Explore the Possibilities

Give Now

 

 

College of Computing and Software Engineering 2023-2024 Projects

Click here to return to the main project listings page. Questions: Email our@kennesaw.edu.

  • 2023-2024 First Year Scholars: Mercy Olaniran

    • With the rapid advancement of machine learning (ML), it has shown transformative power across diverse fields. From medical diagnostics to autonomous driving, ML has demonstrated promising performance in plenty of fields due to the ability to solve complex problems effectively. This effectiveness often arises from its capacity in processing a vast amount of data, enabling models to extract internal features from the data that are typically not seen in conventional computing methodologies. Despite its strength, ML also faces several challenges, especially in the domain of data privacy. With the ML models being developed and analyzed, it is certain that training data with large size are yielding desirable results. ML models, during their training phase, can inadvertently "memorize" sensitive aspects of the data, potentially compromising the privacy of data owners.

      Nowadays, a lot of Internet giants such as Google, Amazon and Microsoft have been offering machine learning as a service. Adversarial parties can easily access to such services and launch inference attacks to extract private information by querying the ML model. Moreover, the common strategy of data anonymization is not safe enough because adversarial parties can re-identify individuals in anonymized datasets by combining the data with background information. Therefore, here comes an essential research question: How do we continue enjoying the benefits of ML while protecting against privacy leakages in ML frameworks? Recently, generative models have gained a lot of attentions from both academia and industry and are rapidly evolved in the last decade. Generative models can be utilized to generate a huge number of high-fidelity images or even artworks based on the input training images. Thanks to the ability of generative models, there is a potential to leverage such models to generate synthetic data based on the original training data and further use the synthetic data instead of the original data that contains sensitive information during the ML training phase. Therefore, based on the generated synthetic data, we can potentially protect the whole ML frameworks.

      In this project, (1) we will first conduct a comprehensive analysis of cutting-edge generative models, understanding their mechanics, capabilities, and limitations; (2) then we will explore the feasibility and methodologies to harness these generative models as protection method, ensuring that ML frameworks remain private.

      1. Apply fundamental and disciplinary concepts and methods that supports the research project.
      2. Attain the ability to identify, analyze and solve problems creatively.
      3. Investigate the cutting-edge generative models.
      4. Propose solutions to protect machine learning frameworks.
      5. Learn the principles of academic writing and research presentation skills.
      6. Collaborate with other graduate and undergraduate students with effective oral and written communication.
      1. Weekly meeting and updates.
      2. Implement the state-of-the-art generative models.
      3. Develop the system to defend attacks against machine learning models.
      4. Prepare presentations for literature review or key findings in the project.
      5. Final research project reports and poster presentation in annual symposium.

    • Hybrid

    • Dr. Xinyue Zhang, xzhang48@kennesaw.edu

  • 2023-2024 First Year Scholars: Divyen Marsonia, Sanjay Ravikumar, and Brendan Senatus

    • With the advancement of Artificial Intelligence (AI) technology, it is used in every part of our life, e.g., healthcare, finance, security system, autonomous vehicle, cybersecurity, and transportation system. Although AI achieved state-of-the-art performance in healthcare domain e.g., disease diagnosis, disease prognosis, virtual health assistants, malicious actors can utilize adversarial attacks to access and manipulate the AI-based system. The attackers can use adversarial example attacks to craft a poison sample in the inference phase to predict incorrect information or perform a model poisoning attack to steal confidential data.

      In this project, students will identify the previous attacks that may have occurred in the US healthcare system, explore the list of attack surfaces the attacker used to execute the attacks, identify the commonalities of attack surface, prospect of the adversarial attacks in machine learning-based healthcare systems. Students will identify case studies to prove their hypothesis and findings. Students will explore the potential security vulnerability primarily in healthcare systems but can be extended according to research findings. Student must read research papers, government websites, newspapers, and white papers to prove their hypothesis. 

      • Investigate cutting edge technologies in the AI based healthcare system.
      • Develop secured AI models framework in healthcare system.
      • Develop scientific writing skills by reading, critically analyzing, and discussing key scientific conference papers with mentors.
      • Improve presentation skills by participating in conference/workshop venue based on the research outcome.
      • Advance communication skills based on regular meeting with mentors.
      • Collaborate with other graduate/undergraduate students. 
      • Attend weekly scheduled meeting in-person/online, present weekly outcome and receive mentor’s feedback.
      • Read research papers and summarize the finding in a scientific paper format.
      • Implement algorithm and execute experiments to get hands-on experience in cutting edge research.
      • Assist mentor writing research papers or submitting grants.

    • Hybrid

    • Dr. Kazi Aminul Islam, kislam4@kennesaw.edu 
      Dr. Nazmus Sakib, nsakib1@kennesaw.edu 

  • 2023-2024 First Year Scholars: Yousef Hasan and Amina Hussain

    • Artificial intelligence improves automated decision-making performance in real-world applications. However, incorporating humans in the application loop achieves decision superiority in various environments, including a high-risk, time-critical nature. Behavioral health is critical for our overall well-being, and emotional health challenges are rising globally, especially during and after the pandemic. The emergence of artificial intelligence (AI) can assist community residents and providers with some elements of support in decision-making that can ease the pressure on the behavioral health care system. For example, students in continuous stress or distress could be automatically guided by the virtual AI companion (e.g., chatbot similar as chatgpt) to take necessary steps to resolve their issues. We would apply a machine learning algorithm to make decisions smarter secure, and more trustworthy.

      In this research, we would develop and deploy our natural language human-AI teaming system as a behavioral health companion to provide personalized behavioral health support to a large-scale community population. Furthermore, we envision setting up an experimental environment based on our acquired knowledge to develop a prototype by collecting sensor signals and analyzing and developing machine learning and deep learning (AI) algorithms. Our research group has investigated, designed, and created machine learning algorithms. In this project, we utilize this knowledge, and codebases, analyze text, and develop a novel application. Students do not need any prior coding experience. 

      • Develop scientific literature review skills by reading and analyzing technical articles, blogs.
      • Real-world experience working with text, AI/ML models and tools for preparation for research in AI/ML in industry.
      • Utilize ML tools such as Weka to analyze the data and showcase ML applications.
      • Improve communication and scientific writing skills.
      • Present research results
      • Read papers and technical articles
      • Annotate text data and understand ML tools such as Weka
      • Showcase ML results using Weka
      • Execute and modify (if needed) a sample ML/AI source code and generate and analyze results
      • Meet weekly (in-person or virtually) and report progress

    • Students will work in this project in hybrid or online setting depending on the students' understanding and need. From time to time, student performance will be evaluated and changes will be accommodated accordingly.

    • Dr. Md Abdullah Al Hafiz Khan, mkhan74@kennesaw.edu 
      Abm. Adnan Azmee, aazmee@students.kennesaw.edu 
      Pradeep Rekapalli, prekapal@students.kennesaw.edu 

  • 2023-2024 First Year Scholars: Kareigh Gammon, Toni Kamau, and Johaan Kathilankal Jis

    • This project aims to leverage advanced computing technologies to gain comprehensive insights into the complex processes of DNA damage and repair. This cutting-edge research endeavor will play a critical role in advancing our understanding of the fundamental mechanisms that safeguard the integrity of genetic material, paving the way for groundbreaking discoveries in various fields, including medicine, biotechnology, and environmental science. The technology involved in this project includes Data Analysis, Data Visualization, Molecular Dynamics Simulations, etc.

      1. Define the terminology associated with research and theory in the field of in DNA repair research
      2. Describe past research studies in the field of DNA research
      3. Explain the rationale for choosing particular research methodologies and data analytic techniques
      4. Design a study to answer a research question in DNA research
      5. Develop a hypothesis
      6. Describe ethical research practices and apply those practices to a research study
      7. Collect data for DNA damage and repair research
      8. Analyze, synthesize, organize, and interpret data
      9. Work effectively as part of a team
      10. Present research/creative activity to an audience (e.g., poster, oral presentation)
      1. Research Meetings: Attend regular research meetings with your faculty mentor and other team members
      2. Literature Review: Spend time each week conducting literature reviews to understand the current state of knowledge regarding DNA damage and repair mechanisms
      3. Data Analysis: Work on data analysis tasks using computational tools and techniques
      4. Collaborative Discussions: Engage in collaborative discussions with other team members to exchange ideas, share insights, and troubleshoot challenges
      5. Data Visualization: Work on data visualization tasks to create clear and informative representations of research findings
      6. Project Documentation: Keep detailed records of your work, including methods, results, and observations
      7. Presentations and Reports: Prepare periodic presentations or reports summarizing your findings and progress

    • Hybrid, with weekly online meetings and monthly in-person meetings

    • Dr. Chloe Yixin Xie, yxie11@kennesaw.edu
      Dr. Lei Zhang, lzhang24@kennesaw.edu 

  • 2023-2024 First Year Scholars: Leo Janse van Rensburg

    • Website fingerprinting acts like a detective trying to guess what you've been up to online.

      Imagine someone looking at the digital 'footprints' left by your web browsing - the timing, direction, and size of the data you send and receive. Even if you use tools to keep your online activities private, like proxies, VPNs, or Tor, this detective could potentially piece together which websites you've visited.

      In this field, we use machine learning (think of it as a smart computer program that can learn from patterns) to better understand and protect online privacy. In the case of website fingerprinting, these smart programs can analyze your data footprints and guess the websites they originated from. In this project, we will study how to safeguard digital privacy or understand the tactics used to compromise it through an application of web security. 

      1. Improve research and technical skills.
      2. Develop literature reviews about machine learning for cybersecurity.
      3. Gain understanding and knowledge about computer networking.
      4. Implement web applications using real-world data.
      5. Improve communication skills and scientific writing skills.
      1. Read papers to gain knowledge about computer networking and cybersecurity.
      2. Literature review and report of findings regarding machine learning for cybersecurity.
      3. Develop a prototype for testing the proposed attacks and defenses.
      4. Attend weekly meetings and report weekly updates.

    • Hybrid

    • Dr. Liang Zhao, lzhao10@kennesaw.edu

  • 2023-2024 First Year Scholars: Morgan Bennett, Peter Souder, and Rachel Wilson

    • In today's digital age, children seem to be glued to screens of all kinds - from tablets to smartphones to video game consoles. While technology has its benefits, experts are expressing growing concerns about the effects of screen addiction on children's brain development. This project aims to unpack these challenges and the science behind them.

      This group research will combine articles from neurology, psychology, physiology, and education. It will explore the ways in which screen addiction can impact a child's ability to learn, socialize, and regulate their emotions. From attention deficit disorders to poor impulse control, we will uncover the range of obstacles that children face when overexposed to screens. Our goal is not to vilify technology but to provide parents, educators, and policymakers with the knowledge they need to make informed decisions about screen time. With this information, we hope to empower parents to set healthy boundaries for their children, teachers to create engaging classrooms that mitigate the negative effects of screen time, and policymakers to craft policy that promotes healthy screen use. Join us on this journey into the fascinating effort and study of children's brain development, where we will tackle the complex challenges posed by screen addiction to help children thrive in a constantly evolving digital landscape.

      This project is designed as a collaborative group project and seeks 4-5 qualified students motivated to research in a group environment. No particular background knowledge and coding skill is required. The project is to be led by Drs. Sakib (Healthcare Informatics and mHealth expert) and Ramos (Healthcare and Nursing expert).

    • This project will well-verse participant students in

      1. Understanding and Increased awareness of the impact of screen addiction on children's cognitive development, identification of strategies to mitigate or address risks associated with children's increased use of screens and technology, and investigation on designing practical solutions for parents, educators, and caregivers to help reduce the potential harm caused by overuse of screens.
      2. Assisting the supervisors in preparing and publishing a comprehensive literature review on “Confronting Children Brain Development Challenges Due to Screen-Addiction: Unpacking Perspectives from Stakeholders” in the conference/journal. 
      • Attend bi-weekly meetings with the project mentors as scheduled, and join lab meetings as schedule permits
      • Discuss and communicate findings from reading various sources
      • Participate in hands-on tutorial activities to have a better understanding of the concepts
      • Assist the mentors in writing a scholarly paper

    • Hybrid

    • Dr. Nazmus Sakib, nsakib1@kennesaw.edu
      Dr. Mary Ramos, mramos18@kennesaw.edu 

  • 2023-2024 First Year Scholars: Tahsin Kazi

    • To gain insights into the influence of physical human factors, like skin color, on AI models for non-invasive IoT devices, the professor and the student will commence the research by focusing on optical sensors, which find extensive application in numerous consumer-grade medical devices. This preliminary investigation aims to examine how these sensors interact with human subjects’ characteristics and affect the performance of AI models. The investigation will focus on analyzing the device and AI-model of a case study, GlucoCheck, an innovative solution for non-invasive blood glucose estimation. The investigation will focus on analyzing the device and AI-model of a case study, GlucoCheck, an innovative solution for non-invasive blood glucose estimation. The goal is to identify and quantify the impact of these physical human factors on the performance of the AI model, and subsequently develop strategies to mitigate their influence.

      1. Presentation for Student Scholar Symposium (Fall and Spring)
      2. Paper for Journal of Biomedical Healthcare.
      3. Presentations and dissemination of the resutls
      1. Meet with Dr. Valero every week to design activities for the project
      2. Be in the IoTaS lab for ~7 hours working on the project
      3. Report results every week

    • Face-to-Face

    • Dr. Maria Valero, mvalero2@kennesaw.edu

  • 2023-2024 First Year Scholars: Andrew Daugherty, Gabe Purcell, and Sonaj Sanders

    • Immersive and interactive storytelling in virtual reality (VR) is an emerging creative practice that has been thriving in recent years.

      Educational applications using immersive VR storytelling to explain complex science concepts have very promising pedagogical benefits because on the one hand, storytelling breaks down the complexity of science concepts by bridging them to people’s everyday experiences and familiar cognitive models, and on the other hand, the learning process is further reinforced through rich interactivity afforded by the VR experiences. However, some important design elements of the VR learning experiences, such as essential storytelling components and level of interactivity remain to be further explored to optimize learning experiences and outcomes.

      This project will be based on current research and design practices of storytelling and interactivity design in educational VR experiences and collaborate with a content domain expert in computational biology (Dr. Chloe Yixin Xie) with a special topic focus on DNA damage and repair. The goal of the project is to explore storytelling and interactivity design in educational VR through development of a working prototype and evaluation of its effectiveness on learning selected biology topic. 

      1. Learn the fundamentals of VR development process with Unity game engine.
      2. Explore effective storytelling design for learning with its essential components, such as story structure, plot, setting, characters, dialogue, etc.
      3. Familiarize with interaction and 3D user interface designs in VR
      4. Acquire essential research knowledge in the area of human-computer interaction (HCI) and collaborating skills for interdisciplinary projects.
      1. Meet weekly with PI and/or co-PI
      2. Give a brief report of project progress based on assigned tasks for each week. 

    • Hybrid

    • Dr. Lei Zhang, lzhang24@kennesaw.edu
      Dr. Chloe Yixin Xie, yxie11@kennesaw.edu

  • 2023-2024 First Year Scholars: Fareedah Ashiru

    • In this project, students will conduct research to understand the utilization of immersive technology. They will employ virtual and mixed-reality headsets alongside multisensory devices, delving into the integration of haptic feedback, spatial audio, and responsive visual interfaces within immersive environments. Based on this exploration, the research will focus on applying cutting-edge technology to enhance human perception, cognition, and physical well-being. Participants will have the opportunity to contribute to the advancement of knowledge in the field of immersive experiences. This will involve fostering innovative solutions for real-world challenges, all while developing a strong understanding of both theoretical investigations and practical implementations.

    • This project expects students to conduct high-impact research to address critical issues in multisensory immersive experiences. Also, developing prototypes for research projects utilizing immersive technology tools, including Virtual/Mixed Reality devices and haptic devices, within Unity or the Unreal game engine or similar is critical. The students will need to prepare and deliver presentations to showcase their comprehension of academic papers, new tools, or emerging technologies including analyzing the outcomes and limitations of published research. 

    • Weekly duties include weekly attending lab meetings and submitting reports on scientific research work involving the implementation of prototypes using tools such as Unity or Unreal Engine.

    • Hybrid

    • Dr. Sungchul Jung, sjung11@kennesaw.edu




©