Digital Commons Network^™

Retrieval-Augmented Generation For Survival Analysis In Cancers: Methods And Evaluation On The Surveillance, Epidemiology, And End Results Database, Jyothi Vaidyanathan

Master's Projects

Healthcare is one of the most important fields that benefits from advancements in Artificial Intelligence (AI). From classic models like linear regression to cuttingedge transformers, AI is applied across various healthcare subdomains, such as drug discovery, predictive analytics, and personalized medicine, to name a few. These techniques enable medical practitioners to make more informed decisions, significantly improving both the speed and accuracy of diagnoses and treatments. Machine learning has played a transformative role in oncology, especially in areas like early detection, diagnosis, treatment planning, and patient monitoring, by analyzing medical images, clinical information, genomic data, sensor information. Our research aims …

Medilightrag: A System For Medical Query Response Using Fine-Tuned Llms And Graph Based Retrieval, Rajiv Karthik Reddy Kodimala

Master's Projects

The exponential increase in medical data has created a greater demand for precise and efficient information retrieval systems. Existing Large Language Models (LLMs) face domain-specific difficulties such as sophisticated medical jargon, situational comprehension, and the continual advancement of healthcare knowledge. To tackle these challenges, we present MediLightRAG, an innovative two-stage system which integrates parameter-efficient fine-tuning of Large Language models with LightRAG’s graph-based retrieval. The first stage focuses on enabling accurate resource-efficient model adaptation for the medical domain through QLoRA fine-tuning. In the second stage, LightRAG’s two-tiered retrieval architecture that combines graph-based indexing with dynamic knowledge retrieval is employed to enhance …

Physiotrack: A Gamified Physiotherapy System, Pranavi Chaturvedula

Master's Projects

Traditional physiotherapy methods tend to be non-interactive and provide little to no personalized instruction, even though physiotherapy is critical to stroke recovery. This thesis explores a fully adaptive, sensor-based, feedback architecture intended for stroke patients which remotely supervises movement and personalizes exercises enabled by multimodal sensors. The system uses filtering and windowed segmentation of accelerometer and skeletal data to compute features like jerk, speed, and joint movement angular range. A game engine applies accelerometer and skeletal features together with optimized, lightweight ML models to drive adaptive feedback, scoring, and difficulty adjustment. The architecture supports responsive continuous sensor streaming within the …

Secured Data Storage Management With Deduplication In Cloud Computing And Local Gpt Integration, Pavan Myana

Master's Projects

Exponential growth in cloud computing has brought enormous changes in data storage and processing, but also raised several questions on the security, privacy, and efficient storage of data. This report provides a dual-focused approach toward solving these challenges. First, we try to build an application securely and efficiently using data deduplication and Proxy Re-Encryption for optimization of storage and enabling secure data sharing. Deduplication ensures that redundant data is removed before encryption for maximum efficiency in storage, while PRE enables the safe sharing of encrypted data by re-encrypting the keys for specified recipients without the leakage of sensitive information. We …

Evorgcn: Harnessing Esm-2 Evolutionary Embeddings With Relational Gcns For High-Fidelity Protein-Protein Interaction Prediction, Mohit Kunder

Master's Projects

Accurately predicting protein-protein interactions (PPIs) is essential for understanding cellular function and advancing biomedical discovery. We model PPIs as graphs, where nodes represent proteins and edges denote interactions. Using interaction data from the STRING database, we use two samples of it, namely the benchmark datasets—SH27K and SH148K—filtered by confidence score and annotated by interaction mode (multiple relations). In this project, we present EvoRGCN, a graph-based machine learning framework for PPI prediction that integrates both sequence-level (ESM-2 embeddings) and network-level information. We incorporate various Graph Neural Network architectures, including Graph Convolutional Networks, Graph Attention Networks, and Relational Graph Convolutional Networks. Our …

Synthetic Malware Generation Using Generative Ai, Phanidhar Sai Sravan Chandana

Master's Projects

Malware grows in numbers and complexity, evading conventional signature-and anomaly-based defenses and worsening extreme data sparsity and class imbalance problems for machine learning based detection. Generative models, specifically GANs conditioned on contextual embeddings like BERT have proved effective augmenting training corpora to improve classifier accuracy, but these approaches have largely produced family-specific samples In this paper, we propose a generalized augmentation scheme for generating robust malware embeddings for various families. We begin by extracting opcode sequences from 13 malware families and encoding them into three embedding methods: CountVectorizer, TF-IDF, and BERT’s ‘[CLS]‘ vectors. We therefore train standard GANs and Wasserstein …

Advanced Knowledge Extraction With Biomedical Data Using Llms, Akshat Krishna

Master's Projects

The rapid growth of biomedical research has led to an overwhelming volume of unstructured textual data in the scientific literature. This has necessitated the development of an automated approach for knowledge extraction and integration. In

this project, we present a comprehensive pipeline for constructing a unified biomed- ical knowledge graph by combining two well-known datasets: CHEMPROT [1],

which captures chemical–protein interactions, and EU-ADR [2], which annotates drug–gene–disease relationships. In order to identify important biomedical entities and interactions from CHEMPROT dataset, we perform Named Entity Recognition (NER) and relation Extraction (RE) using state-of-the-art biomedical models like BioBERT [3], BioGPT [4] and …

Form And Function In Mobulids: A Comparative Analysis Of Filter Morphology With Bioinspiration Applications, J. B. Teeple, S. R. Kahane-Rapport, K. E. Cohen, L. Hamann, J. A. Strother, E. W. M. Paig-Tran

Biological Sciences Faculty Publications

Mobulas (manta and devil rays) are large-scale ram filter feeders that separate planktonic food particles from large volumes of water with minimal clogging. This contrasts with most human-made filters that can suffer from problematic clogging requiring additional mechanisms for clearing blocked surfaces and maintaining performance. Prior studies have shown that mobulas employ a unique mechanism referred to as ricochet separation to filter feed, whereby captive vortices in filter pores cause particles to bounce off the filter surfaces and away from the filter pores. This mechanism enables the filtration of particles smaller than the pore size and reduced clogging. However, few …

Decoding Tattoo And Permanent Makeup Pigments: Linking Physicochemical Properties To Absorption, Distribution, Metabolism, And Elimination Profiles Using Quantitative Structure-Activity Relationship (Qsar)-Based New Approach Methodologies (Nams), Girija Bansod, Ajay Vikram Singh, Preeti Bhardwaj, Tulika Rai, Sweta Vijay Nakhale, Amruta Shelar, Rajendra Patil, Peter Laux, Andreas Luch, Christopher J. Osgood, Michael W. Stacey

Biological Sciences Faculty Publications

The safety and quality of tattoo and permanent makeup (PMU) pigments are subject to increased scrutiny due to their potential to cause adverse effects like anaphylaxis, photoallergic responses, and long-term toxicity. These undesirable reactions governed by their chemical structure possess varied physicochemical properties and absorption, distribution, metabolism, and elimination (ADME) characteristics. These properties control the pigment behavior during application, stability, and interaction with human tissue. The correlation between these physicochemical characteristics and ADME parameters of tattoo/PMU pigments remain under-explored despite the current advances in toxicology. Our study aims to address and bridge the gap by leveraging open-access QSAR computational toxicology …

Multimodal Feature Fusion And Machine Learning For Adhd Detection Using Neuroimaging Data, Isabel Pham

Master's Projects

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopment disorder that can significantly affect a person’s attention, impulse control, and executive function. Currently, the traditional diagnosis method often relies on clinical assessments and observations. However, these methods can be subjective and lead to inconsistencies in diagnosis between individuals. To address this challenge, neuroimaging and machine learning (ML) are promising tools for providing a more objective diagnosis of ADHD. The goal of this project is to apply a multimodal approach in which structural and functional features of specific regions of the brain are used to develop a more accurate and objective …

Social Engineering Scenario Generation For Awareness-Based Attack Resilience, Jade Webb

Master's Projects

Social engineering is found in a strong majority of cyberattacks today, as it is a powerful manipulation tactic that does not require the technical skills of hacking. Calculated social engineers utilize simple communication to deceive and exploit their victims, all by capitalizing on the vulnerabilities of human nature: trust and fear. When successful, this inconspicuous technique can lead to millions of dollars in losses. Social engineering is not a one-dimensional technique; criminals often leverage a combination of strategies to craft a robust yet subtle attack. In addition, offenders are continually evolving their methods in efforts to surpass preventive measures. A …

Cca Analysis Using Computer Vision Techniques, Rahul Thakur

Master's Projects

Coral reefs are an essential part of the marine ecosystem. They perform a wide variety of tasks, some directly and others indirectly. They can produce oxygen, absorb carbon dioxide, along with supporting ocean habitat. Crustose Coralline Algae (“CCA”) plays an important role in helping provide structural support to Coral Reef ecosystems. However, global warming is causing ocean water to become more acidic resulting in coral bleaching. This is leading to changes in coral environments and causing coral deaths at alarming rates. Object detection using computer vision techniques, specifically deep learning, can help to monitor coral reef health and identify CCA …

Coral Vision – Crustose Coralline Algae Detection With Computer Vision, Ryan Tseng

Master's Projects

Crustose coralline algae (CCA) are a group of red algae that are vital contributors to the health of coral reef ecosystems. Monitoring CCA abundance can serve as an indicator for coral reef health and improve reef conservation efforts. Autonomous Reef Monitoring Structures (ARMS) are artificial structures that can be deployed into coral reef ecosystems and retrieved to gather ecological data without harming reef structures. Traditional methods of calculating CCA abundance require manual analysis and are labor-intensive. Recent developments in computer vision and deep learning technology have provided an avenue to fully automate this task. This research aims to train a …

Real-Time Adaptive Framework For Topic Modeling In Social Engineering Attacks, Manav Bhasin

Master's Projects

Detecting social engineering attempts is crucial for security, as these threats are becoming more frequent and increasingly exploit human vulnerabilities. This research focuses on topic modeling using conversational data from Kevin Mitnick’s ”The Art of Deception” with dialogues that illustrate various social engineering strategies. The dataset comprises manually extracted and synthetically augmented conversations to ensure natural dialogue flow. Two methodologies are presented for utterance-level and global topic extraction: prompt engineering leveraging OpenAI’s GPT-4o-mini, characterized by few-shot learning and chain-of-thought prompting, and Quantized Low Rank Adaptation (QLoRA) utilizing Mistral’s 7B instruct model for efficient fine-tuning. Through experimentation and evaluation, this study …

Simple Vs. Complex Human Activity Classification Via Hybrid Machine Learning Models, Anusha Kukreja

Master's Projects

In-depth understanding of the complexity of daily human activities is crucial for building responsive health monitoring and assistive technologies. However, limited research has focused on distinguishing activities based on their involvement level, as most existing work classifies only the type of activity performed. In this thesis, we address this gap by proposing a method to classify human activities as either simple or complex using sensor data from the Opportunity dataset. We define complex activities as those involving object interactions or multiple coordinated movements (e.g., drinking from a cup, cleaning a table), and simple activities as static or low-effort postures (e.g., …

Advances In Conductive Polymer-Based Flexible Electronics For Multifunctional Applications, Md Abdus Shahid, Md Mostafizur Rahman, Md Tanvir Hossain, Imam Hossain, Md Sohan Sheikh, Md Sunjidur Rahman, Nasir Uddin, Scott W. Donne, Md Ikram Ul Hoque

Michigan Tech Publications

The rapid developments in conductive polymers with flexible electronics over the past years have generated noteworthy attention among researchers and entrepreneurs. Conductive polymers have the distinctive capacity to conduct electricity while still maintaining the lightweight, flexible, and versatile characteristics of polymers. They are crucial for the creation of flexible electronics or gadgets that can stretch, bend, and adapt to different surfaces have sparked momentous interest in electronics, energy storage, sensors, smart textiles, and biomedical applications. This review article offers a comprehensive overview of recent advancements in conductive polymers over the last 15 years, including a bibliometric analysis. The properties of …

Fatigue Life Of Pre-Cut Seam Asphalt Mixture Composite Beams: A Combined Study Of Fatigue Damage Evolution And Reflective Cracking Extension, Hongfu Liu, Hong Lu, Xun Zhu, Zhengwei Yi, Xin Yu, Dongzhao Jin, Xinghai Peng, Songtao Lv

Michigan Tech Publications

This study investigated the impact of reflective cracking on the fatigue performance of asphalt pavements after milling and resurfacing under various conditions. Fatigue life was assessed through four-point flexural fatigue tests, while the crack extension pattern of composite beams was analyzed by digital image correlation (DIC) at both macroscopic and microscopic scales. Evaluation parameters such as stress ratios, immersion time, porosity, and types of viscous oils were assessed. A fatigue life prediction model of composite beams was established, accounting for the combined influence of these factors. To enhance the accuracy of determining composite beam failure, the critical fatigue damage was …

Predicting Biomechanical Risk Factors For Division - I Women’S Basketball Athletes, Aayushi Shah, Vanaja Agarwal, Dhairya Shah, Harman Jani, Sristi Sharma, Kaya Tolga, Christopher Taber, Mehul Raval

School of Computer Science & Engineering Faculty Publications

Collegiate basketball is characterized by high-impact movements such as jump landings, making athletes more susceptible to injuries. Critical biomechanical factors like knee flexion, lateral trunk flexion, and foot landing asymmetry are strongly associated with injury risk. This study aims to predict six biomechanical risk factors in the landing error scoring system (LESS). The dataset comprises 8600 video frames of counter-movement jumps (CMJs) from 17 NCAA Division I female basketball athletes, recorded from frontal and lateral perspectives and annotated using a customized error annotation algorithm. The study uses the You Only Look Once (YOLOv5nu) model to analyze the basketball athletes’ CMJ …

Investigation Using Single Point Incremental Forming (Spif) To Fabricate Patient-Specific, Titanium Orbital Floor Implants, Elizabeth M. Mamros, Lauren E. Blaha Md, Christian A. Kauffman Md

Faculty Conference Papers and Presentations

The floor of the human orbit is composed of thin bone that is prone to traumatic fracture. This leads to a loss of support for the eye, which can cause vision changes. Therefore, fractures may need surgical reconstruction using a thin, sheet-like implant. Titanium implants are available off-the-shelf in standard sizes, but fitting to each patient’s unique anatomy requires surgeons to cut, file, and bend these plates. This can be time-consuming and imprecise. To both save time and ensure a perfect fit for the patient, a custom plate can be created prior to surgery. This investigation focuses on single-point incremental …

Scalable Machine Learning Framework For Adaptive Irrigation Management Of Maize And Soybean In The U.S. Midwest, Precious N. Amori, Derek M. Heeren, Yeyin Shi, Eric Wilkening, Ivo Z. Goncalves, Guillermo R. Balboa, Daran R. Rudnick, Abia Katimbo, Randall S. Ritzema

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Conventional soil water balance (SWB) irrigation scheduling tools, such as FAO-56-based Spreadsheets and the Spatial Evapotranspiration Modeling Interface (SETMI), rely heavily on manual inputs and periodic field measurements, leading to delayed recommendations and missed opportunities to prevent crop stress. More critically, these tools lack the computational scalability and adaptability to leverage the high-frequency, high-volume datasets now available through modern sensing technologies. As precision irrigation increasingly depends on integrating spatially and temporally nuanced field information, there is a pressing need for decision-support systems that can process Big Data efficiently and respond in real-time. To overcome these limitations, we developed and validated …

Enhancing Walking Culture In Egyptian Cities As An Approach To Energy Harvesting, Kareem M. Ali

Mansoura Engineering Journal

It has become possible to generate clean energy based on the physical effort of individuals, whether during the use of sports equipment or by converting kinetic energy (walking steps) into electricity instead of it being wasted effort. The World Health Organization’s recommendation to walk for at least half an hour daily helps to enhance public health. Therefore, the research proposes dedicating pathways within cities built with energy-generating technology from pedestrian movement and organizing regular walking races to help produce more electrical energy. This would provide part of the urban environment’s electricity needs, reduce the carbon footprint, and enhance public health. …

Enhance The Design Of Low-Cost Fast Charging Battery Systems For Electric Mobility Systems, Omar Matar, Abdalrahman S. Alneklawy, Yara M. El-Hawary, Ahmed M. Elbeshbeshy, Ali Shoman, Ahmed R. Alagmy, Ahmed Mashaly, Arwa G. Saheen, Sahar S. Kaddah, Basem M. Badr

Mansoura Engineering Journal

The need of electric mobility (E-Mobility) systems increases daily, where the E-Mobility systems contribute in decreasing gas emissions from transportation Electric motorcycles (E-Motorcycles) are one of the E-Mobility systems, which reduce the problems resulting from traditional fossil fuel exhausts. This paper discusses the design and development of low-cost battery systems for E-Motorcycles, where a fast charging system is simulated, analyzed, and deployed to charge a battery package that outputs 72V & 8A at rated performance. Research and analysis of different power converter topologies are performed with respect the cost and system performance. A battery tester circuit is designed and built …

Exploring The Role Of Cinema In Architectural Perception Of Biophilic Design., Walaa Abdou Abd Elrazik, Mona Awad Abu El-Enein, Mahmoud M. Saafan

Mansoura Engineering Journal

With rapid urbanization transforming the built environment, biophilic architecture offers a sustainable approach that integrates natural elements to promote well-being and ecological balance. As a powerful storytelling medium, cinema shapes architectural perceptions by depicting both the presence and absence of biophilic principles in future urban landscapes. This study investigates how cinematic depictions of biophilic architecture influence audience understanding and appreciation. Using film content analysis, case studies, and surveys of architectural professionals, this research examines selected film scenes, evaluating the emotional and perceptual impact of biophilic versus non-biophilic environments. Findings indicate that films effectively highlight key biophilic features such as natural …

Application Of Genetic Algorithm In Container Vessel Stowage Planning With Carbon Tax Considerations, Ming-Feng Yang, Wei-Hao Su, Ko-Meng Hu, Yu-Hsuan Li

Journal of Marine Science and Technology–Taiwan

This study developed a method for optimizing stowage planning for container vessels, a crucial aspect of international trade logistics. Over 80% of global trade depends on containerized transportation; thus, effective stowage planning is essential for minimizing transportation costs and enhancing operational efficiency. In the proposed hybrid optimization approach, integer programming is combined with a genetic algorithm to generate optimal stowage plans. The key factors considered in this method include load capacity limits, stacking constraints, and carbon tax regulations. The proposed method involves maximizing space utilization while minimizing logistics costs, with particular emphasis on reducing port dwell times. The findings of …

Exploring The Red Sea Crisis’S Supply Chain Disruption Impacts On The Shipping Industry, Po-Hsing Tseng, Nick Pilcher

Journal of Marine Science and Technology–Taiwan

Since October 7, 2023, the Houthi militia in Yemen has continuously attacked Israel and its nearby ships in the Red Sea. This crisis has impacted on global ship operations, freight rates, and shipping networks, since this conflict seriously affects the international trade between Europe and Asia and brings many unpredictable butterfly effects (e.g. supply chain disruption, and high transportation costs in shipping and air cargo). This papero explores its impact on the supply chain and suggests potential solutions;, and to consider perceptions on who should be responsible for the crisis, and who will actually shoulder the responsibility for the crisis. …

Operational Risk Evaluation Of Oil Tankers Via Multivariate Gaidai Reliability Framework Incorporating Memory Effects, Oleg Gaidai, Shicheng He, Jinlu Sheng, Yan Zhu, Alaa Elsayed, Mahmoud El-Wazery

Journal of Marine Science and Technology–Taiwan

The retreat of Arctic Sea ice may exert a major impact on economy，potentially transforming the nature of commerce between Asia, Europe, and the Americas. Projections indicate a 40% reduction in transit distance and a 30% decrease in voyage time between Europe and northwest Asia compared to traditional routes such as the Suez Canal. However, even during summer navigation, fragmented floating ice persists, generating stochastic ice loads on vessel bows and hulls through complex ship-to-ice interaction. For structural design, statistical extrapolation methods are required to accurately assess excessive areal bow/hull stresses. This study proposes a novel multi-modal structural damage risk assessment …

New Insights Into Decapod Chemical Communication: A Focus On The Hydrothermal Vent Crab Xenograpsus Testudinatus, Jishnu Panamoly Ayyappan, Mark June S. Consigna, Li-Chun Tseng, Jiang-Shiou Hwang

Journal of Marine Science and Technology–Taiwan

Chemical communication in decapod crustaceans has been extensively studied for over 150 years, with most of the research focusing on sex pheromones. These crustaceans inhabit chemically complex environments and rely on diverse chemical signals for essential behaviors such as mate recognition, predator avoidance, and social interaction. This review synthesizes key findings from studies on shrimp, crayfish, lobsters, and crabs, the most well-documented taxa in crustacean chemical ecology. Various appendages, including the first and second antennae, mouthparts, and walking legs, are involved in chemosensory detection. Special emphasis is placed on chemical communication in extreme environments such as hydrothermal vents (HVs), with …

Geo-Chemical Fractionations Of Phosphorus In Sediments Of Thuy Trieu Lagoon And Cam Ranh Bay, Vietnam, Phu H. Le, Ngoc H. Pham, Dung T. Le, Tuan Linh T. Vo, Binh V. Tran, The V. Ho

Journal of Marine Science and Technology–Taiwan

The geochemical fractions of phosphorus (P) and its bioavailability in sediments of Thuy Trieu Lagoon and Cam Ranh Bay were investigated. Twenty-four surface sediment samples were collected in the dry season (Jun 2024) and the rainy season (Oct 2024). A sequential extraction procedure was applied to identify the phosphorus (P) fractions in sediments, including Exchangeable P (Ex-P), iron-bound P (Fe-P), aluminum-bound P (Al-P), calcium-bound P (Ca-P), and residual P (Res-P). Total P (TP) ranged from 214.9 to 2365.2 µg.g^-1, and the Ca-P fraction was the dominant chemical form in sediments. Based on the results of Pearson correlation and …

Beyond Basic Needs : Exploring The Antecedents And Outcomes Of Seafarers’ Well-Being, Chian Liou, Cheng Kuo Sung, Kimberly Hsiu-Chin Lee, Jiunn Liang Guo

Journal of Marine Science and Technology–Taiwan

Given the importance of seafarers’ mental health and the limited literature on this topic, this study aims to explore the causes and consequences of seafarers’ well-being. A questionnaire survey was conducted, and the data were analyzed using structural equation modeling and hierarchical regression analysis. Consistent with the predictions of the happy and productive worker thesis, this study found that the more satisfied the seafarers are with the shipping company’s seafarer policy, the higher their well-being tends to be, leading to a more positive work attitude. Interestingly, the study found that a company effect is significantly present in this correlation; that …

Deep Learning-Based Model For Automated Prediction Of Coastal Changes: A Robust Approach To Environmental Forecasting, Tsair-Fwu Lee, Chu-Ho Chang, Chin-Shiuh Shieh, Chih-Hsien Wu, Jen-Chung Shao, Chien-Liang Chiu

Journal of Marine Science and Technology–Taiwan

The coastline stands as a critical domain encompassing industry and the environment. The escalating global warming, leading to elevated sea levels and intensified wave-current interactions, has given rise to substantial coastal erosion. This predicament, in conjunction with excessive human development and Taiwan's coastal areas' extreme climatic impact, accentuates the perceptibility of coastal beach alterations. As a result, coastal erosion has emerged as a pressing issue necessitating resolution. Traditional methodologies for assessing coastline changes have conventionally relied on manual measurements. However, owing to the fluctuating distance of coastlines, influenced by tidal patterns, extended measurement processes over several months are susceptible to …