCAC Theses and Dissertations

Millions of people willingly expose their lives via Internet technologies every day, and even the very few ones who refrain from the use of the Internet find themselves exposed through data breaches. Billions of private information records are exposed through the Internet. Marketers gather personal preferences to influence shopping behavior. Providers gather personal information to deliver enhanced services, and underground hacker networks contain repositories of immense data sets. Few users of Internet technologies have considered where their information is going or who has access to it. Even fewer are aware of how decisions made in their own lives expose significant …

Human Errors In Data Breaches: An Exploratory Configurational Analysis, Gabriel A. Cornejo

CCAC Theses and Dissertations

Information Systems (IS) are critical for employee productivity and organizational success. Data breaches are on the rise—with thousands of data breaches accounting for billions of records breached and annual global cybersecurity costs projected to reach $10.5 trillion by 2025. A data breach is the unauthorized disclosure of sensitive information—and can be achieved intentionally or unintentionally. Significant causes of data breaches are hacking and human error; in some estimates, human error accounted for about a quarter of all data breaches in 2018. Furthermore, the significance of human error on data breaches is largely underrepresented, as hackers often capitalize on organizational users’ …

A Study Of Factors That Influence Symbol Selection On Augmentative And Alternative Communication Devices For Individuals With Autism Spectrum Disorder, William Todd Dauterman

CCAC Theses and Dissertations

According to the American Academy of Pediatrics (AAP), 1 in 59 children are diagnosed with Autism Spectrum Disorder (ASD) each year. Given the complexity of ASD and how it is manifested in individuals, the execution of proper interventions is difficult. One major area of concern is how individuals with ASD who have limited communication skills are taught to communicate using Augmentative and Alternative Communication devices (AAC). AACs are portable electronic devices that facilitate communication by using audibles, signs, gestures, and picture symbols. Traditionally, Speech-Language Pathologists (SLPs) are the primary facilitators of AAC devices and help establish the language individuals with …

Identifying The Impact Of Perceived Shared Cultural Values On Knowledge Sharing Through A Social Media Application, Mel Anthony Tomeo

CCAC Theses and Dissertations

Knowledge sharing (KS) has been determined by many researchers as an important tool for problem-solving experiences and achieving success. Recent studies have explained KS as an activity in which knowledge is exchanged through individuals or between organizations. KS can help facilitate decision-making capabilities, stimulate cultural change, and create innovation. Through KS, individuals and organizations can capture explicit and tacit knowledge to save time and money. Previous studies have indicated a lack of research in how perceived shared cultural values impact KS through a social media application.

The purpose of this research was to add new information to the body of …

An Empirical Examination Of The Impact Of Organizational Injustice And Negative Affect On Attitude And Non-Compliance With Information Security Policy, Celestine Kemah

CCAC Theses and Dissertations

Employees’ non-compliance with Information Security (IS) policies is an important socio-organizational issue that represents a serious threat to the effective management of information security programs in organizations. Prior studies have demonstrated that information security policy (ISP) violation in the workplace is a common significant problem in organizations. Some of these studies have earmarked the importance of this problem by drawing upon cognitive processes to explain compliance with information security policies, while others have focused solely on factors related to non-compliance behavior, one of which is affect. Despite the findings from these studies, there is a dearth of extant literature that …

Feature Selection On Permissions, Intents And Apis For Android Malware Detection, Fred Guyton

CCAC Theses and Dissertations

Malicious applications pose an enormous security threat to mobile computing devices. Currently 85% of all smartphones run Android, Google’s open-source operating system, making that platform the primary threat vector for malware attacks. Android is a platform that hosts roughly 99% of known malware to date, and is the focus of most research efforts in mobile malware detection due to its open source nature. One of the main tools used in this effort is supervised machine learning. While a decade of work has made a lot of progress in detection accuracy, there is an obstacle that each stream of research is …

The Construction And Internal Validation Of A Model For The Effective Collaboration Of Distributed Agile Teams, Ernesto Custodio

CCAC Theses and Dissertations

Agile approaches to software development have increased steadily over the past decade. Agile processes emphasize iterative and collaborative discovery of requirements and solutions executed by self-organizing, cross-functional teams. Software development using distributed teams, including distributed sub-teams, fully dispersed teams, and partially dispersed teams, has also increased due to benefits such as access to global talent and faster delivery, among others.

However, most Agile approaches, models, and frameworks only address the needs of colocated teams. Distributed teams come with unique challenges when it comes to effective collaboration. The goal was to construct and validate internally a model for the effective collaboration …

Neural Network Variations For Time Series Forecasting, David Ason

CCAC Theses and Dissertations

Time series forecasting is an area of research within the discipline of machine learning. The ARIMA model is a well-known approach to this challenge. However, simple models such as ARIMA do not take into consideration complex relationships within the data and quite often fail to produce a satisfactory forecast. Neural networks have been presented in previous works as an alternative. Neural networks are able to capture non-linear relationships within the data and can deliver an improved forecast when compared to ARIMA models.

This dissertation takes neural network variations and applies them to a group of time series datasets found in …

Improving Employees’ Compliance With Password Policies, Enas Albataineh

CCAC Theses and Dissertations

Employees’ lack of compliance with password policies increases password susceptibility, which leads to financial damages to the organizations as a result of information disclosure, fraud, and unauthorized transactions. However, few studies have examined what motivates employees to comply with password policies.

The purpose of this quantitative cross-sectional study was to examine what factors influence employees’ compliance with password policies. A theoretical model was developed based on Protection Motivation Theory (PMT), General Deterrence Theory (GDT), Theory of Reasoned Action (TRA), and Psychological Ownership Theory to explain employees’ compliance with password policies.

A non-probability convenience sample was employed. The sample consisted of …

Enterprise Social Network Systems Implementation Model For Knowledge Sharing Among Supply Chain It Professionals, Edgardo Luis Velez-Mandes

CCAC Theses and Dissertations

With the increased use of social network technologies in organizational environments, there is a need to understand how these technologies facilitate organizational knowledge management, particularly knowledge sharing. Prior research has focused on the relationship between knowledge management and enterprise social networking systems (ESNS), but little research has been conducted relating to how organizations implement and use ESNS for knowledge sharing. The goal was to construct and validate internally a model that offers guidance for the successful implementation and use of ESNS for knowledge sharing and building successful virtual communities of practice (vCoPs) among IT supply chain professionals in a healthcare …

The Empirical Study Of The Factors That Influence Threat Avoidance Behavior In Ransomware Security Incidents, Heriberto Aurelio Acosta Maestre

CCAC Theses and Dissertations

Ransomware security incidents have become one of the biggest threats to general computer users who are oblivious to the ease of infection, severity, and cost of the damage it causes. University networks and their students are susceptible to ransomware security incidents. College students have vast technical skills and knowledge, however they risk ransomware security incidents because of their lack of mitigating actions to the threats and the belief that it would not happen to them. Interaction with peers may play a part in college students’ perception of the threats and behavior to secure their computers. Identifying what influences students’ threat …

An Empirical Examination Of The Computer Security Behaviors Of Telecommuters Working With Confidential Data Through Leveraging The Factors From Fear Appeals Model (Fam), Titus Dohnfon Fofung

CCAC Theses and Dissertations

Computer users’ security compliance behaviors can be better understood by devising an experimental study to examine how fear appeals might impact users’ security behavior. Telecommuter security behavior has become very relevant in information systems (IS) research with the growing number of individuals working from home. The increasing dependence on telecommuting to enhance the viability and convenience has created an urgency with the advent of the COVID-19 pandemic to examine the behavior of users working at home across a corporate network. The home networks are usually not as secure as those in corporate settings. There is seldom a firewall setting and …

Deep Neural Networks For Sentiment Analysis In Tweets With Emoticons, Mutharasu Narayanaperumal

CCAC Theses and Dissertations

Businesses glean meaningful feedback in regard to products and services from social media posts in order to improve the quality of products and services, as well as to meet customer expectations. Sentiment analysis is increasingly being used to help businesses by assigning positive or negative polarity to such posts. Although methods currently exist to determine the polarity of sentiments, such methods are unreliable when posts contain terms that are not typically part of a standard dictionary used for sentiment analysis, such as slang and informal language. This dissertation has aimed to empirically investigate alternative methods to improve the classification accuracy …

Identifying Physicians’ User Experience (Ux) Pain Points In Using Electronic Health Record (Ehr) Systems, Elizabeth Janelle Arceneaux

CCAC Theses and Dissertations

Healthcare institutions have migrated to online electronic documentation through the means of Electronic Health Record (EHR) systems. Physicians rely on these systems to support their various clinical work processes, such as entering clinical orders, reviewing essential clinical data, and making important medical decisions using reporting analytics. Although EHR systems appear to be useful and have known advantages over paper records, studies suggest there are persistent user interface design problems that may hinder physician productivity. The study focused on the research problem that EHR system designs create productivity problems for physician users who frequently report that system workflows are inefficient and …

A Covid-19 Induced Shift: From Introducing High School Females To Computing Careers To An Assessment Of Technological Readiness Among Stem Teachers, Jareau Almeyda

CCAC Theses and Dissertations

Prior to the global COVID-19 pandemic, this study aimed to explore how exposure to information systems (IS) project management impacts perceptions of computing careers among high school female participants. Given the demand for computing professionals continues to grow, enrollment in some computing disciplines across institutions of higher education have experienced declining enrollments. Studies have shown that one of the reasons high school students do not enroll in computing disciplines is because they perceive computing as difficult, boring, and irrelevant.

As a computing discipline, information systems is focused on developing professionals who are able to integrate technologies into systems that run …

Predictive Accuracy Of Recommender Algorithms, William Blake Noffsinger

CCAC Theses and Dissertations

Recommender systems present a customized list of items based upon user or item characteristics with the objective of reducing a large number of possible choices to a smaller ranked set most likely to appeal to the user. A variety of algorithms for recommender systems have been developed and refined including applications of deep learning neural networks. Recent research reports point to a need to perform carefully controlled experiments to gain insights about the relative accuracy of different recommender algorithms, because studies evaluating different methods have not used a common set of benchmark data sets, baseline models, and evaluation metrics. The …

An Investigation Of The Factors That Contribute To The Perceived Likelihood Of Compliance With The Hipaa Security Rule Among Healthcare Covered Entities And Business Associates, James Furstenberg

CCAC Theses and Dissertations

The Health Insurance Portability and Accountability Act (HIPAA) Security Rule (SR) mandate provides a national standard for the safeguard of electronically protected health information (ePHI). SR compliance enforcement efforts started in 2005; however, U.S.-based covered entities and business associates (CEs & BAs) remain challenged to comply with the HIPAA SR regulatory strategy. Although there is a significant volume of academic research on HIPAA compliance, research specific to the SR is sparse.

This study addressed the research gap by designing a unique conceptual model that assessed factors affecting CEs & BAs compliance (or non-compliance) with the SR regulatory strategy. The primary …

Organizational Culture And Knowledge Transfer In Enterprise Social Media, Garry Blackstock

CCAC Theses and Dissertations

Enterprise social media (ESM), digital platforms used within organizations to facilitate knowledge sharing and collaboration, are valuable tools that can help organizations gain a competitive advantage. Efficient retention, dissemination, and transfer of knowledge is an industry differentiator, and companies are spending a tremendous amount of resources on ESM to achieve this discriminating advantage. The behavior of transferring knowledge, especially tacit knowledge, can be a challenging task. Discordant organizational culture has been identified as a barrier to efficient knowledge transfer, whether it is explicit or tacit. Despite ESM’s positive track record of promoting communication, it lacks the efficiency to facilitate knowledge …

Sns Use, Risk, And Executive Behavior, Andrew Green

CCAC Theses and Dissertations

Andrew Green April 2020 Personal social networking sites (SNS) are popular outlets for people to share information about themselves, their family and friends, and their personal and professional lives. On the surface, the information shared may seem to be innocuous or nonthreatening. However, prior studies have shown that cybercriminals can take information shared via personal SNS and use it to conduct attacks against organizations. Organization executives are of particular interest to cybercriminals because they have access to sensitive data, and they also have the ability to command actions from their subordinates. The purpose of this study was to explore what …

Reducing Bittorrent Download Time Via Handshake-Based Switching, Elliotte Kim

CCAC Theses and Dissertations

Peer-to-peer networking overcomes the single point of failure and bandwidth limitations inherent to the centralized server model of file-sharing. It is both a popular means of sharing digital content and a major consumer of internet traffic, with BitTorrent being the most-used protocol. As such, significant research has gone into improving peer-to-peer performance in order to reduce both download times and networking costs. One aspect that can affect performance is the client’s selection of peers to download from, as the time spent downloading from even a single poor-performing peer can impact the overall download duration.

A recent peer selection strategy explored …

Examining The Creation Of Information Privacy Culture In Healthcare Organizations To Achieve Collective Hipaa Compliance Practice, Osborne Obeng

CCAC Theses and Dissertations

The digitization and transfer of patient records has increased the risk of patient data being improperly handled by healthcare organizations. In light of this growing concern, the United States government and state authorities have implemented various regulations to mitigate the privacy concerns. Beside privacy regulations, healthcare organizations have been forced by other pressures such as organization’s competitive pressures, resources, ethical responsibilities, and legitimacy to implement privacy safeguards. However, surveys show that healthcare organizations fail to achieve information privacy compliance. This study examined the creation of information privacy culture from the different occupational communities in healthcare organizations to help achieve information …

Smart Privacy For Iot: Privacy Embedded Design For Home Automation Systems, Love James

CCAC Theses and Dissertations

The emerging paradigm shift in technology to make everyday devices more intelligent than previously considered also known as internet of things (IoT) has further elevated the importance of privacy not only in theory but also in practice. The intrusive nature of these devices and in particular, the home automation system is also beginning to raise privacy concerns which might impact their usage either by deterring potential users from adopting the technology or discouraging existing users from the continued use of these home automation systems.

This study was an empirical and quantitative study that evaluates the impact of users’ behavior when …

Improvements To Iterated Local Search For Microaggregation, Tracy Bierman

CCAC Theses and Dissertations

Microaggregation is a disclosure control method that uses k-anonymity to protect confidentiality in microdata while seeking minimal information loss. The problem is NP-hard. Iterated local search for microaggregation (ILSM) is an effective metaheuristic algorithm that consistently identifies better quality solutions than extant microaggregation methods. The present work presents improvements to local search, the perturbation operations and acceptance criterion within ILSM.

The first, ILSMC, targets changed clusters within local search (LS) to avoid vast numbers of comparison tests, significantly reducing execution times. Second, a new probability distribution yields a better perturbation operator for most cases, significantly reducing the number of iterations …

An Empirical Assessment Of Audio/Visual/Haptic Alerts And Warnings To Mitigate Risk Of Phishing Susceptibility In Emails On Mobile Devices, Molly Marie Cooper

CCAC Theses and Dissertations

Phishing emails present a threat to both personal and organizational data. Phishing is a cyber-attack using social engineering. About 94% of cybersecurity incidents are due to phishing and/or social engineering. A significant volume of prior literature documented that users are continuing to click on phishing links in emails, even after phishing awareness training. It appears there is a strong need for creative ways to alert and warn users to signs of phishing in emails.

The main goal of the experiments in this study was to measure participants’ time for recognizing signs of phishing in emails, thus, reducing susceptibility to phishing …

Sns As An Educational Tool: Effect On Academic Performance And Learners’ Perceptions, Nawwaf Mohssen Altalhi

CCAC Theses and Dissertations

With Social Networking Sites (SNSs) being extensively used by students, there has been extensive research in relation to their ability to enhance students’ academic performance in various learning environments, although the advent of research on online learning is a recent development.

Studies regarding the use of SNSs indicated that there was a negative relationship between students’ use of SNSs and students’ academic performance. However, it is unknown whether the implementation of an instructional training course utilizing SNSs as an educational tool might lead to improvements in students’ academic performance. Many students have admitted to not knowing how to properly use …

A Hierarchical Temporal Memory Sequence Classifier For Streaming Data, Jeffrey Barnett

CCAC Theses and Dissertations

Real-world data streams often contain concept drift and noise. Additionally, it is often the case that due to their very nature, these real-world data streams also include temporal dependencies between data. Classifying data streams with one or more of these characteristics is exceptionally challenging. Classification of data within data streams is currently the primary focus of research efforts in many fields (i.e., intrusion detection, data mining, machine learning). Hierarchical Temporal Memory (HTM) is a type of sequence memory that exhibits some of the predictive and anomaly detection properties of the neocortex. HTM algorithms conduct training through exposure to a stream …

An Approach To Twitter Event Detection Using The Newsworthiness Metric, Jonathan Adkins

CCAC Theses and Dissertations

No abstract provided.

Detecting Rogue Manipulation Of Smart Home Device Settings, David Zeichick

CCAC Theses and Dissertations

Smart home devices control a home’s environmental and security settings. This includes devices that control home thermostats, sprinkler systems, light bulbs, and home appliances. Malicious manipulation of the settings of these devices by an outside adversary has caused emotional distress and could even cause physical harm. For example, researchers have reported that there is a rise in domestic abuse perpetrated via smart home devices; victims have reported their thermostat settings being unwittingly manipulated and being locked out of their house due to their smart lock code being changed. Rapid adoption of smart home devices by consumers has led to an …