Computer Engineering Commons^™

Optimizing Lightweight Authentication Protocols For Enhancing Security In Resource-Constrained Iot Devices, Anuj Jayeshbhai Naik

Electronic Theses, Projects, and Dissertations

IoT devices are increasingly being used in critical applications such as smart cities, healthcare, and industrial systems. However, due to their limited processing power, memory, and energy, traditional authentication methods are not suitable in these resource-constrained scenarios. To construct and evaluate a lightweight authentication system for such devices, this study incorporates secure, efficient cryptographic techniques. The following are the research questions: Q1) How can a hybrid lightweight authentication protocol that includes ECC and AES be used to safely and successfully link resource-constrained IoT devices? Q2) How can nonce-based challenge-response approaches to protect against replay threats be used to create lightweight …

Virtual Makeup And Technology Integration, Vishwa Bhatt

Electronic Theses, Projects, and Dissertations

The Virtual Makeup Streamlit application presents an advanced approach to digital cosmetic try-on by allowing users to apply makeup to their facial images in real time. This project uses computer vision and web technologies to create an interactive and user-friendly platform that capitalizes on the increasing popularity of virtual try-on solutions in the cosmetics industry.

At its core, the system uses effective facial detection and semantic segmentation techniques to recognize and separate facial areas such as lips and hair. Techniques such as U-Net and Resnet, and Midepipe are used to create accurate segmentation masks, which are essential for accurate makeup …

Lightlink: Visible Light Communication For Batteryless Devices With Variable Computational Load, Charles Phillips

All Theses

Visible Light Communication (VLC) devices have been experimentally proven to work as a suitable communication medium for batteryless devices. However, the effects of practical load have yet to be fully explored. To that end, we have developed LightLink, a new MAC and PHY layer protocol for VLC within batteryless devices, and have studied various ways that computational load can affect transmission accuracy in realistic scenarios. Our key findings point us towards an adaptive VLC reception system based on inferred environmental variables.

Graph Based Deep Reinforcement Learning Aided By Transformers For Multi-Agent Cooperation, Michael S. Elrod

All Theses

Mission planning for a fleet of cooperative autonomous drones in applications that involve serving distributed target points, such as disaster response, environmental monitoring, and surveil- lance, is challenging, especially under partial observability, limited communication range, and uncertain environments. Traditional path-planning algorithms struggle in these scenarios, particu- larly when prior information is not available. To address these challenges, I propose an innovative framework that integrates Graph Neural Networks (GNNs), Deep Reinforcement Learning (DRL), and transformer-based mechanisms for enhanced multi-agent coordination and collective task ex- ecution. My approach leverages GNNs to model agent-agent and agent-goal interactions through adaptive graph construction, enabling efficient …

Blockchain-Integrated Version Control For Secure And Transparent Software Supply Chains, Iwinosa W. Aideyan

All Theses

The software supply chain encompasses all stages of software development and delivery from initial coding and version control to integration and deployment. As development environments become increasingly distributed and reliant on external dependencies, ensuring the integrity, auditability, and consistency of code changes has become a pressing challenge. Traditional version control systems like Git, while effective for collaboration and tracking revisions, do not inherently provide tamper-evident commit histories. Features such as history rewriting (e.g., git rebase, git push --force) can be exploited to manipulate commit logs without detection, posing risks in security-sensitive domains. This thesis proposes a blockchain-integrated version control framework …

Privacy Implications Of Data Collection In Android Automotive Os, Bulut Gözübüyük

All Theses

Modern vehicles have become sophisticated computational and sensor systems, as evidenced by advanced driver assistance systems (ADAS), in-car infotainment, and autonomous driving capabilities. They collect and process vast amounts of data through various onboard subsystems. One significant player in this landscape is Android Automotive OS (AAOS), which has been integrated into over 100 million vehicles and has become a dominant force in the in-vehicle infotainment (IVI) market. With this extensive data collection, privacy concerns have become increasingly crucial. The volume of data gathered by these systems raises questions about how this information is stored, used, and protected, making privacy a …

Multimodal Emotion Recognition For Human-Robot Interaction Across Neuro-Diverse Populations., Ruchik Mishra

Electronic Theses and Dissertations

This dissertation explores the integration of multimodal data streams and artificial intelligence pipelines to understand human affect in neurotypical and children with Autism Spectrum Disorder (ASD). This dissertation captures human affect in the context of human-robot interaction. For this, multiple studies have been presented with both children with ASD and neurotypical adults. This dissertation makes four contributions: 1) The first study introduces autonomy during perspective-taking teaching sessions by making verbal content generation through large language models (LLMs). This system is the first of its kind for teaching perspective-taking in a semi-autonomous manner under the supervision of domain experts. Furthermore, this …

Propasafe: A Bert-Based Offline Tool For Propaganda Detection, Vivek Sharma, Mohammad Mahdi Shokri, Shweta Jain, Sarah Ita Levitan, Elena Filatova

Publications and Research

In an era marked by the rapid consumption of digital news, the proliferation of propaganda poses significant threats to democratic values and informed decision-making. We propose a novel framework that prioritizes user privacy while assisting in the automatic detection of propaganda in news articles, allowing users to sift through the rhetoric to read the relevant objective news. As a demonstration of this framework, we present Propasafe, a BERT-based browser extension designed to alert users to propagandist tones in news articles. By highlighting instances of propaganda-like language in real-time, Propasafe empowers users to critically engage with news content, promoting objective understanding …

A System And Method For Measuring Spatially Varying Surface Appearances With A Study Of Feathers, Jessica Baron-Lis

All Dissertations

Real-world materials, particularly biological structures such as feathers exhibit complex appearances that vary spatially across their surfaces. The field of computer graphics provides a means of understanding such surfaces through material modeling which uses both analytical models and data acquired from light-surface interactions. There are many efforts within the past decade in measuring materials for graphics, but common limitations in these works include not accounting for spatially varying properties and reliance on neural networks and synthetic datasets.

Feathers from modern birds present diverse appearances due to how light interacts with their unique hierarchical microstructures. Variations in those structures lead to …

The Role Of Ai In Enhancing Teamwork, Resilience And Decision-Making: Review Of Recent Developments, Satyadhar Joshi

Harrisburg University Other Works

This paper explores the transformative impact of artificial intelligence (AI) on organizational teamwork, decision-making, and resilience. This paper furthur reviews recent literature on the integration of Artificial Intelligence (AI) in various organizational functions, focusing on its impact on innovation management, leadership paradigms, and organizational resilience. We provide groundwork required to enhance frameworks that can integrate cognitive scaffolding with antifragile team dynamics, employing behavioral economics and neurocognitive principles. We introduce methodologies for enhancing team resilience through adaptive AI systems, cross-training interventions, and pre-mortem simulation techniques. The framework addresses key challenges in confirmation bias mitigation, cultural dimension alignment, and vigilance decrement prevention. …

Robot-Integrated 4d Building Information Modeling (4d Bim): Framework For Planning Safe Autonomous Construction Operations In Dynamic Environments, Hafiz Oyedimeji Oyediran

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

In the construction industry, the use of autonomous robots is considered a solution to overcome the heavy reliance on human workers to perform repetitive, strenuous, and hazardous tasks. While these robots offer the advantage of autonomous operation, ensuring their safe and efficient integration within construction sites requires precise planning. Such planning must account for the varying project complexities such as scope, site layout, tasks, timelines, existence of human workers, and other spatiotemporal conditions of the construction site. Currently, there are no methods to safely plan autonomous robot operations considering these factors within the overarching construction planning process. Thus, autonomous robots …

Sensor Data Fusion For Air Quality Monitoring, Mirna Hesham

Theses and Dissertations

Since traditional air quality monitoring methods often rely on geographically sparse and costly air quality monitoring stations, image-based air quality method- ologies are recently offering a compelling alternative that utilizes images from sources like satellites, traffic cameras, and even smartphones to monitor pollution levels by using estimation models, image-processing techniques, and deep-learning models. In this thesis, we first conduct a systematic review, in which we categorize and discuss the existing literature work. Moreover, we introduce a novel, multi- modal dataset designed to address the limitations of existing datasets, which are restricted in size, geographical coverage, and fixed-scene imagery, impeding the …

Advanced Day-Ahead Scheduling Of Hvac Demand Response Control Using Novel Strategy Of Q-Learning, Model Predictive Control, And Input Convex Neural Networks, Rahman Heidarykiany, Cristinel Ababei

Electrical and Computer Engineering Faculty Research and Publications

In this paper, we present a Q-Learning optimization algorithm for smart home HVAC systems. The proposed algorithm combines new convex deep neural network models with model predictive control (MPC) techniques. More specifically, new input convex long short-term memory (ICLSTM) models are employed to predict dynamic states in an MPC optimal control technique integrated within a Q-Learning reinforcement learning (RL) algorithm to further improve the learned temporal behaviors of nonlinear HVAC systems. As a novel RL approach, the proposed algorithm generates day-ahead HVAC demand response (DR) signals in smart homes that optimally reduce and/or shift peak energy usage, reduce electricity costs, …

Understanding The Breadth And Impact Of The Ias [President’S Message], Ayman El-Refaie

Electrical and Computer Engineering Faculty Research and Publications

No abstract provided.

Integrating Blockchain Technology Into Telemedicine: A Framework For Enhancing Data Privacy And Security, Harsha Sammangi, Aditya Jagatha, Jun Liu

Research & Publications

This paper presents a blockchain-based framework designed to enhance data privacy, integrity, and security in telemedicine systems. The proposed architecture employs distributed ledger technology to ensure transparency, traceability, and immutability of patient data exchanges among healthcare providers. Smart contracts automate access permissions and auditing processes, reducing the risks of unauthorized data sharing. The study evaluates the framework’s performance in secure data handling, highlighting blockchain’s role in fostering patient trust and resilience against cyberattacks in remote healthcare environments.

Decentralized Multi-Hop Federated Reinforcement Learning For Energy-Efficient And Secure Routing In Lorawan-Based Smart City Infrastructure, Harsha Sammangi, Aditya Jagatha, Jun Liu

Research & Publications

This paper proposes a decentralized hybrid framework that integrates Federated Learning (FL) and Reinforcement Learning (RL) to enable energy-efficient and secure multi-hop routing in LoRaWAN-based smart city networks. The method allows local model training at gateways and relay nodes, combining real-time routing decisions with privacy-preserving federated aggregation. Key metrics such as residual energy, link quality, and node trust levels are embedded into the reward function, and lightweight encryption plus differential privacy safeguard routing metadata. Simulation results demonstrate substantial gains in packet-delivery ratio, latency, network lifetime and resilience to adversarial attacks when compared to traditional routing protocols.

Optimization-Based Distributed Controller For Multi-Agents System In Microgrid Secondary Control, Fahad S. Alshammari, Ayman El-Refaie, Saleh Alyahya, Sheroz Khan

Electrical and Computer Engineering Faculty Research and Publications

Micro-grids function to connect to power system power produced by the renewable energy resources. In islanded micro-grids, grid-forming units collaborate to maintain the micro-grids voltage and frequency by utilizing droop control technique that includes primary, secondary and tertiary levels. Secondary control intervenes to improve power sharing and restore voltage and frequency to their nominal levels. However, the conventional droop control applied to a grid with mismatched line parameters experiences a trade-off between reactive power sharing and voltage regulations. This paper applies real-time trajectory tracking convex optimization to ensure by communicating power sharing between units in a consensus topology. The optimization …

Real Time Object Detection Using Yolo, Rohit Malik, Manisha Kumari, Sanghoon Lee

Symposium of Student Scholars

This project explores the implementation of real-time object detection using the You Only Look Once (YOLO) architecture. Leveraging its speed and accuracy, we developed a system capable of identifying and localizing multiple objects within live video streams. Our implementation focused on optimizing YOLO's performance for real-time applications, specifically addressing the trade-off between speed and accuracy.

We employed a pre-trained YOLO model and fine-tuned it on a custom dataset tailored to specific object classes. This fine-tuning process aimed to enhance the model's ability to recognize objects in our target environment. The system was implemented using Python and the OpenCV library, enabling …

Campus Navigator: A Mobile App For Seamless University Navigation, Hafsa Mohammed, Ali Rahimzadehfard, Rachab Wilson, Mathias Rossi, Turaj Ashuri, Amir Ali Amiri Moghadam

Symposium of Student Scholars

Navigation services play a big role in everyone’s daily lives, from directing them on new roads to guiding them through buildings. Outdoor navigation services have evolved from physical maps to digital ones like Google Maps for ease of use and accessibility. Upon conducting literature research, the team found that many navigation apps lack clear and accurate instructions for how to navigate university campuses such as Marietta campus. Due to the size of KSU’s Marietta campus and its buildings, effortless navigation has been a common challenge for students, faculty, and visitors alike. Additionally, all buildings are referred to by letters, numbers, …

Sandrapp: A Digital Intervention To Enhance Social Connectivity And Emotional Support Among Older Adults, Pavan Chowdary Chilukuri, Purna Chandu Anukula

Symposium of Student Scholars

Social isolation and loneliness are significant challenges affecting the well-being of older adults, often leading to adverse mental and physical health outcomes. Prolonged isolation has been linked to increased risks of depression, anxiety, cognitive decline, and chronic illnesses such as hypertension and cardiovascular diseases. As digital technology continues to evolve, innovative solutions have emerged to address these issues and foster meaningful social interactions for older adults.

SANDRApp is a user-friendly digital platform designed to reduce loneliness and enhance social connectivity among older adults. The platform caters to three primary user groups: (1) families with elderly loved ones living far away, …

Low Cost Additive Manufacturing Of Segmented Stator Composite Polymer Permanent Magnet Dc Motors, Ben Goldberg, Jordan Bailey, Connor Hawkins, Colin Haskins, Razvan Voicu

Symposium of Student Scholars

This study presents a novel approach to the design, manufacture, and optimization of segmented stators for composite construction axial flux permanent magnet DC motors. Traditional axial flux stator manufacturing is both challenging and expensive, creating a bottleneck in rapid prototyping and innovation. To overcome these limitations, the stator is divided into individually fabricated segments using advanced composite polymer materials and low-cost additive manufacturing techniques. This segmentation not only drastically reduces production complexity and cost but also allows for customized coil geometries that maximize the surface area for improved heat dissipation.

A key innovation of our design is the integration of …

Preparing Students For The Quantum Era: Qml Training And Applications, Triveni Kandimalla, Valentina Nino

Symposium of Student Scholars

Quantum Machine Learning (QML) emerges as a transformative approach to addressing the growing complexities of modern data processing and computational challenges. Classical machine learning (CML) techniques, while powerful, face limitations in handling vast amounts of high-dimensional data and solving complex optimization problems efficiently. Despite its potential, QML remains underrepresented in academia, highlighting the need for accessible, hands-on learning experiences and knowledgeable faculty. This project seeks to advance QML education by incorporating it into diverse curricula, creating practical learning materials, and fostering workforce readiness. Using Google Colab, an open source labware has been designed to provide interactive learning modules (M0 to …

Human-Ai Teaming For Academic Performance Analysis, Kendarius Ward, Elise Hernandez, Tom Antony, Md Abdullah Al Hafiz Khan, Kazi Aminul Islam, Abm Adnan Azmee

Symposium of Student Scholars

Educators today often work with students who are struggling academically, but limited time and resources make it difficult to uncover the root causes and provide timely assistance. Artificial intelligence (AI) is a growing, viable tool for analyzing large datasets and solving problems in different domains; however, human expertise is required to enhance the AI model’s performance. This study will utilize human-AI teaming to assess student performance based on factors such as their academic involvement, hours spent studying, and grade-point-average, among others. These findings will help instructors better grasp each student's academic needs. By incorporating humans into the AI pipeline, we …

Sustainable Smart Farming Device With Leafit Adaptive Growth Technology, Saville Atkins, Anthony Iwejuo, Julian Pitts, Luis Mercado, Rachnicha Rojjhanarittikorn, Sandip Das, Hai Ho

Symposium of Student Scholars

For farmers, gardeners, and horticulture enthusiasts worldwide, one immutable reality is that maintaining a consistent physical presence to care for plants is not always feasible. In addition, different plants have unique needs for watering, nutrients, and environmental conditions to thrive. Failing to meet these specific needs can result in poor plant health, reduced yields, and inefficient resource usage. In this research project, we have designed and developed ‘LeaFit’ – a cutting-edge Internet of Things (IoT) device that offers a sophisticated and sustainable smart farming and gardening solution. Equipped with intelligent soil moisture, ambient temperature, humidity, and light sensors, LeaFit autonomously …

A Comprehensive Analysis Of Recognition Of Hand Gestures Using Machine Learning, Shivani Shivani, Satinder Bal Gupta

Makara Journal of Technology

Hand gestures are a natural means of conveying information and thus, there is an increasing interest in utilizing gestures for communication with computers. This study focuses on systematically reviewing different machine learning algorithms while assessing their working mechanisms and accuracy. Articles were analyzed for comparing the performance of K-Nearest Neighbors (KNN), Random Forest (RF), Support Vector Machines (SVM), Naive Bayes (NB), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN). In accordance with input data, intricacy of gestures, processing resources, and real-time demands, the study shows that each technique has distinct advantages and disadvantages. RNN showed the best accuracy of …

Design Of A Teleoperabletendon-Driven Robotic Hand, Zachary Giese, Joseph Gober, Samuel Grisham, Avery Mahan, Aspen White, Brayden May, Aspen White

ATU Scholars Symposium

This work presents the design, implementation, and validation of a 3D-printed tendon-driven robotic hand with a bi-directional wireless control system. The robotic hand emulates human anatomical principles, focusing on replicating flexion and extension mechanisms of the metacarpophalangeal (MCP), proximal interphalangeal (PIP), and distal interphalangeal (DIP) joints via a tendon-pulley system. Iterative prototyping resolved initial challenges in joint stiffness, tendon routing, and servo interference, culminating in a design where a single servo drives both flexion and extension for each joint using a bidirectional tendon control mechanism. A reliable bidirectional wireless communication framework, using Arduino Nano Every microcontrollers and NRF24L01 modules, enables …

Scalable Distributed Ai: Low-Cost, High-Performance Computing With Jetson Nano And Dask, Kesava Manikanta Chirumamilla

ATU Scholars Symposium

No abstract provided.

Deep Learning-Based Multi-Class Classification Of Breast Cancer Ultrasound Images Using Convolutional Neural Networks, Andres E. Dewendt Urdaneta

ATU Scholars Symposium

The National Cancer Institute forecasts 2,001,140 cancer diagnoses in 2024, with approximately 600,000 expected deaths. Breast cancer is projected to be the most prevalent, with about 310,000 cases. Early diagnosis is critical to improving outcomes, and various diagnostic technologies, including imaging, biopsies, and blood tests, play a vital role. Image testing methods include X-rays, ultrasounds, magnetic resonance imaging (MRI), and PET scans. Artificial intelligence (AI) has recently significantly improved cancer detection, improving speed, accuracy, and effectiveness. This research project uses a convolution neural network (CNN) to analyze ultrasound breast images, classifying them as benign, malignant, or normal. Our CNN model …

Empowering Mental Support Health Through Ai Chatbot, Anish Ilapaka

ATU Scholars Symposium

The growing prevalence of mental health concerns worldwide underscores the urgent need for accessible, scalable, and supportive solutions. Artificial Intelligence (AI) has emerged as a promising tool in this domain, capable of delivering immediate and empathetic interactions to complement traditional methods of mental health care. This project introduces a conversational AI system to assist individuals experiencing mental health challenges. The proposed system is built on a LLaMA model fine-tuned with a dataset of 10,000 mental health-related dialogues; the system leverages advanced natural language processing and machine learning techniques for meaningful engagement. The core functionality of this tool lies in its …

Empowering Students Through Project-Based Learning In Computer Science: Connecting Real-World Problems To Classroom Innovation, Roza Shaimurat, Faith Bogrek, Bethany Ratermann, Shruti Bhandari, Tolga Ensari

ATU Scholars Symposium

Project-Based Learning (PBL) is a powerful approach in computer science education that moves beyond technical instruction to cultivate problem-solving, adaptability, and resilience. Unlike traditional methods, PBL immerses students in real-world challenges, where failure becomes a steppingstone to success. This paper explores how PBL fosters deep learning through hands-on projects, such as robotics competitions and smart technology solutions, bridging the gap between classroom concepts and real-world innovation. Despite its unpredictability and instructional challenges, PBL ignites student engagement, instills a sense of ownership, and prepares learners for the evolving demands of the tech industry. By embracing PBL, educators not only equip students …