Computer Sciences Commons^™

Predicting The Need For Cardiovascular Surgery: A Comparative Study Of Machine Learning Models, Arman Ghavidel, Pilar Pazos, Rolando Del Aguila Suarez, Alireza Atashi

Engineering Management & Systems Engineering Faculty Publications

This research examines the efficacy of ensemble Machine Learning (ML) models, mainly focusing on Deep Neural Networks (DNNs), in predicting the need for cardiovascular surgery, a critical aspect of clinical decision-making. It addresses key challenges such as class imbalance, which is pivotal in healthcare settings. The research involved a comprehensive comparison and evaluation of the performance of previously published ML methods against a new Deep Learning (DL) model. This comparison utilized a dataset encompassing 50,000 patient records from a large hospital between 2015-2022. The study proposes enhancing the efficacy of these models through feature selection and hyperparameter optimization, employing techniques …

Asem 4.0/5.0 - Evolving The Engineering Management Profession Through Industry 4.0/5.0 Collaborative Networks, T. Steven Cotter, Faisal Mahmud, Ziniya Zahedi

Engineering Management & Systems Engineering Faculty Publications

The American Society for Engineering Management was created and matured under Industry 3.0 automation. The emergence of Industry 4.0 and 5.0 are forcing all organizational sectors to rethink their long-term strategy with respect to emerging horizontal/vertical cyber-physical systems integration. This leaves open the question of the directions in which ASEM should evolve into the 21st century. This paper reports an initial mapping of Industry 4.0 and 5.0 technologies and initiatives as goal-oriented, long-term strategic collaborative networks. The research method began with the Boston Consulting Group nine technologies of Industry 4.0 (2015) and the Industry 5.0 technologies within its human-centric, sustainability, …

A Speech And Facial Information Based Emotion Recognition System Of Collaborative Robot For Empathic Human-Robot Collaboration, Jianna Loor, Jordan Murphy, Rui Li

School of Computing Faculty Scholarship and Creative Works

A robot's ability to effectively recognize human emotions is critical in human-robot collaboration. However, most of the current collaborative robots were designed to improve productivity. Few of these robots consider human emotions. This situation would cause humans to be unwilling to work with robots for a long time. Motivated by this gap, this research developed a human emotion recognition system for enhancing the interaction abilities of collaborative robots. In this project, both speech and facial information were analyzed for robust human emotion recognition in complex working environments like manufacturing assembly environments. In the experiment, the developed system has been tested …

A Survey: Emerging Cybersecurity Threats In Driverless Cars, Vaibhavi Tiwari, Dharshana Rajasekar, Jiayin Wang

School of Computing Faculty Scholarship and Creative Works

In light of the increasing adoption of autonomous vehicles in our transportation networks, it is crucial to emphasize the significance of implementing strong cybersecurity protocols. These self-driving cars, which heavily depend on state-of-the-art sensors, artificial intelligence (AI), and complex communication networks, represent a remarkable advancement in technology. However, they also bring about new vulnerabilities. While it is true that autonomous vehicles have been shown to be statistically safer than traditional cars, it is important to acknowledge the growing concern surrounding cyber threats and their potential impact on the safety and reliability of these vehicles. This paper provides a thorough examination …

Using Generative Large Language Models For Hierarchical Relationship Prediction In Medical Ontologies, Hao Liu, Shuxin Zhou, Zhehuan Chen, Yehoshua Perl, Jiayin Wang

School of Computing Faculty Scholarship and Creative Works

This study extends the exploration of ontology enrichment by evaluating the performance of various open-sourced Large Language Models (LLMs) on the task of predicting hierarchical relationships (IS-A) in medical ontologies including SNOMED CT Clinical Finding and Procedure hierarchies and the human Disease Ontology. With the previous finetuned BERT models for hierarchical relationship prediction as the baseline, we assessed eight open-source generative LLMs for the same task. We observed only three models, without finetuning, demonstrated comparable or superior performance compared to the baseline BERT -based models. The best performance model OpenChat achieved a macro average F1 score of 0.96 (0.95) on …

Using Software Metrics For Predicting Vulnerable Classes In Java And Python Based Systems, Kazi Zakia Sultana, Vaibhav Anu, Tai Yin Chong

School of Computing Faculty Scholarship and Creative Works

[Context:] Failure to predict vulnerability in the earlier stage of development can cause vulnerable code being written and deployed in the final software product. Vulnerability prediction using software metrics as features can support the discovery process by localizing vulnerable code. Existing studies have successfully employed metrics for vulnerability prediction for some platforms (C/C++ or Java projects). We propose that a comparative evaluation of how these metrics perform in projects of different languages can help the developers in deciding whether metrics-based prediction approach can be effective in their own project’s context. [Objective:] The purpose of this research is to analyze/compare the …

Escape The Planet: Revolutionizing Game Design With Novel Oop Techniques, Qusai Kamal Fannoun

All Graduate Theses, Dissertations, and Other Capstone Projects

Mobile devices are continuously evolving and greater computing power and graphics capabilities are being introduced every year. As a result, there is an increasing demand for challenging and engaging mobile games that leverage these advanced features. This project explores best design practices using the development of Escape the Planet, which is an intricate maze game for mobile devices in which players navigate using a spaceship that is trapped in a hostile planet’s maze while avoiding obstacles and enemy attacks. The goal is to safely guide the spaceship out of the maze without colliding into walls or taking bullets from defensive …

A Prototype Application For The Measurement Of Data Breach Event Intensity, James Palazzolo

Master's Theses and Doctoral Dissertations

The data breach phenomenon is not new. People have valued information, its protection, and its security for centuries. A data breach is the loss of control over one’s information. In contemporary society (circa 2024), a data breach can occur in several ways: through accidental disclosure, negligence, or malicious action. Likewise, the study of the data breach phenomenon is not new. As with other studies, this research effort seeks to expand the current body of knowledge concerning data breaches. However, unlike previous research, we adopt a novel approach to further our understanding of the phenomenon. By employing topological and phenomenological thinking, …

Comment On Chapters 1 And 4: Health Ai, System Performance, And Physicians In The Loop, W. Nicholson Price Ii

Book Chapters

Accounts of artificial intelligence (AI) in medicine must grapple, in one way or another, with the interaction between AI systems and the humans involved in delivering healthcare. Humans are, of course, involved throughout the process of developing , deploying, and evaluating AI systems, but a particular role stands out: the human in the loop of an algorithmic decision. In medicine, when an algorithm is involved in a decision , a typical view of the system envisions a human healthcare professional mediating that algorithm - deciding whether and how to implement or react to any recommendation, prediction, or other algorithmic output. …

Time Series Anomaly Detection Using Generative Adversarial Networks, Shyam Sundar Saravanan

Masters Theses

"Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal patterns, and generalizing over different datasets. In this work, we propose TSI-GAN, an unsupervised anomaly detection model for time-series that can learn complex temporal patterns automatically and generalize well, i.e., no need for choosing dataset-specific parameters, making statistical assumptions about underlying data, or changing model architectures. To achieve these goals, we convert each input time-series into a sequence of 2D images using two encoding techniques with …

Radiofrequency Interference Detection Using Lstmand Statistical Analysis Discriminator, Luke Smith

Masters Theses

"Wireless devices are becoming increasingly pervasive across all aspects of society. Examples of such devices include radios, routers, mobile phones, tablets, and more. As the number of radio frequency (RF) devices continues to rise, so does the amount of interference and noise increase. This is why an efficient approach to interference detection is explored. Most research within this area has been done strictly within the frequency domain as viewing a signal within this domain provides many insights into what makes the signal. This has, however, led to the time domain being underutilized for this area of research.

To explore the …

Learn From The Past: Using Peer Data To Improve Course Recommendations In Personalized Education, Colton Walker

Masters Theses

"This work describes a recommendation approach designed to enhance student success by identifying semester schedules and graduation paths. The primary objective is to provide personalized graduation path recommendations rooted in individual student performance and draw insights from the academic journeys of similar students who successfully graduated. The original research contribution of this work lies in the development of a graduation path recommender system that leverages a combination of Markov Decision Process, Q-Learning, and collaborative filtering techniques to pinpoint graduation paths with a higher likelihood of leading students to success based on their academic progress thus far. The effectiveness of the …

A Gat-Bilstma Model For Weather-Aware Prediction Of Traffic Speed, Bikis Muhammed

Masters Theses

This thesis presented a method for incorporating the effect of weather conditions in the prediction of the average speed of vehicular traffic for each segment of a road network. The proposed approach utilized two different deep learning methods: graph attention networks and bidirectional long short-term memory with attention layers. The accuracy of predictions is increased by considering the real-world driving distance between road segments, in contrast to the Haversine distance used in several existing prediction methods. Categorization of input data as weekend or weekday further increased the prediction accuracy. The proposed approach was validated using two data sets published by …

Embedded Collaborative Intelligence Service Mechanism In Emergencies, Chen Wei, Chensheng Wu, Bingfeng Zhao, Qingtao Fan

Journal of Scientific Information Research

[Purpose/significance]Faced with complex cross-domain emergencies, the barriers among intelligence resources, intelligence services and the rights and responsibilities within emergency management must be broken to generate embedded synergy, enhancing emergency management effectiveness. [Method/process]From the three perspectives of intelligence system guarantee, intelligence organization guarantee and early warning intelligence mechanism, this paper studies the basic guarantee, intelligence lack problem and realization path of cross-domain intelligence service emergencies based on the emergency management system and traditional intelligence collaborative service system. With embedded collaborative intelligence monitoring and collection systems and crisis early warning intelligence systems, an embedded collaborative intelligence service system framework is built. [Result/conclusion]Intelligence …

Topic Mining And Dynamic Evolution Analysis Of Patent Technology From The Perspective Of Binary Evolution：Take The Field Of Industrial Robots As An Example, Luyao Dou, Zhigang Zhou, Yi Li, Tao Jiang

Journal of Scientific Information Research

[Purpose/significance]From the perspective of "overall ecology + local stage", mining the technical theme and its evolution law in the field of industrial robots can not only know the overall process of technological development, but also clarify the specific paradigm of technology combination, which has important practical significance for insight into the technological progress and capital investment focus in the field of industrial robots.[Method/process]Based on incoPat patent database, taking the industrial robot field from 2003 to 2022 as an example, combined with Word2vec word vector model and LDA topic model, data mining and corpus expansion of patent texts were carried out, …

Embracing Ai In English Composition: Insights And Innovations In Hybrid Pedagogical Practices, James Hutson, Daniel Plate, Kadence Berry

Faculty Scholarship

In the rapidly evolving landscape of English composition education, the integration of AI writing tools like ChatGPT and Claude 2.0 has marked a significant shift in pedagogical practices. A mixed-method study conducted in Fall 2023 across three sections, including one English Composition I and two English Composition II courses, provides insightful revelations. The study, comprising 28 student respondents, delved into the impact of AI tools through surveys, analysis of writing artifacts, and a best practices guide developed by an honors student. Initially, the study observed a notable anxiety and mistrust among students regarding the use of AI in writing. However, …

Incivility In Open Source Projects: A Comprehensive Annotated Dataset Of Locked Github Issue Threads, Ramtin Ehsani, Mia Mohammad Imran, Robert Zita, Kostadin Damevski, Preetha Chatterjee

Computer Science Faculty Research & Creative Works

In the dynamic landscape of open-source software (OSS) development, understanding and addressing incivility within issue discussions is crucial for fostering healthy and productive collaborations. This paper presents a curated dataset of 404 locked GitHub issue discussion threads and 5961 individual comments, collected from 213 OSS projects. We annotated the comments with various categories of incivility using Tone Bearing Discussion Features (TBDFs), and, for each issue thread, we annotated the triggers, targets, and consequences of incivility. We observed that Bitter frustration, Impatience, and Mocking are the most prevalent TBDFs exhibited in our dataset. The most common triggers, targets, and consequences of …

Trusted Digital Twin Network For Intelligent Vehicles, Asad Malik, Ayan Roy, Sanjay Madria

Computer Science Faculty Research & Creative Works

Vehicle-to-vehicle (V2V) infrastructure facilitates wireless communication among vehicles within close proximity. This allows sharing of contextual information such as speed, location, direction, traffic, route closures, human behavior mental conditions to improve traffic flow, reduce collisions, and enhance safety on the road. However, the assumption of honest peers along with the over-reliability on the information shared in the network can pose a serious threat to human safety. A digital twin is a concept that enables a system to develop a virtual environment that mimics the real-life scenario for any situation. The availability of powerful computing equipment inside vehicles can be leveraged …

Eye-Gaze Guided Multi-Modal Alignment For Medical Representation Learning, Chong Ma, Hanqi Jiang, Wenting Chen, Yiwei Li, Zihao Wu, Xiaowei Yu, Zhengliang Liu, Lei Guo, Dajiang Zhu, Tuo Zhang, Dinggang Shen, Tianming Liu, Xiang Li

Computer Science Faculty Research & Creative Works

In the medical multi-modal frameworks, the alignment of cross-modality features presents a significant challenge. However, existing works have learned features that are implicitly aligned from the data, without considering the explicit relationships in the medical context. This data-reliance may lead to low generalization of the learned alignment relationships. In this work, we propose the Eye-gaze Guided Multi-modal Alignment (EGMA) framework to harness eye-gaze data for better alignment of medical visual and textual features. We explore the natural auxiliary role of radiologists' eye-gaze data in aligning medical images and text and introduce a novel approach by using eye-gaze data, collected synchronously …

The Easy-Ai Symbology, Alexis Ellis, Cogan Shimizu

Computer Science and Engineering Faculty Publications

As artificial intelligence (AI) surges into the forefront of research and the lives of everyday people, challenges in understanding and communicating how these systems operate are becoming more prevalent. The need for a common language for AI systems that allows for multidisciplinary understanding and communication is a prevalent topic within the field. In this work, we take the visual framework EASY-AI and create a symbolic system that overlays the framework’s ontology to facilitate such communication and understanding. Poster submission.

An Ontology Design Pattern For Role-Dependent Names, Rushrukh Rayan, Cogan Shimizu, Pascal Hitzler

Computer Science and Engineering Faculty Publications

We present an ontology design pattern for modeling Names as part of Roles, to capture scenarios where an Agent performs different Roles using different Names associated with the different Roles. Examples of an Agent performing a Role using different Names are rather ubiquitous, e.g., authors who write under different pseudonyms, or different legal names for citizens of more than one country. The proposed pattern is a modified merger of a standard Agent Role and a standard Name pattern stub.

Privacy Vs. Social Capital: Examining Information Disclosure Patterns Within Social Media Influencer Networks, Eidan James Rosado

CCAC Theses and Dissertations

Adversaries have several ways to leverage and expose the data disclosed in social media network engagements for different motives including but not limited to fraud, discreditation, or social engineering. Previous research on social media interactions discussed increased engagements where influencers and viral trends were involved. Studies also discussed engagements declining over time. Within posts or engagements, personal identifiable information (PII) can be shared with varying rate of risk severity. Publicly available data such as this can be leveraged by adversaries. With the absence of insights of whether influencers impact engagements and disclosures, the goal of this study was to obtain …

Design Science Nutrition Label Approach: Satiating U.S. Consumer Concerns For Information Privacy (Cfip) With Privacy Home Automation Assessment Scorecards (Phaats), Andrew S. Ramos

CCAC Theses and Dissertations

In today’s technology-dependent society, information privacy and cybersecurity boundaries between human-to-machine-to-web are non-existent or built on questionable business practices. Consumers are becoming more reliant on and even addicted to their technological enabling, or internet of things (IoT), life tools (e.g., smartphones, smarthome devices, smart-wearable devices). Nevertheless, consumer information privacy rights in the United States have not fully matured to legal ramifications against businesses like in other countries, e.g., the European Union’s 2018 General Data Protection Regulation (GDPR). The real issue lies in consumers not understanding the opportunity cost of associated privacy trade-offs. While some are unaware, others disregard such trade-offs …

An Algorithm Based On Priority Rules For Solving A Multi-Drone Routing Problem In Hazardous Waste Collection, Youssef Harrath Dr., Jihene Kaabi Dr.

Research & Publications

This research investigates the problem of assigning pre-scheduled trips to multiple drones to collect hazardous waste from different sites in the minimum time. Each drone is subject to essential restrictions: maximum flying capacity and recharge operation. The goal is to assign the trips to the drones so that the waste is collected in the minimum time. This is done if the total flying time is equally distributed among the drones. An algorithm was developed to solve the problem. The algorithm is based on two main ideas: sort the trips according to a given priority rule and assign the current trip …

Pupillometry As A Viable Augmentative And Alternative Communication Pathway: A Machine Learning Application, Kouadio Marc-Antoine Niamba

Dissertations and Theses

Every year, clinicians diagnose 5000 new Amyotrophic Lateral Sclerosis (ALS) cases in the United States (Mehta et al., 2018). ALS is a degenerative neuromuscular disease that prevents neurons from sending impulses to the muscles, thus resulting in paralysis and death. People with ALS (PALS) not only experience limited mobility but also lose their ability to communicate. Although the disease currently remains incurable, efforts to improve the patients’ communication are increasingly leading toward Augmentative and Alternative Communication (AAC) systems (Beukelman and Mirenda, 2013). AAC systems are assistive technologies that propose to counteract the defects resulting from ALS through non-verbal communication channels. …

On Vulnerabilities Of Building Automation Systems, Michael Cash

Graduate Thesis and Dissertation 2023-2024

Building automation systems (BAS) have become more commonplace in personal and commercial environments in recent years. They provide many functions for comfort and ease of use, from automating room temperature and shading, to monitoring equipment data and status. Even though their convenience is beneficial, their security has become an increased concerned in recent years. This research shows an extensive study on building automation systems and identifies vulnerabilities in some of the most common building communication protocols, BACnet and KNX. First, we explore the BACnet protocol, exploring its Standard BACnet objects and properties. An automation tool is designed and implemented to …

Privacy And Security Of The Windows Registry, Edward L. Amoruso

Graduate Thesis and Dissertation 2023-2024

The Windows registry serves as a valuable resource for both digital forensics experts and security researchers. This information is invaluable for reconstructing a user's activity timeline, aiding forensic investigations, and revealing other sensitive information. Furthermore, this data abundance in the Windows registry can be effortlessly tapped into and compiled to form a comprehensive digital profile of the user. Within this dissertation, we've developed specialized applications to streamline the retrieval and presentation of user activities, culminating in the creation of their digital profile. The first application, named "SeeShells," using the Windows registry shellbags, offers investigators an accessible tool for scrutinizing and …

A Comprehensive Study Of Patent Litigation In The Pharmaceutical Sector: Employing Network Theories, Graph Neural Networks, Agent Based Modeling, Bayesian Network Autocorrelation Models, Sreehas Gopinathan

Information Systems & Operations Management Dissertations - Archive

Understanding the dynamics and predictors of patent litigation is crucial in intellectual property management, especially given the competitive edge patents offer companies. Also, patents serve as both legal tools and repositories of innovation. This research delves into the complex world of patent litigation within the pharmaceutical industry, focusing on creating and applying advanced computational models to study litigation propensities. Techniques such as Graph Neural Networks (GNN), Agent-Based Modeling (ABM), and Bayesian Analysis of Network Autocorrelation Models (BANAM) are employed to explore the litigation phenomenon

Reinforcement Learning: Applying Low Discrepancy Action Selection To Deep Deterministic Policy Gradient, Aleksandr Svishchev

College of Graduate Studies: Theses & Dissertations

Reinforcement learning (RL) is a subfield of machine learning concerned with agents learning to behave optimally by interacting with an environment. One of the most important topics in RL is how the agent should explore, that is, how to choose actions in order to rate their impact on long-term reward. For example, a simple baseline strategy might be uniformly random action selection. This thesis investigates the heuristic idea that agents will learn faster if they explore by factoring the environment’s state into their decision and intentionally choose actions which are as different as possible from what they have previously observed. …

Infrared Ship Segmentation Based On Weakly-Supervised And Semi-Supervised Learning, Isa Ali Ibrahim, Abdallah Namoun, Sami Ullah, Hisham Alasmary, Muhammad Waqas, Iftekhar Ahmad

Research outputs 2022 to 2026

Existing fully-supervised semantic segmentation methods have achieved good performance. However, they all rely on high-quality pixel-level labels. To minimize the annotation costs, weakly-supervised methods or semi-supervised methods are proposed. When such methods are applied to the infrared ship image segmentation, inaccurate object localization occurs, leading to poor segmentation results. In this paper, we propose an infrared ship segmentation (ISS) method based on weakly-supervised and semi-supervised learning, aiming to improve the performance of ISS by combining the advantages of two learning methods. It uses only image-level labels and a minimal number of pixel-level labels to segment different classes of infrared ships. …