Digital Commons Network^™

Emotion Detection Using Ensemble Learning, Priya Harika Yerapothu

Master's Projects

Emotion detection is gaining exponential necessity in today’s technological age. This research seeks to delve into ways conversational AI could be enhanced by integrating emotional intelligence using an ensemble learning approach. Traditional machine learning along with advanced neural network architectures are implemented to improve the understanding and intricacies of emotion detection from textual data. The dataset we use is GoEmotions dataset, annotated with 27 emotional labels, to conduct a detailed analysis of emotion recognition. Various machine learning models, such as HistGradientBoosting, LightGBM, CatBoost, and MLP, will be evaluated side by side with advanced models of Bidirectional Long Short-Term Memory (BiLSTM) …

Optimized Community Detection Across Distributed Heterogeneous Servers, Akash Narang

Master's Projects

The exploration of community detection is crucial across various fields, including marketing, and biological research. This area has evolved from non-overlapping communities to recognize nodes as part of multiple overlapping communities. Current research continues to uncover these dynamics. The main challenge is identifying overlapping communities in graphs with billions of nodes and edges. This paper aims to enhance methodologies for community detection in parallel for unprecedentedly large and complex networks. We introduce the HeteroNodesAdapter algorithm, which supports heterogeneous worker nodes and optimized load distribution in graph stream processing. Additionally, we propose the TailBalancedCommunitySize algorithm to find an optimum community size, …

Community Detection Using Deep Learning: Variational Graph Autoencoder Enhanced With Leiden And K-Truss Techniques, Jyotika Hariom Patil

Master's Projects

Community detection in networks is essential for understanding the complex structures of connected systems. Traditional deep learning (DL) methods such as Graph Neural Networks (GNNs) and Graph Convolutional Networks (GCNs) have shown promised results in supervised tasks, like classification, but often fail in unsupervised tasks like community detection because of the lack of labels. Self- supervised approaches where we integrate crucial community information offer a solution. This project seeks to explore DL methods for community detection, focusing specifically on using Graph Variational Autoencoders (VGAEs). While classical approaches can efficiently handle small to medium-sized networks, they typically struggle with larger-sized structures. …

Influence Maximization Using Triadic Closures, Communities, And Quotas, Matthew Fu

Master's Projects

Online social networks have exploded in popularity in the last decade. In addition, traditional advertising methods such as television advertising have greatly decreased. This allows companies to utilize viral marketing more effectively. With viral marketing, companies can spread information on a product to a social network by reaching out to a small group of early adopters, who will go on to inform the people around them of the product. The problem is selecting the early adopters that can maximize the spread of influence. The Influence Maximization (IM) problem is finding a social network’s most influential (early adopters) starting nodes, called …

Employing Large Language Models And Retrieval Augmented Generation For Enhanced Predictive Flexibility In Cancer Mortality Prediction, Mridang Kejriwal

Master's Projects

Today, cancer is a major health risk to thousands of people, and there are over a two-hundred different types of cancer. Luckily, over the past several years, the outcomes and survival rates have increased, all thanks to machine learning, specifically Recurrent Neural Networks (RNN) and Long Short-Term memory (LSTM) networks. However, the current prognostic models don’t allow healthcare professionals to adapt the variables to mimic all the different features of every type of cancer, resulting in a model that works but is not as accurate as it could be. This study explores improving the accuracy and adaptability of the current …

Temporal Dynamics In Diabetes Prediction: A Sensor-Driven Time-Series Exploration, Monica Meduri

Master's Projects

Diabetes is a lifelong illness that, if not detected or managed appropriately, turns into serious complications. Correct glucose forecasting is critical to ensuring timely interventions, thereby minimizing risks of hyperglycemia and hypoglycemia, and optimizing the management strategies of the disease. Classical machine learning models have been applied in the blood glucose forecasting problem for a long time, however, usage of transformer-based architectures is still scarce within the literature. Due to the self-attention mechanism, transformers can capture temporal relationships very effectively, which makes them suitable for time-series data. TFT is a novel framework proposed here to utilize time-series data from CGM …

Comparison Of Protein Structures Predicted By Genai Tools In A Zero-Shot Manner, Kruthi Shankar Rao

Master's Projects

Generative AI models have vast applications and one such critical application explored in this study is protein structure prediction. The 3D structures of proteins determine their function. Our study mainly focuses on using generative AI models such as ESMFold and ColabFold to predict and examine naturally occurring and mutated sequences. The workflow begins with collecting antimicrobial resistance (AMR) and toxin-antitoxin (TA) protein data. The sequences are applied over pretrained AI models to predict protein structures. Following this, models are fine-tuned with original and mutated target datasets. A comparison of models’ performances is done using metrics such as root mean square …

Detecting Crustose Coralline Algae (Cca) In Marine Photos Using Mask R-Cnn, Vrushali Harshwardhan Deshpande

Master's Projects

Coral reefs, made up of thousands of polyps - tiny sac-like marine invertebrates sea anemones and jellyfish, are important to marine ecosystems and prevent loss of life by acting as a natural barrier against storms, floods, and waves. These reefs support a wide range of species, many of which are underexplored and new species being discovered regularly. Crustose coralline algae (CCA) is one of the vital algal species that provides reef structure. Studying the abundance of CCA is important in helping marine biologists analyze coral reef health while understanding the impact of climate change on the marine lifeforms. This study …

An Ai-Based Conceptual Framework To Improve Program Management Of Complex Systems, Michael D. Parrish, Steven Corns

Engineering Management and Systems Engineering Faculty Research & Creative Works

With evolving technologies, changing requirements, and limited budgets, governments and industries need to consider new methodologies to help streamline program lifecycle management, from cradle to grave, to ensure projects are delivered on time, on budget, and to the expected performance standards. Traditional approaches fail to adequately address the added complexities of System of Systems programs such as integration, interoperability, and variable lifecycle of subcomponents. The objective of this study is to assess and address the research question - can a new acquisition approach be designed to address and improve program lifecycle management of complex systems? A comparison study, using the …

Optimized Gadolinium-Do3a Loading In Raft-Polymerized Copolymers For Superior Mr Imaging Of Aging Blood-Brain Barrier, Hunter A. Miller, Aaron Priester, Evan T. Curtis, Krista Hilmas, Ashleigh Abbott, Forrest M. Kievit, Anthony J. Convertine

Materials Science and Engineering Faculty Research & Creative Works

The development of gadolinium-based contrast agents (GBCAs) has been pivotal in advancing magnetic resonance imaging (MRI), offering enhanced soft tissue contrast without ionizing radiation exposure. Despite their widespread clinical use, the need for improved GBCAs has led to innovations in ligand chemistry and polymer science. We report a novel approach using methacrylate-functionalized DO3A ligands to synthesize a series of copolymers through direct reversible addition-fragmentation chain transfer (RAFT) polymerization. This technique enables precise control over the gadolinium content within the polymers, circumventing the need for subsequent conjugation and purification steps, and facilitates the addition of other components such as targeting ligands. …

Effect Of Ph And Hydroxyapatite-Like Layer Formation On The Antibacterial Properties Of Borophosphate Bioactive Glass Incorporated Poly(Methyl Methacrylate) Bone Cement, Kara A. Hageman, Rebekah L. Blatt, William A. Kuenne, Richard K. Brow, Terence E. Mciff

Materials Science and Engineering Faculty Research & Creative Works

Infection is a leading cause of total joint arthroplasty failure. Current preventative measures incorporate antibiotics into the poly (methyl methacrylate) (PMMA) bone cement that anchors the implant into the natural bone. With bacterial resistance to antibiotics on the rise, the development of alternative antibacterial materials is crucial to mitigate infection. Borate bioactive glass, 13–93-B3, has been studied previously for use in orthopedic applications due to its ability to be incorporated into bone cements and other scaffolds, convert into hydroxyapatite (HA)-like layer, and enhance the osseointegration and antibacterial properties of the material. The purpose of this study is to better understand …

Multiple Imputation For Robust Cluster Analysis To Address Missingness In Medical Data, Arnold Harder, Gayla R. Olbricht, Godwin Ekuma, Daniel B. Hier, Tayo Obafemi-Ajayi

Mathematics and Statistics Faculty Research & Creative Works

Cluster Analysis Has Been Applied To A Wide Range Of Problems As An Exploratory Tool To Enhance Knowledge Discovery. Clustering Aids Disease Subtyping, I.e. Identifying Homogeneous Patient Subgroups, In Medical Data. Missing Data Is A Common Problem In Medical Research And Could Bias Clustering Results If Not Properly Handled. Yet, Multiple Imputation Has Been Under-Utilized To Address Missingness, When Clustering Medical Data. Its Limited Integration In Clustering Of Medical Data, Despite The Known Advantages And Benefits Of Multiple Imputation, Could Be Attributed To Many Factors. This Includes Methodological Complexity, Difficulties In Pooling Results To Obtain A Consensus Clustering, Uncertainty Regarding …

Optical Fiber Sensors Based On Advanced Vernier Effect - A Review, Wassana Naku, Jie Huang, Chen Zhu

Electrical and Computer Engineering Faculty Research & Creative Works

The Optical Vernier Effect Has Emerged as a Powerful Tool for Enhancing the Sensitivity of Optical Fiber Interferometer-Based Sensors, Ushering in a New Era of Highly Sensitive Fiber Sensing Systems. While Previous Research Has Primarily Focused on the Physical Implementation of Vernier Effect-Based Sensors using Different Combinations of Interferometers, Conventional Vernier Sensors Face Several Challenges. These Include the Stringent Requirements on the Sensor Fabrication Accuracy to Achieve a Large Amplification Factor, the Necessity of using a Source with a Very Large Bandwidth and a Bulky Optical Spectrum Analyzer, and the Associated Complex Signal Demodulation Processes. This Article Delves into Recent …

Electromagnetic-Circuital-Thermal-Mechanical Multiphysics Numerical Simulation Method For Microwave Circuits, Huan Huan Zhang, Zheng Lang Jia, Peng Fei Zhang, Ying Liu, Li Jun Jiang, Da Zhi Ding

Electrical and Computer Engineering Faculty Research & Creative Works

An electromagnetic-circuital-thermal-mechanical Multiphysics numerical method is proposed for the simulation of microwave circuits. The discontinuous Galerkin time-domain (DGTD) method is adopted for electromagnetic simulation. The time-domain finite element method (FEM) is utilized for thermal simulation. The circuit equation is applied for circuit simulation. The mechanical simulation is also carried out by FEM method. A flexible and unified Multiphysics field coupling mechanism is constructed to cover various electromagnetic, circuital, thermal and mechanical Multiphysics coupling scenarios. Finally, three numerical examples emulating outer space environment, intense electromagnetic pulse (EMP) injection and high-power microwave (HPM) illumination are utilized to demonstrate the accuracy, efficiency, and …

Impact Of Ai On The Hri Dynamic In Search And Rescue Operations Using Uav Swarms, Jordan Morrow, Maciej Jan Zawodniok, Anhar Sami Mohammed

Electrical and Computer Engineering Faculty Research & Creative Works

Artificial intelligence (AI) offers significant benefits in search and rescue applications by enhancing the efficiency and effectiveness of the search. However, an over-reliance on AI can hinder the operation due to biases embedded in the underlying algorithms. This partiality, if left un-monitored, can pose a risk to the safety of those in need of disaster relief. Typically manifests into inaccuracies in the decision-making processes and if not carefully monitored can cause larger issues. This paper extends the knowledge presented in a previous work, which presents the design and modeling of search and rescue operations using unmanned aerial vehicle (UAV) swarms. …

High-Sensitivity Fabry-Perot Interferometric Sensor Based On Microwave Photonics With Phase Demodulation, Ruimin Jie, Hongkun Zheng, Osamah Alsalman, Jie Huang, Chen Zhu

Electrical and Computer Engineering Faculty Research & Creative Works

Optical fiber sensors have emerged as vital tools in various applications. Among them, Fabry-Perot interferometers (FPIs), have gained prominence due to their compactness and versatility in sensor design. Microwave photonics (MWP) techniques offer enhanced performance and flexibility for developing optical sensor interrogation methods. This paper proposes and experimentally demonstrates a novel MWP interrogation technique based on phase measurement for short-cavity FPI sensors. The technique utilizes the phase response of the FPI sensor within an MWP-assisted single radio frequency bandpass filter, providing improved sensitivity and dynamic sensing capabilities compared to traditional methods. Simulation and experimental results validate the effectiveness of the …

Design Of The Tm010 Mode Cylindrical Cavity Resonator For Pcb Dielectric Characterization, Reza Asadi, Chaofeng Li, Seyedmehdi Mousavi, Seyed Moastafa Mousavi, Reza Vahdani, Xiaoning Ye, Donghyun Kim

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents the study of the TM₀₁₀ mode cylindrical resonator, which can be used for printed circuit board (PCB) material properties extraction, e.g., the dielectric constant (Dk) and the loss tangent (Df) extraction. The theoretical formulas of the resonance frequency and Q-factor of the resonator are presented. In real measurement, the TM₀₁₀ mode cylindrical cavity resonator needs to be excited by the probe. The study emphasizes the impact of probe orientation, location, and field distribution on the accuracy of material property extraction. The relationship between cavity dimensions and resonance frequency is explored, highlighting the influence of cavity …

Lifelong Direct Error-Driven Learning For Uav Altitude Estimation In Different Weather Conditions, Shirin Nasr-Esfahani, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

While deep neural networks achieve remarkable visual perception capabilities for UAV position and orientation estimation, their resilience to different weather conditions still needs improvement. These models often suffer from catastrophic forgetting when adapted to new environments, losing previously acquired knowledge. Lifelong learning methods aim to balance learning flexibility and memory stability. In this paper, we present an image-based approach to estimate the relative altitude of a UAV using 2D images under varying weather conditions, including sunny, sunset, and foggy scenarios. Our experiments demonstrate significant performance degradation when the model is trained sequentially on different weather datasets, especially when new images …

Prediction Interpretations Of Ensemble Models In Chronic Kidney Disease Using Explainable Ai, K M Tawsik Jawad

Browse all Theses and Dissertations

Chronic Kidney Disease (CKD) poses significant health and financial threat to millions of patients all around the world. The irreversible nature of this disease not just leads to comorbid diseases like Diabetes Mellitus, Hypertension, Anemia, Bone Disease, Neurological Implants etc. It can permanently damage the kidney by progressing to Acute Kidney Injury (AKI) or End Stage Renal Diseases (ESRD). The risk factors of CKD become more dangerous as patients suffering from it have little to no idea about the presence of CKD in their body until it takes the shape of AKI or ESRD. There are severe economic burdens for …

Biomechanical Simulation Of Cardiovascular Implantable Electronic Device Leads With Residual Properties, Anmar Mahdi Salih

Browse all Theses and Dissertations

Implantable leads used in pacemakers, defibrillators, and cardiac resynchronization therapy are designed for in-vivo applications, yet their longevity is inevitably shaped by the conditions within the human body. The mechanical behavior of these leads can be affected over time, necessitating the evaluation of their residual properties. Two main insulators, silicone, and polyurethane are commonly used for the outer insulation of cardiac leads. Understanding the long-term performance of these insulators is crucial for ensuring the reliability and safety of cardiac implantable devices. The research aims to assess the long-term mechanical properties and performance of implantable leads utilized in cardiovascular implantable electronic …

Infant Molds For Cleft Deformities, Hannah Brunow, Drew Reinbolt, Rhonda Troyer, Christian Miller

Williams Honors College, Honors Research Projects

Cleft lip and palate are very common birth defects where the roof of a baby's mouth and lip do not form properly while in the womb. Babies born with cleft lip or palate can undergo surgery after going through a process to make the initial gap smaller through incrementally smaller, retainer-like appliances. We will be trying to find a way to improve the pre-surgery process by implementing 3D printing. We will be performing this research for a craniofacial orthodontist at Akron Children's Hospital. We hope that our success will lead to a decrease in the amount of time spent making …

Effects Of Energy Drink Additives On Crayfish Metabolism, Katherine Paltz

Williams Honors College, Honors Research Projects

The effects of caffeine and additives commonly found in energy drinks were tested on crayfish to record changes, if any, in their metabolism. Three experimental groups were studied: 1. Caffeine; 2. Caffeine + Glucuronolactone; 3.) Caffeine + Glucuronolactone + Taurine. Caffeine is a common stimulant used to improve mental awareness, headaches, memory, and athletic performance. Glucuronolactone is connected with cardiovascular issues and aggressive behavior. Taurine is said to improve mood and focus. The experiment was performed at two different caffeine levels: 600mg and 1200mg for an initial 1 hour of exposure and 10 hours after exposure used as a pseudo-baseline. …

Course-Based Undergraduate Research Experiences (Cure) In Engineering Technology, Bill Hutzel, Craig Zywicki, Stephanie M. Gardner

School of Mechanical Engineering Faculty Publications

Although most universities provide excellent research experiences for outstanding undergraduate students, the number of interested students typically outstrips the supply of faculty and graduate student mentors. Addressing this shortfall is the reason Course-based Undergraduate Research Experiences (CUREs) were created. CUREs face obvious challenges because they operate at a larger scale than the traditional apprentice-based model for undergraduate research, creating resource issues for experimental research that requires equipment, laboratory space, and staff oversight. To help address these hurdles, one university has created a professional development program that provides training, collegial mentoring, and financial support to interested faculty. This paper provides an …

Degradable Staples And Delivery Device, Meha Elango, Jessica Cabrera, Makayla Scarpitti, Kareemat Melaiye

Williams Honors College, Honors Research Projects

The scope of this project is to design a method to secure skin grafts to healthy tissue. The ultimate goal for the proposed method is to be dissolvable in some form. Currently, skin grafts procedures utilize staples in most cases to hold a skin graft in place, but there are disadvantages that come with it. Staples are easy to place, but time consuming during the removal procedure. They also cause a lot of pain and discomfort for the patient. The goal of this project is to determine a way a secure skin grafts to healthy skin in order to reduce …

Aggregation-Induced Emission Probe For Alzheimer's Detection And Treatment Screening, Gemini Ramlo

Williams Honors College, Honors Research Projects

The proposed project is to research if ROF-2, an aggregation-induced emitter, can be used to screen medications for Alzheimer's Disease and to accurately detect this disease, along with its progression. This will be done through multiple incubation periods using different identifiers that have already been solidified within Alzheimer's research to prove its ability and accuracy within screening and detection regarding this disease.

Development Of Advanced Multi-Nozzle Multi-Material 3d Printing, Mohammed Al Ali

Wayne State University Dissertations

Extrusion-based 3D printing methods, such as Direct Ink Writing, are extensively utilized across sectors like biomedical, energy, and electronics, employing a diverse range of materials. However, the lengthy printing times associated with single-nozzle systems limit their application in complex mass production and rapid prototyping. While multi-nozzle systems have attempted to address this issue, they often result in costly, and bulky setups with limited material options. This research introduces a novel multi-nozzle multi-material system that allows for simultaneous 3D printing using bent nozzles. The system is cost-effective, simple in design, and capable of printing a wide range of materials. Its universal …

Proceedings Of The Ninth Annual Indiana Stem Education Conference: Resourcing Stem Education, William S. Walker Iii, Lynn A. Bryan, S. Selcen Guzey

Indiana STEM Education Conference

The Proceedings of the Ninth Annual Indiana STEM Education Conference are edited by the Center for Advancing the Teaching and Learning of STEM (CATALYST, https://www.education.purdue.edu/catalyst/) at Purdue University. The theme for the 2024 conference is Resourcing STEM Education. This year’s Indiana STEM Education Conference provides opportunities to learn about effective STEM education strategies, curriculum, and resources to engage students in integrated STEM learning opportunities and address the recently updated Indiana Academic Standards for Science and Computer Science, Indiana Academic Standards for Mathematics, and Indiana Academic Standards for Integrated STEM (https://www.in.gov/doe/students/indiana-academic-standards/).

Potential Role Of Ttt Complex In Regulating Dna Replication Checkpoint In The Fission Yeast Schizosaccharomyces Pombe, Sankhadip Bhadra

Browse all Theses and Dissertations

DNA replication can be perturbed by various agents that slow or stall the replication forks, causing replication stress. If undetected, stressed forks may collapse, causing mutagenic DNA damage or cell death. In response to replication stress and DNA damage, the eukaryotic cell activates the DNA replication checkpoint (DRC) and DNA damage checkpoint (DDC) pathways to promote DNA synthesis, repair, and cell survival. The two cell cycle checkpoint pathways are controlled by the protein sensor kinases Rad3 (hATR/scMec1) and Tel1 (hATM/scTel1) in fission yeast, although Tel1 plays a minimal role in checkpoint functions. Rad3 and Tel1 belong to a family of …

Evaluation Of A Blockchain-Based Prescription System And Data Source For National Research And Development, Sean Chan, Aedin Clay, Lance Tan, Christian E. Pulmano

Department of Information Systems & Computer Science Faculty Publications

In the Philippines, healthcare providers, government agencies, and research institutions use data from patient prescriptions to generate reports for health planning and decision-making. However, current e-prescription systems have vulnerabilities, including erroneous information, hacking attempts, a single point of failure, and medical fraud. In addition to affecting the quality of data reporting, these issues violate a patient's rights to data privacy. One promising solution is a blockchain-based prescription system. Blockchain's immutable ledger accurately traces medical fraud and erroneous information, while its decentralized nature reduces the impact of failures. Performance is an important consideration, as healthcare systems need to be scalable and …

The Effects Of Various Nanoplastics On The Inflammatory Response In Primary Alveolar Epithelial Cells, Eunice J. Pak

Theses and Dissertations

As plastic pollution begins to multiply in the environment and the workplace, gradual degradation of these plastics creates an unseen threat to biological health: nanoplastics. These nanoplastics are common in day-to-day life, and have been found in various internal organs of the human body. The biological and health effects of these nanoplastics are still widely unknown, and only recently has research focused on the impacts of these particles on human health at the cellular level.

In this thesis, poly(methyl methacrylate) and three forms of polystyrene (carboxyl-modified, amine-modified, and neutral surface charge) have been tested on submerged primary C57BL/6 mouse alveolar …