Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network

Open Access. Powered by Scholars. Published by Universities.®

PDF

Kennesaw State University

Conference

Discipline
Keyword
Publication Year
Publication

Articles 1 - 30 of 1244

Full-Text Articles in Entire DC Network

Depression Among College Students: Differences By Race, Generation Status, And Their Intersection, Kenzie Thomas May 2024

Depression Among College Students: Differences By Race, Generation Status, And Their Intersection, Kenzie Thomas

Symposium of Student Scholars

Previous research has shown that depression can negatively impact college students. Yet, there is a major gap in the literature regarding differences in depression among college students by race, generation status, and their intersection. One study demonstrated that first-generation college students (FGCS; neither parent obtained a college degree) experience higher levels of depressive symptoms compared to continuing-generation college students (CGCS; at least one parent obtained a college degree). Similarly, another study found that African American college students endure more experiences of hopelessness and depression than their counterparts. Still, this evidence is scant, and there remains little research on depression as …


Daylighting In Buildings: Investigating The Relationship Between Daylight Levels And Building Compactness In Various Contemporary Architectural Types. [Efficient Typology Classification], Andrew Welch, Ermal Shpuza Phd May 2024

Daylighting In Buildings: Investigating The Relationship Between Daylight Levels And Building Compactness In Various Contemporary Architectural Types. [Efficient Typology Classification], Andrew Welch, Ermal Shpuza Phd

Symposium of Student Scholars

One of the key ways of improving the energy efficiency of a building is to enhance the daylight levels and reduce the need for artificial lighting. Good daylight levels are also associated with increased productivity and the well-being of a building's occupants. Daylight levels are often a direct function of the floorplate depth, where locations near the windows receive more daylight, and those deep inside the buildings receive less. As a result, shallow floorplates and elongated buildings are usually related to higher daylight levels. However, shallow buildings that have more natural light are also associated with greater construction costs due …


Pregnancy Behind Bars: Exploring The Impact Of Incarceration On Prenatal And Postnatal Care For Female Inmates, Caitlin Callahan, Anisah Bagasra, Meghan Bankhead May 2024

Pregnancy Behind Bars: Exploring The Impact Of Incarceration On Prenatal And Postnatal Care For Female Inmates, Caitlin Callahan, Anisah Bagasra, Meghan Bankhead

Symposium of Student Scholars

Incarcerated women have a constitutionally protected right to obtain appropriate medical care. Past research has found that “38 states had inadequate or no prenatal care in their prisons” (NWsLC, 2010). A report from The US Department of Justice states that “46% of pregnant imprisoned women reported they received no pregnancy care” (Maruschak, 2008). There is a gap in the literature of analyzing primary accounts of pregnant inmates. The current study is investigating the interaction of incarceration and the available care and quality of care given to female inmates in American correctional institutions. This study is comprised of a qualitative video …


Mosaic Swarm Robotics: Emulating Natural Collective Behaviors For Efficient Task Execution With Custom Mobile Robots, Jonathan Ridley, Arielle Charles, Charles Koduru, Muhammad Hassan Tanveer, Razvan Voicu May 2024

Mosaic Swarm Robotics: Emulating Natural Collective Behaviors For Efficient Task Execution With Custom Mobile Robots, Jonathan Ridley, Arielle Charles, Charles Koduru, Muhammad Hassan Tanveer, Razvan Voicu

Symposium of Student Scholars

Mosaics, as an artistic expression, involves the meticulous arrangement of diverse tiles to form a unified composition. Drawing inspiration from this concept, the field of swarm robotics seeks to emulate nature’s collective behaviors observed in ant colonies, fish schools, and bird flocks, employing multiple agents to accomplish tasks efficiently. Our research explores the concept of mosaic swarm robotics, where numerous nodes with specialized functions are deployed across various domains, including applications for outdoor data capture and environment mapping. We utilized custom mobile robots operated by Raspberry Pi microcontrollers. By establishing an elaborate web of client-to-client communications to enable true localized …


Bridging The Epochs Of Ledoux And Da Vinci, Nancy Sanchez, Ehsan Sheikholharam Ma May 2024

Bridging The Epochs Of Ledoux And Da Vinci, Nancy Sanchez, Ehsan Sheikholharam Ma

Symposium of Student Scholars

Undergraduate Student: Nancy Sanchez

Research Mentor(s): Ehsan Sheikholharam Mashhadi

Bridging the Epochs of Ledoux and Da Vinci

From two different periods of time, Claude-Nicholas Ledoux and Leonardo Da Vinci have transformed the history of architecture and art. Their work has helped shape the two eras they were a part of. Leonardo Da Vinci was from the 16th century and was coined as the ‘Italian Polymath of the High Renaissance era’, due to his extensive knowledge in engineering, painting, architecture, and science. Claude-Nicolas Ledoux was an 18th century neoclassical architect from France. Ledoux produced architecturally innovative work that influenced social changes …


Spatial Associations Of Lung Cancer Rates And Socioeconomic, Health, And Environmental Factors In Georgia, Nguyet Le, Jun Tu May 2024

Spatial Associations Of Lung Cancer Rates And Socioeconomic, Health, And Environmental Factors In Georgia, Nguyet Le, Jun Tu

Symposium of Student Scholars

According to CDC, Lung and Bronchus Cancer ranks the highest by the rate of cancer deaths among different types of cancers in the United States with the rate of 31.8 per 100 thousand people, and also for Georgia with the rate of 33.4 per 100 thousand people. Thus, to reduce the death rate of lung cancer, it is quite important and urgent to understand its risk factors. Smoking and inhaling radon are among the top risk factors of lung cancer for individuals. The socioeconomic, health, and environmental characteristics of communities might be also related to the likelihood of getting …


Loneliness And Parental Relationships Among College Students, Alanna James, Charlie Barna May 2024

Loneliness And Parental Relationships Among College Students, Alanna James, Charlie Barna

Symposium of Student Scholars

The transition to adulthood is a unique developmental period that involves rapid changes in youths’ individual development and social contexts, which can involve leaving behind familiar support networks (Eeske et al,. 2015). Common experiences during the transition to adulthood, like leaving home, pursuing college, and entering the workforce can leave individuals feeling marginalized and cutoff (Mathews et al,. 2022). Loneliness is a subjective feeling experienced by individuals in all age demographics (Matthews et al,. 2022). Despite a wide array of research on social connectedness interventions for older adults and people with physical disabilities (Zagic et al,. 2021), there is little …


Biomechanical Differences In Crawling Between Typically Developing Infants And Infants With Limb Loss, Feby Takawy, Larissa Brehm, Analise Oliver, Mark Geil May 2024

Biomechanical Differences In Crawling Between Typically Developing Infants And Infants With Limb Loss, Feby Takawy, Larissa Brehm, Analise Oliver, Mark Geil

Symposium of Student Scholars

INTRODUCTION: In 2022, the Centers for Disease Control and Prevention published updates to their checklists for the milestones children should achieve during typical development, and removed crawling entirely, citing a lack of normative data, inconsistent definitions, and variability timing of crawling onset (1,2). This project collected normative kinematic and spatiotemporal data on typically developing (TD) crawling infants and crawlers with limb loss (LL).

METHODS: Eleven TD infants were assessed every two weeks between onset of crawling and transition to walking. Six LL infants were assessed once without the use of a prosthesis. Infants crawled on a pressure-sensing mat that was …


The Impact Of Student Stress On Physical Wellbeing, Isabelle Fevrier May 2024

The Impact Of Student Stress On Physical Wellbeing, Isabelle Fevrier

Symposium of Student Scholars

This study will explore the intricate relationship between student stress and its impact on physical health. It will explore how stressors such as academic pressures, jobs, and lengthy commutes impact physiological manifestations and various aspects of physical well-being in students. The literature this research builds upon is diverse, ranging from in-depth looks at how the body responds to stress, such as the actions of the brain when under stress, to how stress causes disturbances in sleep, diet, and physical activity. For this specific research, physical health will be defined as sleep schedule, frequency of sickness, and daily fatigue. There will …


Influence Of Al2o3 Passivation Layer Thickness On The Thermal Stability And Quality Of Mocvd-Grown Gan On Si, S M Atiqur Rahman, Manika Tun Nafisa, Zhe Chuan Feng, Benjamin Klein, Ian T. Ferguson May 2024

Influence Of Al2o3 Passivation Layer Thickness On The Thermal Stability And Quality Of Mocvd-Grown Gan On Si, S M Atiqur Rahman, Manika Tun Nafisa, Zhe Chuan Feng, Benjamin Klein, Ian T. Ferguson

Symposium of Student Scholars

This research delves into the significant impact of varying thicknesses of the Al2O3 passivation layer on the thermal stability and crystalline quality of GaN on Si structures, an essential aspect for the next generation of high-temperature electronic and optoelectronic devices. By adopting metal-organic chemical vapor deposition (MOCVD) for the growth process, we analyzed structures with different Al2O3 passivation layer thicknesses: none, 2 nm, 10 nm, and 20 nm, each built upon the GaN layer. Through Raman spectroscopy, we meticulously assessed the changes in the E2 (High) phonon mode's peak position and full width …


Gpr-103 Personalized Pedagogy Through A Llm-Based Recommender System, Mourya Teja Kunuku, Bharath Y Yadla Apr 2024

Gpr-103 Personalized Pedagogy Through A Llm-Based Recommender System, Mourya Teja Kunuku, Bharath Y Yadla

C-Day Computing Showcase

The educational domain is undergoing transformation due to the incorporation of Artificial Intelligence (AI), Large Language Models (LLMs), and generative AI technologies, raising the need for educators to integrate cutting-edge technological advancements and methodologies into their teaching approaches. Pedagogical Design Patterns (PDPs) have become prominent for their role in sharing effective educational practices and narrowing the divide between academic research and actual teaching methods. Despite their potential, the lack of widely accessible resources and the scattered nature of publishing outlets pose significant barriers to the broad application of PDPS. To address this issue, we propose the application of large language …


Gc-104 Edai – Ai Enabled Teaching Robot For Informal Learning, Jennifer Bower, Shane Williams, Justice Fuller Apr 2024

Gc-104 Edai – Ai Enabled Teaching Robot For Informal Learning, Jennifer Bower, Shane Williams, Justice Fuller

C-Day Computing Showcase

We began our project by researching various popular, open-source AI tools that are available today. After we chose to focus on ChatGPT as our AI tool, we decided on cybersecurity as our subject matter. Next, we researched traditional cybersecurity training methods used by companies to train their employees on cybersecurity issues. Our project focused on determining whether or not open-source AI tools such as ChatGPT could replace traditional cybersecurity training tools and methods for companies.


Gc-101 Learning Resource Finder: A Web Scraping Tool For Educational Materials, Ashrith Kumar Devara Apr 2024

Gc-101 Learning Resource Finder: A Web Scraping Tool For Educational Materials, Ashrith Kumar Devara

C-Day Computing Showcase

The Learning Resource Finder is a pioneering tool designed to alleviate the challenges associated with navigating the vast landscape of online educational content. Leveraging sophisticated web scraping techniques and API integrations, this tool empowers users to efficiently discover relevant learning materials tailored to their specific needs. Through a user-friendly Flask-based web interface, users initiate search queries, which are then encoded and utilized to fetch pertinent URLs from leading educational platforms such as JavaTPoint, W3Schools, Coursera, Udemy, and GeeksforGeeks, as well as Google search results. The core of the web scraping process lies in the meticulous extraction of URLs from HTML …


Gc-17 Crm For Ccse Department Of Ksu, Venkatesh Alla, Keerthi Nannapaneni, Vinay Kumar Rapolu Apr 2024

Gc-17 Crm For Ccse Department Of Ksu, Venkatesh Alla, Keerthi Nannapaneni, Vinay Kumar Rapolu

C-Day Computing Showcase

This project outlines the development of a bespoke Customer Relationship Management (CRM) system specifically designed for the College of Computer and Software Engineering (CCSE). The initiative aims to centralize customer information into a unified repository, thereby enhancing the confidentiality, management, and optimization of data and communication processes within the college. The CRM system will integrate features for detailed profiles, communication optimization, complex workflow management, document repository, and data migration to ensure efficiency and data integrity. It will also facilitate seamless interaction with Microsoft 365 and Outlook, supporting the college's operational needs and maintaining its commitment to excellence in education and …


Gc-22 Fabric Moderation Ticketing Mod For Minecraft, John Lambert, Kathy Nguyen, Hayden B Scarbrough, Dasiane Taplin Apr 2024

Gc-22 Fabric Moderation Ticketing Mod For Minecraft, John Lambert, Kathy Nguyen, Hayden B Scarbrough, Dasiane Taplin

C-Day Computing Showcase

This project targets enhancing the KSU Esports program’s Minecraft server by implementing an in-game ticketing system. The system will enable players to report any instances of in-game incidents/issues seamlessly within the game environment. The integration with the KSU Minecraft Discord server will facilitate efficient communication between players and administrators. With a user-friendly interface and optimized resource usage, the system aims to streamline moderation processes.


Gmr-45 Cloud Based Bus Tracking And Ticketing System, Vyghni Sudha Kommineni, Damacharla Sravani Apr 2024

Gmr-45 Cloud Based Bus Tracking And Ticketing System, Vyghni Sudha Kommineni, Damacharla Sravani

C-Day Computing Showcase

In many urban areas, public transportation systems frequently fail to fulfill passenger demand, causing aggravation owing to a lack of real-time information about bus locations, timetables and delays. Outdated ticketing processes, which are labor-intensive and prone to mistakes, compound the annoyance by failing to match current travelers' expectations. Furthermore, transportation operators encounter difficulties with fleet management, route optimisation, and issue response due to a lack of comprehensive data analytics. Reliable monitoring systems are required to prioritize passenger and bus safety, and achieving sustainability targets necessitates efficient operations to reduce fuel consumption and emissions. A scalable and customizable cloud-based bus tracking …


Gmr-118 Stress Detection By Wearable Devices: Integrating Multimodal Physiological Signals And Machine Learning Techniques, Pranita Subhash Shedage Apr 2024

Gmr-118 Stress Detection By Wearable Devices: Integrating Multimodal Physiological Signals And Machine Learning Techniques, Pranita Subhash Shedage

C-Day Computing Showcase

In the medical field, the most common complaint of patients is “stress”. Stress can cause severe effects on the human body. For example, prolonged mental stress can cause serious health issues in long term such as hypertension, cardiovascular diseases, increased susceptibility to infections, and depression. These health issues can be prevented by early detection of stress and by taking preventive measures. The most common detecting stress was determined from the questionnaires or from the interactive sessions conducted to assess the people's affective state. However, this method is not highly reliable and can be biased depending on the person who is …


Gmr-59 Customer Segmentation For Marketing Campaigns Using K-Means Clustering, Jaswanthi Vellanki, Hrithik Singh Chandel, Vyghni Sudha Kommineni, Priyanka A Bagal, Rutvikkumar K Ramani Apr 2024

Gmr-59 Customer Segmentation For Marketing Campaigns Using K-Means Clustering, Jaswanthi Vellanki, Hrithik Singh Chandel, Vyghni Sudha Kommineni, Priyanka A Bagal, Rutvikkumar K Ramani

C-Day Computing Showcase

The objective of this project is to use K-means clustering an unsupervised machine learning algorithm to categorize customers based on characteristics such as demograp hics, purchasing history and interaction behavior. The purpose is to discover different client segments that can be targeted with specialized marketing techniques that improve marketing campaign efficiency and increase consumer satisfaction and engagement.


Gmr-23 Jamming Signal Detection Using Extreme Gradient Boosting (Xgboost) Algorithm, Keerthana Adamana, Christian K Sao Apr 2024

Gmr-23 Jamming Signal Detection Using Extreme Gradient Boosting (Xgboost) Algorithm, Keerthana Adamana, Christian K Sao

C-Day Computing Showcase

Radar jamming involves sending intentionally disruptive radio waves toward the target radar, which might over-saturate its receiver so it can’t receive anything or deceive it into interpreting false information. Machine learning (ML) techniques increased the capability to automatically learn the experience without being explicitly programmed. Machine learning models usually require a large, labeled sample to perform. Building a robust jamming detection model will be challenging due to the wide variability of jamming signals and less available labeled samples. In this project, we developed an eXtreme Gradient Boosting(XGBoost) algorithms for radar jamming signal classification and achieved superior performance compared with Random …


Gc-84 Owl Cyber Defense Systems, Randolph S Gilstrap, Christopher Dunbar, Stephanie Aguirre, Ryan M Leblanc, Justin Place Apr 2024

Gc-84 Owl Cyber Defense Systems, Randolph S Gilstrap, Christopher Dunbar, Stephanie Aguirre, Ryan M Leblanc, Justin Place

C-Day Computing Showcase

Owl Cyber Defense Systems is a fictitious (for now?) start-up offering comprehensive cybersecurity solutions for small and medium businesses. Our premier flagship product is an AI Chatbot that answers security related questions and provides vetted code and security settings to secure and harden a variety of systems. Starting with the initial concept, we methodically progressed through the business planning process, carefully considering technology usage and design. This comprehensive approach ultimately enabled us to develop a robust set of client offerings. We used a hybrid approach combining Agile Scrum and traditional Waterfall methodologies to complete the project. We utilized Jira Project …


Uc-27 Crm Proposal, Luis A Maiocchi Castro, Crystal Misko, Steven Damico, Ethan Groves, Maryah Outlaw Apr 2024

Uc-27 Crm Proposal, Luis A Maiocchi Castro, Crystal Misko, Steven Damico, Ethan Groves, Maryah Outlaw

C-Day Computing Showcase

This project addresses concerns raised by a Sponsor regarding inefficiencies in managing CCSE capstone projects. Key pain points include organization, project management, and communication among stakeholders. The proposed solution involves implementing Customer Relationship Management (CRM) software. Upon gathering requirements from the Sponsor, including contact information capture, workflow management, document control, and customization capabilities, we evaluated several CRM platforms. A total of thirty-two CRMs were reviewed and Vtiger, OroCRM, and SuiteCRM were selected for testing. SuiteCRM was chosen for its comprehensive features and user-friendliness. The second step of the project involved testing SuiteCRM functionalities on a dedicated server, leading to its …


Uc-33 Big Munchin', Tabitha Reynolds, Steven M Amerson, David J Buck, Jacques P Gatipon, Aaliyah Mcelrath, Nick S Watson Apr 2024

Uc-33 Big Munchin', Tabitha Reynolds, Steven M Amerson, David J Buck, Jacques P Gatipon, Aaliyah Mcelrath, Nick S Watson

C-Day Computing Showcase

Big Munchin' is a video game designed to help teach portioning skills and promote healthy eating habits. The overall metabolic health of individuals in America is comparatively low to other countries. Metabolic health is bolstered by several factors including exercise and a proper diet consisting of essential vitamins, proteins, and other important biomolecules.The increased cost of healthy nutrient-rich foods and a lack of proper nutritional education have hindered the overall metabolic health of modern Americans. Engaging individuals in learning more about nutritional health can be a difficult task made easier by an engaging experience that stays in the user’s minds. …


Uc-35 Ksu Ccse Crm, Alex Curran, Dj Mitchell, Christian Miller Apr 2024

Uc-35 Ksu Ccse Crm, Alex Curran, Dj Mitchell, Christian Miller

C-Day Computing Showcase

Our task was to select, implement and customize a CRM solution for the College of Computing and Software Engineering to more effectively manage communication with industry partners and manage projects such as capstones, and C-Day. Our team selected SuiteCRM as our recommendation and have implemented an instance on a virtual machine provided by UITS. We have customized branding including using a KSU logo provided by the Office of Strategic Communications and Marketing, as well as customizations based on the official KSU color pallete. The process we used to select our CRM recommendation involved gathering requirements from our sponsor and comparing …


Gc-8 Informal Learning Artificial Intelligence Large Language Model Fine-Tuning On The Select Topic Of Entrepreneurship, Kristen Gabby, Melina Castellon, Jyothi Sampathirao Apr 2024

Gc-8 Informal Learning Artificial Intelligence Large Language Model Fine-Tuning On The Select Topic Of Entrepreneurship, Kristen Gabby, Melina Castellon, Jyothi Sampathirao

C-Day Computing Showcase

This project explored the usage and development of open-source Large Language Model (LLM) Artificial Intelligence (AI) with a chat feature, specifically to fine-tune on the topic of entrepreneurship. This project sought to showcase the adaptability of open-source LLMs and highlight challenges and solutions faced in leveraging those LLMs. The primary goal was to show proof of concept that training a LLM on the selected subject can create a specialized AI chat for informal learning.


Gmr-7 A Novel Identity Verification Framework Using A Hybrid Biometric System, Namratha Tavva, Bhanu Prakash Vadlamudi, Sumanth Kunchala, Snigdha Katta Apr 2024

Gmr-7 A Novel Identity Verification Framework Using A Hybrid Biometric System, Namratha Tavva, Bhanu Prakash Vadlamudi, Sumanth Kunchala, Snigdha Katta

C-Day Computing Showcase

In recent years, the field of big data analytics has gained immense attention due to the increasing volume and complexity of data being generated from various sources. One of the key applications of big data analytics is in the field of identity verification, where it is used to process and analyze large amounts of biometric data to authenticate individuals. A hybrid biometric system that combines multiple biometric modalities has been shown to be more effective in identity verification than a single modality system. In this project, we propose an Identity Verification Framework using a Hybrid Biometric System that leverages big …


Gmr-90 Digimindready: Enhancing Military Readiness With Edge Ai-Driven Wellness, Education, And Digital Discipline Through Mhealth Innovation., Md Mehedi Hasan, Nafisa Anjum Apr 2024

Gmr-90 Digimindready: Enhancing Military Readiness With Edge Ai-Driven Wellness, Education, And Digital Discipline Through Mhealth Innovation., Md Mehedi Hasan, Nafisa Anjum

C-Day Computing Showcase

Military personnel often need to operate in high-stakes situations. Combating such volatile missions primarily includes control over cognitive overload, reckless mindset, and maintaining concentration amid distractions to sustain operational effectiveness. Military training significantly focuses on human performance, which benefits military readiness. However, the 21st century has introduced unanticipated challenges, such as adverse effects of excessive screen time, external distractions, and over-reliance on technology to the US military, on top of existing issues like anxiety and emotional stability, adversely impacting military readiness and decreasing quality of life. A strategic investigation into these issues and the advancement of effective tools to address …


Uc-82 Trip Logger, Reese D Gassner, Jason Zhou, Justin T Barker Apr 2024

Uc-82 Trip Logger, Reese D Gassner, Jason Zhou, Justin T Barker

C-Day Computing Showcase

We developed an Android mobile app using the Software Development Life Cycle (SDLC) approach to enable users to track their travel distance and time via GPS, fostering greater emissions awareness through their driving habits of distance and time taken. Built with the Flutter framework and Dart language, the app features a user-friendly interface created with Flutter widgets that manage both appearance and user interactions. Our streamlined architecture comprises three layers: the presentation layer for UI elements, the application layer containing the core logic, and the data layer, which locally stores trip data in CSV format to ensure quick access and …


Uc-99 Interactive Training Games - Robins Air Force Base, Sean J Tenney, Vt Nguyen, Ian Ford, Mason Farmer, Aaron Hannah Apr 2024

Uc-99 Interactive Training Games - Robins Air Force Base, Sean J Tenney, Vt Nguyen, Ian Ford, Mason Farmer, Aaron Hannah

C-Day Computing Showcase

Our project involves converting three PowerPoint training presentations on STINFO, No Fears Act, and Records Management into engaging web-based games. Commissioned by Robins Air Force Base, our team utilizes Unity WebGL for game development and React/Firebase for website hosting. The goal is to provide Air Force personnel with interactive training modules accessible from their desks, enhancing learning retention and engagement. By gamifying the content, we aim to make learning enjoyable while ensuring critical information retention. This interdisciplinary project merges game development and web technologies to modernize training methods and improve educational outcomes for military personnel.


Ur-12 Multiple Myeloma: Increase Longevity And Quality Of Life Through Early Detection, Desyne Martinez Apr 2024

Ur-12 Multiple Myeloma: Increase Longevity And Quality Of Life Through Early Detection, Desyne Martinez

C-Day Computing Showcase

Multiple Myeloma is a rare form of bone marrow cancer where plasma cells accumulate in the blood stream attacking the skeletal system, nervous system, and kidneys of predominantly African Americans. The disease results in high mortality rates within 5 years of initial diagnosis. Multiple Myeloma has subtle symptoms of bone pain; doctors often send people to physical therapy missing the diagnosis. Current research on the International Myeloma Foundation website includes summaries of blood tests of Multiple Myeloma patients. This study seeks to identify the best blood test predictors of Stage 3, the most aggressive stage of Multiple Myeloma. The cost …


Ur-15 Analyzing Breast Cancer Histopathology Images Using Deep Neural Network Models, Je'dae Lisbon, Michael Bolnik, Sepehr Eshaghian Apr 2024

Ur-15 Analyzing Breast Cancer Histopathology Images Using Deep Neural Network Models, Je'dae Lisbon, Michael Bolnik, Sepehr Eshaghian

C-Day Computing Showcase

Our project aims to explore human tissue cells digitized by whole slide scanners for a better understanding of complex tumor microenvironments in breast cancer histopathology images, using various deep neural network models. First, we experimented with 70% percentages of tumor cells on image classification using ResNet50, VGG16, and Inception-ResNet. Second, we performed instance image segmentation using Mask-RCNN. Third, we applied two well-known explainable artificial intelligence (AI) techniques including Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP) to determine the effectiveness of the models.