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

Engineering Commons™

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

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 13441 - 13470 of 196022

Full-Text Articles in Engineering

Exploring Facilitators’ Experiences Addressing Students’ Needs In A Higher Education Work-Based Engineering Program, Cody D. Mann Jan 2025

Exploring Facilitators’ Experiences Addressing Students’ Needs In A Higher Education Work-Based Engineering Program, Cody D. Mann

All Graduate Theses, Dissertations, and Other Capstone Projects

This study addresses a critical gap in higher education by examining the unique facilitator position at Iron Range Engineering (IRE), a work-based program at Minnesota State University, Mankato. Facilitators are full-time teaching staff in support roles that focus on helping students achieve positive outcomes, such as students successfully transitioning into working professionals. No formal research has been conducted to explore the comprehensive support and overall implications of this role. This qualitative study focused on phenomenography to capture the different experiences of 12 facilitator participants. Data collection was guided by role theory to explore the expectations and perceptions of facilitators, and …

Go to article

Laser Based Metal 3d Printer, Inura Goonawardena Jan 2025

Laser Based Metal 3d Printer, Inura Goonawardena

All Graduate Theses, Dissertations, and Other Capstone Projects

The technology and applications of additive manufacturing (AM) have advanced significantly in recent years. Research from hobbyist to industrial scale has evolved and has seen advancements in materials that can be utilized for industrial manufacturing. The Institute for Machine Tools and Industrial Management at the Technical University of Munich (TUM) developed the reAM250, an open-source research platform for Powder Bed Fusion with a Laser (LPBF). It was made available to facilitate study into component-level innovation, control techniques, and process monitoring without the budgetary and intellectual property constraints of commercial machines. This paper delves into the concept and production of the …

Go to article

Climate Variability Study For Arid Regions, Faisal Almutairi Jan 2025

Climate Variability Study For Arid Regions, Faisal Almutairi

Electronic Theses and Dissertations

Water is the primary source for all living species to thrive, and water scarcity has been a primary concern for biological species and plants in arid regions due to urban planning, population growth, poor water management, and overgrazing. The objective of this research was to study the climate variability in precipitation and temperature for an arid region. This research encompasses two distinct studies. The first study examined the impact of climate variability on precipitation in Phoenix. Precipitation data were acquired from NOAA from 1948 to 2023 and the study was broken down into three time scales: annually, seasonally, and monthly. …

Go to article

Development Of Food Preservative Hydrogel Using Bioactive Compounds Extracted From Canola Meal, Kayla Christopherson Jan 2025

Development Of Food Preservative Hydrogel Using Bioactive Compounds Extracted From Canola Meal, Kayla Christopherson

Electronic Theses and Dissertations

With an ever-growing population comes the need for a greater food supply. Yet land and other agricultural resources put a limit on the availability of food production. As farmers strive to optimize higher produce yields, society must turn to greener, more sustainable food preservation techniques to reduce food spoilage. The inclusion of extracted bioactive compounds found in canola meal into a food preservative hydrogel is such a solution for food spoilage reduction. In this thesis, extraction parameters of glucosinolates were examined along with their inhibition of E. coli DH5αZ1 when incorporated into 2 developed hydrogels: gelatin A Schiff-base and agar-agar. …

Go to article

Design And Optimization Of The Injection Molding Process Of Glass Fiber Reinforced Polymeric Car Fender Using Computational Simulation, Synthia Ferdouse Jan 2025

Design And Optimization Of The Injection Molding Process Of Glass Fiber Reinforced Polymeric Car Fender Using Computational Simulation, Synthia Ferdouse

Electronic Theses and Dissertations

The increasing demand for lightweight and energy-efficient materials in the automotive industry has accelerated the adoption of fiber-reinforced polymer composites. This research presents the design and optimization of the injection molding process for glass fiber-reinforced polymer (GFRP) car fenders using computational simulation. The effects of various gate types and locations on key process parameters, including fiber orientation, volumetric shrinkage, shear rate, and fill time, were investigated using Finite Element Analysis (FEA), Autodesk Moldflow Insight 2024, and MATLAB-based Multi-Criteria Decision-Making (MCMD) techniques. Simulations were conducted across multiple configurations involving three, four, and five gates, with several variations in location. Among all, …

Go to article

Impact Of Automated Controlled Tile Drainage On Field Discharge Water, Soil Moisture, And Crop Yield In Southeastern South Dakota, Joshua Becker Jan 2025

Impact Of Automated Controlled Tile Drainage On Field Discharge Water, Soil Moisture, And Crop Yield In Southeastern South Dakota, Joshua Becker

Electronic Theses and Dissertations

Automated controlled tile drainage is an innovative approach to water management, using dynamic weir settings programmed to drain water out of the tile system if it encroaches into the root zone at pre-programmed depths and duration. While past studies have indicated potential yield and water quality benefits of controlled drainage, there has been very little research into the performance of automated controlled drainage. In addition to overall performance, there is a gap in knowledge of management settings to optimize yield and water quality benefits. Two experiments, one plot-scale and one modeling, were conducted to assess the impact of automated controlled …

Go to article

Biopolymer-Induced Soil Ductility Enhancement: Mitigating The Effects Of Desiccation Cracks, Rabindra Prasad Bohara Jan 2025

Biopolymer-Induced Soil Ductility Enhancement: Mitigating The Effects Of Desiccation Cracks, Rabindra Prasad Bohara

Electronic Theses and Dissertations

This study addresses the formidable challenges of expansive clayey soils, notorious for their swelling-shrinkage characteristics, which often lead to ground instability and structural damage. While effective in mitigating soil swell-shrink potential and enhancing strength, traditional calcium-based stabilizers can react with higher sulfate content to form ettringite, causing volumetric changes and infrastructure distress. To assess the impact of stabilizing sulfate-rich soils and determining the various engineering properties, samples of both control and stabilized soils were prepared using lime, biopolymer (guar gum), and lime with guar gum at concentrations of 2% and 4% lime only, 0.5%, 1% and 1.5% guar gum only, …

Go to article

Evolution Of Bed Shear Stress In Open Channel Flow Over A Rough-To-Smooth Transition, Monika Kafle Jan 2025

Evolution Of Bed Shear Stress In Open Channel Flow Over A Rough-To-Smooth Transition, Monika Kafle

Electronic Theses and Dissertations

The study of flow over roughness transition in an open channel is very important in the field of hydraulic engineering. Bed shear stress is the key factor in predicting sediment transport and determining the stability of hydraulic structures while flow depth, flow velocity, surface roughness are some hydraulic parameters that can affect the bed shear stress in an open channel flow. In this thesis, a detailed investigation into the development of bed shear stress in a rough-to-smooth transition is performed. Experiments were conducted on flow over a rough-to-smooth transition in an open channel flume with an M2 to S2 composite …

Go to article

Improving K-Mean Clustering: A Comparative Study Of Parallelized Version Of Modified K-Mean Algorithm For Clustering Of Satellite Images, Yuv Raj Pant Jan 2025

Improving K-Mean Clustering: A Comparative Study Of Parallelized Version Of Modified K-Mean Algorithm For Clustering Of Satellite Images, Yuv Raj Pant

Electronic Theses and Dissertations

Efficient clustering of high-dimensional satellite image datasets remains a critical challenge, particularly due to the computational demands of spectral distance calculations, random centroid initialization, and sensitivity to outliers in conventional K-Mean algorithms. This study presents a comprehensive comparative analysis of eight parallelized variants of the K-means algorithm, designed to enhance clustering efficiency and reduce computational burden for large-scale satellite image analysis. The proposed parallelized implementations incorporate optimized centroid initialization for better starting point selection, a Dynamic K-mean sharp method to detect the outlier to improve cluster robustness, and a Nearest-Neighbor Iteration Calculation Reduction method to minimize redundant computations. These enhancements …

Go to article

Development Of A Collagen-Based Bioink For 3d Printing Biomimetic Tendon-To-Bone Tissue Grafts For Rotator Cuff Repair, Samiul Nibir Jan 2025

Development Of A Collagen-Based Bioink For 3d Printing Biomimetic Tendon-To-Bone Tissue Grafts For Rotator Cuff Repair, Samiul Nibir

Electronic Theses and Dissertations

This study presents the development of a collagen-based bioink for 3D printing tendon-to-bone tissue grafts, specifically designed for rotator cuff repair applications. Three different bioink formulations were developed: (i) 5.1% (w/v) collagen I, (ii) 5% (w/v) collagen I and collagen II, and (iii) 4.5% (w/v) collagen I combined with β-TCP. The bioink containing collagen I and collagen II was prepared by mixing the two components in a 1:1 ratio, while the collagen I plus β-TCP formulation was made by incorporating 20 wt % β-TCP into the collagen I solution. These formulations were developed to replicate the natural tendon-to-bone complex interface …

Go to article

Modeling Fluid Flow In Complex Biological Systems: Implications For Dense Tumor Microenvironments, Metastasis, And Bone Cancer, Mohammad Mehedi Hasan Akash Jan 2025

Modeling Fluid Flow In Complex Biological Systems: Implications For Dense Tumor Microenvironments, Metastasis, And Bone Cancer, Mohammad Mehedi Hasan Akash

Electronic Theses and Dissertations

The transport of biofluids in physiological systems plays a critical role in understanding and optimizing therapeutic interventions for diseases such as cancer and respiratory infections. This dissertation focuses on developing and validating a comprehensive computational framework for studying multiphase transport in complex biological environments. The research emphasizes the use of Computational Fluid Dynamics (CFD) to simulate and analyze plasma perfusion in solid tumors, particle deposition in respiratory airways, and fluid transport in cancer metastasis and bone cancer systems. By addressing the challenges of modeling biological transport phenomena, this work provides valuable insights into therapeutic planning and experimental validation. The study …

Go to article

Semantic Think-On-Graph (Semtog) : Enhancing Graphrag Through Semantic Community Detection, Sugam Mishra Jan 2025

Semantic Think-On-Graph (Semtog) : Enhancing Graphrag Through Semantic Community Detection, Sugam Mishra

Electronic Theses and Dissertations

Graph-based Retrieval-Augmented Generation (GraphRAG) enhances large language models (LLMs) by grounding their reasoning in structured knowledge graphs, making them more reliable for multi-hop reasoning and factual QA. A central mechanism in Think-on-Graph systems such as ToG[14] and FastToG[7] is community detection, which groups locally related nodes into compact subgraphs so that LLMs can reason over focused, information-rich neighborhoods instead of traversing the entire graph. However, these methods rely purely on structural connectivity, often scattering semantically related entities across different communities and weakening the evidence provided to the LLM. We propose Semantic Think-on-Graph (SemToG), a semantic-aware extension of FastToG[7] that integrates …

Go to article

Multi-Source Remote Sensing–Based Soil Moisture Prediction Using Machine Learning, Niraj Neupane Jan 2025

Multi-Source Remote Sensing–Based Soil Moisture Prediction Using Machine Learning, Niraj Neupane

Electronic Theses and Dissertations

Soil moisture (SM) plays a central role in climatic and environmental processes, influencing shear strength of soil, agricultural productivity, land–atmosphere interactions, and hydrologic functioning. However, accurately estimating SM across diverse climatic regions remains challenging due to spatial heterogeneity, limited in situ measurements, and inconsistencies in sensor resolution. Machine learning (ML) and remote sensing offer promising avenues for improving SM prediction, yet many existing approaches struggle with generalization across climatic gradients and often fail to capture temporal variability. This study integrates multi-source satellite and climate datasets, including SMAP L4_SM, MODIS land surface temperature, Daymet meteorological variables, and in situ observations from …

Go to article

Quantitative Assessment And Validation Of Thermal Profiles In The Protodune-Ii Horizontal Drift Detector Using Computational Fluid Dynamics, Hunter Wallster Jan 2025

Quantitative Assessment And Validation Of Thermal Profiles In The Protodune-Ii Horizontal Drift Detector Using Computational Fluid Dynamics, Hunter Wallster

Electronic Theses and Dissertations

The Deep Underground Neutrino Experiment (DUNE) aims to advance understanding of neutrino properties using large liquid Argon time projection chambers (LArTPCs). The ProtoDUNE-II Horizontal Drift (HD) detector, constructed at CERN in Switzerland, serves as 1:20 scale prototype to validate design and operational parameters for DUNE’s Far Detectors. Accurate prediction of cryostat thermal behavior is critical to predicting liquid Argon purity distributions and detector performance, motivating the development of a validated computational fluid dynamics (CFD) model. This research extends previous work at South Dakota State University by constructing a higher-fidelity CFD simulation of ProtoDUNE-II HD using Siemens Simcenter StarCCM+® 19.04.007. Geometry …

Go to article

Distributed Energy Resources (Der) Capacity Estimation With Spatiotemporal Downscaling For Transmission And Distribution Coordination, Abhilasha Suvedi Jan 2025

Distributed Energy Resources (Der) Capacity Estimation With Spatiotemporal Downscaling For Transmission And Distribution Coordination, Abhilasha Suvedi

Electronic Theses and Dissertations

The primary objective of this thesis is to accurately estimate the capacity of distributed energy resources (DERs) using the spatiotemporally downscaled local solar irradiance for their efficient integration into transmission-level grid operations. Accurate estimation of DER capacity is crucial for their enhanced integration into real-time electricity markets. Different methods of spatiotemporally downscaling the solar irradiance are presented in this thesis, followed by their integration into the 12 house distribution network – a low voltage residential distribution system. Grid support functions (GSFs) like Volt-Watt Control, Volt-VAR control, and Frequency-Watt Control are applied to effectively regulate the frequency and maintain the voltage …

Go to article

Optimizing Hypersonic Scramjets: A Numerical Study Of Fuel Type And Cavity Flameholder Design Impacts On Supersonic Combustion, Delaney Baumberger Jan 2025

Optimizing Hypersonic Scramjets: A Numerical Study Of Fuel Type And Cavity Flameholder Design Impacts On Supersonic Combustion, Delaney Baumberger

Electronic Theses and Dissertations

This thesis presents recommendations for optimizing hypersonic scramjets via a numerical study focusing on fuel type and cavity flameholder design and the impacts they have on supersonic combustion. The research is divided into two main investigations aimed at improving scramjet engine efficiency using two distinct geometrical configurations, a square cavity engine and an axisymmetric cavity engine. Each configuration is examined under Mach 2 inflow conditions to assess the role of geometric variation and fuel selection on combustion stability, flameholding, and overall performance. The first study focuses on a comparative assessment of hydrogen and ethylene as scramjet fuels to evaluate their …

Go to article

Redefining Electrical And Computer Engineering Faculty With Longitudinal Support For Women And Underrepresented Minorities, Barbara E. Merino, Agnieszka Miguel Jan 2025

Redefining Electrical And Computer Engineering Faculty With Longitudinal Support For Women And Underrepresented Minorities, Barbara E. Merino, Agnieszka Miguel

Electrical and Computer Engineering Faculty Works

Despite many efforts to increase the diversity among electrical and computer engineering (ECE) faculty, the number of women and underrepresented minority faculty is still alarmingly low. Over the past eight years, NSF-sponsored iREDEFINE hosted 207 underrepresented ECE postdoctoral and PhD students for a two-day workshop designed to motivate and prepare them to pursue faculty positions. Although this program was designed to increase the diversity of ECE faculty, it can serve as a model for other STEM fields. Details of the iREDEFINE program will be shared in this paper along with quantitative and qualitative data demonstrating the success of iREDEFINE. Work …

Go to article

Increasing Student Achievement In Ece Fundamentals Through Standards-Based Grading, Barbara E. Merino, David Berube Jan 2025

Increasing Student Achievement In Ece Fundamentals Through Standards-Based Grading, Barbara E. Merino, David Berube

Electrical and Computer Engineering Faculty Works

In a traditional STEM course, student work is evaluated using points, allowing students to receive partial credit on the problems attempted. Final grades are then determined by combining the scores on the formative (homework) and summative (tests) assessments using a predetermined formula. In some cases, attendance, class participation, and lab work may factor in the final grade calculation. Although this works reasonably well, the final grade does not accurately reflect student knowledge. Standards-based Grading is a more authentic way to assess student achievement. In a course using authentic grading, course grades are based on student proficiency in specific topics,called standards. …

Go to article

Investigating The Roles Of Intrinsic Point Defects And Transition Metal Doping In Monolayer And Bulk Tis2, Patrick J. Keeney Jan 2025

Investigating The Roles Of Intrinsic Point Defects And Transition Metal Doping In Monolayer And Bulk Tis2, Patrick J. Keeney

UNF Graduate Theses and Dissertations

Within this thesis, the magnetic and electronic properties of various 1T-TiS2 systems are thoroughly examined using density functional theory (DFT) and scanning tunneling microscopy (STM). Formation energies and electronic implications of intrinsic point defects in bulk TiS2 and monolayer TiS2 are analyzed by approximating a computational monolayer of TiS2 as the surface layer of a bulk sample. This approximation is validated given that intralayer covalent bonding dominates interlayer van der Waals interactions. We conclude that the most energetically favorable intrinsic defects are Ti atoms settling above the outermost S plane and S vacancies. In addition, the …

Go to article

Modeling Neighborhoods As Fuel For Wildfire, Bryce Alan Young Jan 2025

Modeling Neighborhoods As Fuel For Wildfire, Bryce Alan Young

Graduate Student Theses, Dissertations, & Professional Papers

Wildfire models drive billions of dollars in risk mitigation efforts. However, the modeling community currently lacks a representative fuelscape on which to base simulations of fire spread in the built environment and the wildland-urban interface (WUI) where vegetation and structures act together as fuel for wildfire. This thesis advances wildfire risk modeling by addressing the underdeveloped representation of the built environment in existing frameworks. By identifying inconsistencies in how structure and defensible space features are defined and used across empirical studies, predictive indices, and fire spread models, this research lays the groundwork for standardized modeling approaches and feature selection (Chapter …

Go to article

Intercellular Mitochondrial Transfer Contributes To Microenvironmental Redirection Of Cancer Cell Fate, Julie Sofie Bjerring, Yara Khodour, Emilee Anne Peterson, Patrick Christian Sachs, Robert David Bruno Jan 2025

Intercellular Mitochondrial Transfer Contributes To Microenvironmental Redirection Of Cancer Cell Fate, Julie Sofie Bjerring, Yara Khodour, Emilee Anne Peterson, Patrick Christian Sachs, Robert David Bruno

School of Medical Diagnostics & Translational Sciences Publications

The mammary microenvironment has been shown to suppress tumor progression by redirecting cancer cells to adopt a normal mammary epithelial progenitor fate in vivo. However, the mechanism(s) by which this alteration occurs has yet to be defined. Here, we test the hypothesis that mitochondrial transfer from normal mammary epithelial cells to breast cancer cells plays a role in this redirection process. We evaluate mitochondrial transfer in 2D and 3D organoids using our unique 3D bioprinting system to produce chimeric organoids containing normal and cancer cells. We demonstrate that breast cancer tumoroid growth is hindered following interaction with mammary epithelial cells …

Go to article

Evaluation Of The Maneuverability Of An 85m Fishing Trawler (Focusing On Dynamic Stability), Chun-Ki Lee, Su-Hyung Kim Jan 2025

Evaluation Of The Maneuverability Of An 85m Fishing Trawler (Focusing On Dynamic Stability), Chun-Ki Lee, Su-Hyung Kim

Journal of Marine Science and Technology–Taiwan

Most fishing vessels are less than 100 meters in length, so IMO maneuverability standards do not apply. As a result, studies on the maneuverability of fishing vessels are considerably fewer compared to those on merchant ships. However, with technological advancements, the size of fishing vessels continues to grow, and as more fishermen are on board, accidents could lead to fatal casualties. In response, the authors determined that research on the maneuverability of fishing vessels is urgently needed. Thus, the authors conducted a maneuverability evaluation on a fisheries training vessel with the hull shape of a fishing trawler, 85 meters in …

Go to article

A Hybrid Image Filtering Approach For Improving Edge Detection Of Riverbed Particles With Complex Textures, Po-Wei Lin, Hsun-Chuan Chan Jan 2025

A Hybrid Image Filtering Approach For Improving Edge Detection Of Riverbed Particles With Complex Textures, Po-Wei Lin, Hsun-Chuan Chan

Journal of Marine Science and Technology–Taiwan

The distribution of particle size in gravel-bed rivers affects the flow condition, sediment transport, and river morphology. However, conventional particle size analysis is laborious and time-consuming. To enhance the efficiency of particle size analysis, image-based methods have been widely explored, but complex particle textures increase the difficulty in identifying particle edges during image analysis. This study develops a filtering approach based on the rolling guidance filter and leverages the differences in grayscale gradients between particle edges and textures to design a guidance image tailored for the rolling guidance filter. This design enables the filter to preserve particle edges while smoothing …

Go to article

Comparison Of Canopy Materials To Improve The Performance Of Sea Anchors Used For Fishing Operations, Namgu Kim, Su-Hyung Kim, Yoo-Won Lee, Kyung-Jin Ryu Jan 2025

Comparison Of Canopy Materials To Improve The Performance Of Sea Anchors Used For Fishing Operations, Namgu Kim, Su-Hyung Kim, Yoo-Won Lee, Kyung-Jin Ryu

Journal of Marine Science and Technology–Taiwan

Sea anchors used for fishing operations help improve catch rates by stabilizing vessel drift speeds to match tidal or ocean currents. The underwater resistance experienced by a sea anchor's canopy significantly impacts its performance, yet there has been limited research on canopy materials. This study investigates how different canopy materials can enhance sea anchor performance. Specifically, we tested sea anchors made from three fabrics: the currently used polyamide (PA) material, PA material with increased yarn density in the weft direction, and polyester (PES). Using Korean national standards, we compared the yarn density, weight, water absorption capacity, drying rate, air permeability, …

Go to article

Research On Ship Track Prediction Based On Ipso-Cnn, Xiangen Bai, Nuo Chen, Xiaofeng Xu Jan 2025

Research On Ship Track Prediction Based On Ipso-Cnn, Xiangen Bai, Nuo Chen, Xiaofeng Xu

Journal of Marine Science and Technology–Taiwan

With the rapid development of the global economy, international imports and exports have become increasingly important. Timely and effective tracking and prediction of ship trajectories are important in the face of complex maritime traffic. Based on AIS data, this study establishes a ship trajectory prediction model combining improved particle swarm optimization (IPSO) and a convolutional neural network (CNN) that uses the ship's historical navigation trajectory data to predict the future navigation trajectory. The historical ship trajectory data of the Port of Ningbo-Zhoushan were selected for the experiment, and the IPSO-CNN model experiment results were compared with those of other models. …

Go to article

Toward Strategy Identification And Subtask Decomposition In Task Exploration, Tom Odem Jan 2025

Toward Strategy Identification And Subtask Decomposition In Task Exploration, Tom Odem

Master's Projects

This research builds on work in anticipatory human-machine interaction, a subfield of human-machine interaction where machines can facilitate advantageous interactions by anticipating a user’s future state. The aim of this research is to further a machine’s understanding of user knowledge, skill, and behavior in pursuit of implicit coordination. A task explorer pipeline was developed that uses clustering techniques, paired with factor analysis and string edit distance, to automatically identify key global and local strategies that are used to complete tasks. Global strategies identify generalized sets of actions used to complete tasks, while local strategies identify sequences that used those sets …

Go to article

Ai-Based Dynamic Spectrum Allocation Model For Wireless Network Management, Sai Sashank Peddibhotla Jan 2025

Ai-Based Dynamic Spectrum Allocation Model For Wireless Network Management, Sai Sashank Peddibhotla

Master's Projects

The growth of wireless communication has introduced challenges in the dynamic and resource contrived space which is the efficient utilization of bandwidth and spectrum. This research presents a model for dynamic spectrum allocation with the help of Convolutional Neural Network (CNN) for feature extraction and the Deep Q-Network (DQN) model’s reinforcement learning architecture. The CNN captures both spatial and temporal features of the network states and gives them to the DQN for optimal allocation decision making. This CNN-DQN architecture effectively implements spectrum resource allocation in wireless networks and adapts to resource allocation changes within performance bounds. The system’s performance is …

Go to article

Improving Contextual Retrieval For Long Documents In Q & A Systems, Sakshi Garg Jan 2025

Improving Contextual Retrieval For Long Documents In Q & A Systems, Sakshi Garg

Master's Projects

With the vast amount of information available on the internet distributed across several lengthy documents, finding relevant information has become more important and challenging. The goal of this project is to develop advanced techniques to retrieve information from long texts in order to deliver accurate and relevant results while ensuring speed and efficiency. As part of this work, we employ techniques to address unique difficulties posed by large and complex documents. This paper presents a custom Retrieval-Augmented Generation (RAG) framework designed to improve contextual retrieval in long and multi-document settings. In this paper, we employ several techniques like summarization, semantic …

Go to article

Evorgcn: Harnessing Esm-2 Evolutionary Embeddings With Relational Gcns For High-Fidelity Protein-Protein Interaction Prediction, Mohit Kunder Jan 2025

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 …

Go to article

Synthetic Malware Generation Using Generative Ai, Phanidhar Sai Sravan Chandana Jan 2025

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 …

Go to article

First Prev Next Last