Engineering Commons^™

Generating Real-Time Synthetic Datasets To Improve Aerial Object Detection, Garrett Williams

Theses and Dissertations

The widespread use of unmanned aerial vehicles (UAVs) across civilian and military applications has necessitated the advancement of real-time drone detection and tracking capabilities. Machine Learning (ML) addresses these requirements, however, to train a robust and generalizable model requires large and diverse video datasets. Curating these real-world datasets is often time-consuming and cost-prohibitive. Here, we present DyViR, a real-time customizable rendering application capable of automatically generating highly realistic synthetic, multi-modal video of aerial objects, digital environments, and automatic generation and labeling of bounding boxes. Synthetic data, coupled with real-world training sets, augment the ML training process, leading to increased performance …

Correlations Between Song Popularity And Their Audio Features Using Machine Learning, Rong Chen

Dissertations, Theses, and Capstone Projects

This project is an interactive visual project that explores the relationship between audio features and song popularity on Spotify using machine learning techniques. Through the collection of nearly half a million songs and implementation of seven different machine learning models, including Linear Regression, Random Forest, Decision Trees, and Gradient Boosting, I investigated how audio characteristics correlate with a song's popularity ranking. The project utilized MongoDB for data storage, Spotipy for API integration, and Streamlit with Plotly for visualization. This work provides insights into the practical challenges of large-scale music analysis and the relationship between technical audio characteristics and commercial success, …

Construction Change Order Data As Inputs For A Programmatic Risk Model, Eric C. Klein

Theses and Dissertations

Hurricane Michael struck Tyndall Air Force Base as a Category 5 storm with 160 mph winds, damaging or destroying 90% of its infrastructure (484 buildings). This devastation prompted the Department of Defense to rebuild Tyndall as the “Installation of the Future,” encompassing 44 Military Construction (MILCON) projects and 260 Facility Restoration, Sustainment, and Modernization (FRSM) projects. Since reconstruction began, over 630 Change Request Forms (CRFs) have been closed, adding $67.8 million in costs and 4,880 construction days. The Air Force Civil Engineer Center's Natural Disaster Recovery (NDR) Division developed a programmatic risk model to predict future costs and delays. However, …

From Football To Construction: Transferring Leadership Competencies For The Era Of Construction 4.0, Payson W. Campisano

Construction Management

This study aims to explore the intersection of leadership competencies developed through football and their applicability to the construction industry, with a focus placed on the emerging leadership needs in Construction 4.0. Drawing on insights from interviews with current and former student-athletes who study or studied construction management at the California Polytechnic State University in San Luis Obispo, the research highlights the transferability of key leadership qualities from football, such as resilience, teamwork, and critical thinking, to the cognitive, interpersonal, business, and strategic domains of leadership within construction management. Building on the work of Yang, Sunindijo, and Wang (2020), who …

Metaheuristic Techniques To Optimize Trajectory Planning Of Uav Swarms: Enhancing Data Acquisition In Wireless Sensor Networks, Nada Ali Mohamed Ahmed Ahmed

Theses and Dissertations

Unmanned aerial vehicles (UAVs) have become increasingly integrated into various applications due to their cost-efficiency, rapid deployment, flexible maneuvers, and enhanced performance. This has led to the development of a new field called UAV-assisted Wireless Sensor Networks (U-WSNs), which focus on data routing, network performance optimization, and planning UAV trajectories between sensor nodes in wireless sensor networks. In this thesis, a new framework has been proposed to manage a swarm of UAVs cooperatively serving large-scale wireless sensor networks. The framework consists of three optimization problems: distributing sensor nodes among UAVs, finding optimal trajectories in the presence of obstacles, and performing …

Operation And Maintenance Costs In Reverse Osmosis Desalination Projects Adopting Public-Private Partnerships: A Comprehensive Investigation And Analysis, Mayar Mohamed Khairy

Theses and Dissertations

Water Desalination projects, specifically ones adopting reverse osmosis (RO) technology, play a pivotal role in addressing the scarcity of water globally. Since these projects require huge investments, there is an imperative need to focus on the role of public-private partnerships (PPPs) in their developments. This research tries to provide a comprehensive investigation into the factors affecting O&M costs in PPP desalination projects due to their importance.

A comprehensive research approach, including a literature review, expert interviews, survey analysis, and statistical tools, is adopted in this research aiming to identify key factors and recommendations based on best practices in O&M costs …

Sustainability Transformation For Healthcare Facilities Following Net Zero Model, Esraa Elmitainy

Theses and Dissertations

The healthcare industry is a field undergoing huge development. Focused on SDG 3 “Good Health and Well-being”, the healthcare industry, as the main health service provider, was marked by experts as a sector that should lead sustainable development by example. The current work aims to formulate a sustainability rating system for new and existing healthcare facilities to encourage the Egyptian healthcare industry to move towards sustainability according to net zero concepts. Additionally, the transition to net zero waste is investigated though experimental work to test the possibility of utilizing sterilized medical waste in cement-based bricks.

The rating system starts with …

Design And Implementation Of Uvm-Based Verification Framework For Deep Learning Accelerators, Randa Ahmed Hussein Aboudeif

Theses and Dissertations

Recent advancements in deep learning (DL) have made hardware accelerators, known as deep learning accelerators (DLAs), a preferred solution for numerous high-performance computing (HPC) applications, including speech recognition, computer vision, and image classification. DLAs are composed of hundreds of parallel processing engines to speed up computations and can gain access to pre-trained networks from the cloud or through on-chip memory to implement the DNN inference process. DLA verification is becoming an important and challenging phase. The verification process is required to handle the complex DLA design. Moreover, the reliability of DLAs is critical for assessment as they are involved in …

Navigating The Future Advancing Autonomous Vehicles Through Robust Target Recognition And Real-Time Avoidance, Mohammed Ahmed Mohammed Hussein

Theses and Dissertations

The problem being tackled by this thesis is a very important one and very relevant to our days and times: it is about making improved target recognition and enhanced real-time response skills in AVs under simulated conditions. Our plan is to put some enhanced sensory capabilities into these vehicles and see if that makes them safer and more reliable. We are using as our base a particular object recognition algorithm (YOLOv7) and a particular simulation environment (CARLA). We utilized the CARLA 0.9.14 simulator on Ubuntu 20.04 as a more stable option than the initially used CARLA 0.9.15 on Ubuntu 22.04, …

A Framework To Harmonize Legal Provisions In Infrastructure Ppp Projects In Egypt Funded By Multilateral Development Banks, Menna Elkadi

Theses and Dissertations

Over the last decade, Egypt has witnessed an increase in the number of Public-Private Partnership (PPP) projects, specifically in infrastructure, as a result of the growing interest and popularity of various entities participating in such projects. Public infrastructure systems are no longer thought to be exclusively provided by the government; instead, the private sector’s contribution in the provision of such services is increasing. However, not every PPP program has been equally effective or has made the optimum use of planning and decision-making. The possibility of a project failure as a result of poor risk allocation is increased, if the potential …

Advanced Construction Scheduling: Capturing Conditional And Stochastic Relationships, Amr Elsabagh

Theses and Dissertations

Proper planning is a key factor in all business endeavors. This is especially important in the construction industry as a project is sensitive to countless factors that affect the project's time and cost. This created the need for agile and flexible schedules for close monitoring and dynamic planning for construction projects. The currently prevailing scheduling techniques are CPM and PERT, which professionals in the field widely use. These methods create static schedules that are vulnerable to any changes in the schedule logic, which often happens during construction projects. In addition, these Scheduling techniques do not capture the uncertainties and complex …

Organizational Change Management In Egypt; Contractors’ Perspective, Karim Ayoub

Theses and Dissertations

Organizational change management in the construction industry is a vital process for companies to consider in their operations. Successful implementation of the process allows the companies to go a step further in the market due to their competitiveness derived from better performance and efficiency. However, applying change to the organization and introducing new structure is a challenge for any company seeking better performance, but worth it if it is implemented properly. In general, this research sheds light on the organizational change management implementation in construction contractors in Egypt. Where, this study aims to demonstrate the organizational change management initiatives and …

Assessment Of Risk Factor Prediction Using Machine Learning Techniques And Hybrid Approach Based On Soft Sets, Menaga A

Theses and Dissertations

Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, and India reports a significantly high death rate due to its large population base and the increasing prevalence of non-communicable diseases. National statistics indicate that 20–27% of deaths in India are attributed to CVDs, with the proportion steadily rising over the years. Recognizing the urgency of early detection and risk prevention, the World Health Organization (WHO) introduced “The Global Action Plan for the Prevention and Control of Non-Communicable Diseases (2013–2020),” emphasizing early identification, risk reduction, and timely treatment. In this context, decision-making applications have gained importance across domains especially healthcare …

Assessing Water Quantity And Quality In The Mississippi River Valley Alluvial Aquifer And Coastal Louisiana Through Integrated Airborne Electromagnetic And Borehole Data, Michael George Henin Attia Khalil

LSU Doctoral Dissertations

Numerical modeling has contributed significantly to the understanding of groundwater systems. Many challenges are associated with constructing groundwater models which include an accurate understanding of the geology and aquifer parameters estimation. Traditionally boreholes are a successful way to capture geological features, however, boreholes often have sparse data. Airborne electromagnetic (AEM) data allows for efficient and cost-effective surveying of large areas, providing valuable information about the subsurface electrical resistivity. By bridging the gap between boreholes, AEM data offers a broader view of the aquifer system's structure and heterogeneity. However, interpreting geophysical AEM data has uncertainties. Developing a framework to apply the …

A Precoding, Companding, And Nonlinearity Reduction Approach To Optimize High-Speed Ado-Ofdm For Visible Light Communication, Swaminathan S

Theses and Dissertations

Using light-emitting diodes (LEDs) for data transfer, visible light communication (VLC) presents a strong substitute for radio frequency communication. Yet, because of the non-linearity of LEDs, conventional Orthogonal Frequency-Division Multiplexing (OFDM) approaches in VLC are limited regarding spectrum efficiency, peak-to-average power ratio (PAPR), and system linearity. Multi-carrier asymmetrically Clipped Optical OFDM (MADO-OFDM) is introduced in this study. For VLC operations based on Optical Orthogonal Frequency Division Multiplexing (O-OFDM), a model-driven Deep Learning (DL) approach has been presented. Utilizing an Auto Encoder (AE) network technology reduced the non-linearity of the LEDs. A proposed improved ADO-OFDM protocol, called MADO-OFDM, adaptively modifies the …

Sensing Rotational Direction Using Paramagnetic Nanoparticles For Gyroscopic Applications, Jacob C. Pung

Masters Theses

Gyroscopes have long been used for measuring an object’s angular orientation. Methods range from mechanical spinning disks to oscillating spring-mass systems. However, previous gyroscopes can suffer from high maintenance or fragility. A recently invented novel gyroscope aims to curb these restrictions through the use of ferrofluid.

This thesis proposes a new method of modeling and measuring the signals from the novel gyroscopic device. Rather than simply measuring the device’s average current consumption via slow RMS measurements, an attempt was made to model the voltage amplitude at any time. This allows a faster examination of both the changing magnitude and phase …

Comparison Of Milling Cutting Forces In Synthetic And Biological Cancellous Bone, Matthew Christopher Hartwell

Masters Theses

In many orthopedic and dental interventions, the cutting and removal of bone is necessary. Therefore, it is of the utmost importance that the tools used during these procedures are designed and tested with biological bone or a bone surrogate material that machines the same way as biological bone. To avoid the cost, hazard, and inconsistency of biological cadaveric bone or animal models, many biological engineering firms use bone surrogate material made of glass fiber filled epoxy and polyurethane foam. Although these materials may mimic the elongation of cortical and cancellous bone, respectively, the match of machinability of the bone is …

Structural Earthquake Resiliency Of Rocking Core Systems With Floor Enabled Recentering, S. Taban Hajimirza

Dissertations and Theses

The growing need for structural earthquake resiliency, coupled with increasing demands for environmentally sustainable construction, has driven architects and engineers to emphasize the importance of earthquake-resistant mass timber multistory construction in regions prone to high seismic activity. With advancements in building technologies, cross-laminated timber (CLT) has emerged at the forefront of this movement by unlocking new potentials for urban development.

Motivated by the aforementioned demands, this PhD dissertation investigated lateral behavior and earthquake response of a novel lateral force-resisting structural system, known as Floor Recentering Rocking Core (FLR-ROCR). FLR-ROCR is a low-damage recentering mass-timber system that leverages restoring interactions between …

The Influence Of The Un Watercourses Convention On The Development Of A Policy Design In The Nile River Basin, Zienab Ali Abdelhady

Theses and Dissertations

The adoption in 1997 of the United Nations Convention on the Law of the Non-navigational Uses of International Watercourses (UN Watercourses Convention or UNWC) marked a milestone in the codification and progressive development of international water law. Similarly, the signature in 2010 by the majority of the Nile Basin states of the Nile River Basin Cooperative Framework Agreement (CFA) was a major step towards a permanent legal and institutional framework as well as a significant shift from the currently applicable legal regime in the basin. The research concludes that the principles enshrined in the UNWC can assist future regional treaty …

Synthesis Of Durable Sio2 Nanoparticle Coatings For Self- Cleaning Solar Panel Surfaces, Pratima Parajuli

Masters Theses

The demand for innovations that improve the efficiency of solar panels has grown due to an increasing reliance on solar energy as a sustainable energy source. Great effort has been made to increase the conversion efficiency of solar energy to electrical energy. The accumulation of dirt, dust, and other environmental particulates on their surfaces is a challenge faced by solar panel technology. These contaminants can significantly reduce the overall performance of the solar panel. Recently, interest in developing self-cleaning surfaces has risen to maintain the performance of solar panels.To create self-cleaning surfaces, silicon dioxide (SiO₂) nanoparticles are emerging …

An Integrated Approach To Enhance The Performance Of Rainfall Forecasting By Leveraging Stacking Based Machine Learning And Deep Learning Techniques, Umamaheswari P

Theses and Dissertations

Rainfall forecasting is critical for a variety of reasons, the most important of which is the substantial impact it has on many sectors of the community and the environment. It helps farmers with planting schedules, crop choices and irrigation techniques, all of which directly impact food production and agricultural yields. Rainfall forecasting is also vital in sectors such as hydroelectric power generation, since knowledge about water availability is essential for electricity generation. Accurate rainfall forecasts play very important roles in disaster planning and flood control. They enable authorities to take precautionary measures and, where necessary, plan for the evacuation of …

A Structural Evaluation And Design Optimization Of A Tow Bar For Disabled Snowmobiles, David M. Pevic

Masters Theses

Snowmobile tow bars are devices used to rigidly connect two snowmobiles, such that a disabled snowmobile can be recovered from a remote location with a working snowmobile. These devices, however, are not widely used or readily available. An existing tow bar design was evaluated and redesigned to improve its structural capacity and performance. This evaluation provided a baseline to quantify improvement and included Finite Element Analysis (FEA), Design Failure Mode and Effect Analysis (DFMEA), and Design for Assembly analysis (DFA). A review of existing snowmobile tow bar patents was also performed. An updated design was then fabricated and similarly evaluated. …

Sentiment Analysis For Stock Market Prediction Using Machine Learning Techniques, Rajendiran P

Theses and Dissertations

Sentiment analysis has become one of the most important procedures to predict the stock market behaviour according to the customer reviews about a particular topic such as news, movie, event, and remarks related to the product. Due to the huge number of reviews generated from the customer, for analyzing information in an accurate manner. In order to detect general view of product, sentiment analysis technique is performed. Lately, the majority of research works is designed for Sentiment analysis by application of an organization and ranking techniques. But it suffers less exactness of the accurate classification of the customer reviews.

The …

Turbulent Structures In Coupled Wind-Wave Flows, Cerrina Mouchref

Dissertations and Theses

The interactions between wind and waves in offshore environments are complex and have yet to be fully understood. Analyzing these interactions is motivated by an increased interest in climate modeling and the deployment of offshore construction, such as offshore wind farms. In this study, experiments are performed in a wind tunnel using particle image velocimetry (PIV) to analyze wind-wave interactions over various wave and wind speeds. The addition of the wave, a moving boundary, leads to the use of Reynolds triple decomposition in order to separate the turbulent and wave-phase coherent fluctuations. A curvilinear coordinate system was used to analyze …

State-Of-Charge Estimation Using Deep Learning For Electric Vehicles, Samer Yahya Ribhe Tahboub

LSU Master's Theses

This thesis investigates the application of deep learning models for State of Charge (SOC) estimation in Battery Management Systems (BMS) for electric vehicles (EVs), focusing on optimizing EV range, lifespan, and performance while addressing challenges like range anxiety. The study explores three deep learning architectures—Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU)—each designed to capture complex temporal dependencies in battery data. The LSTM model is trained on EV battery data, including voltage, current, temperature, and SOC, providing a strong baseline for SOC estimation. The BiLSTM model enhances accuracy by processing data in both forward and backward …

Mitigating The Impacts Of Future Climate Change On Urban Infrastructure In Alabama Through Updating Precipitation Intensity-Duration-Frequency (Idf) Curves, Kofi Ntow Opare

All ETDs from UAB

Climate change is set to profoundly impact urban infrastructure, causing increased flooding and storm damage, necessitating the reevaluation and adaptation of design methodologies to account for increasing precipitation extremes. This dissertation aims to enhance the resilience of urban infrastructure in Alabama by updating Precipitation Intensity-Duration-Frequency (IDF) curves, which are crucial for designing stormwater management systems, drainage networks, and flood control structures. Traditional IDF curves, derived from historical rainfall data, operate under the assumption of stationarity, an assumption increasingly invalidated by climate change. This research employs the Generalized Extreme Value (GEV) distribution and compares the efficacy of L-moments and Generalized Maximum …

Processing, Testing, Failure Analysis, And Modeling Of Elementary Natural Fiber-Reinforced Composites, Shuo Sun

All ETDs from UAB

Natural fiber reinforced composites have garnered significant interest as potential substitutes for conventional materials because of their eco-friendly attributes and favorable physical and mechanical properties. Typically, natural fibers undergo chemical treatments to enhance their compatibility with the polymer matrix prior to composite production. However, these treatments primarily affect the surface of the fiber bundles and have a limited impact on the inner elementary fibers within the bundle. This research work introduced a mechanical treatment method for hemp fiber by using an elevated temperature aqueous condition and mechanical force, which broke down the technical fiber bundles into elementary fibers and created …

Origami Without Paper: Surrogate Folds For Origami-Inspired Mechanisms, Ivyann Oveson Running

Theses and Dissertations

Origami is a useful tool for generating novel spatial mechanisms that can address needs in a variety of fields. However, replicating paper folding in other materials requires surrogate folds---some way to approximate folding in otherwise rigid materials. This work presents a collection of potential surrogate fold designs suitable for use in origami-inspired applications. The designs are sorted into families and rated against several design characteristics of interest to engineers and designers to create the Surrogate Fold Catalog. The catalog is formatted to be searchable and filterable based on manufacturability, kinematic motion, and additional utility. Using this collection of surrogate folds …

Non-Catalytic Direct Partial Oxidation Of Methane To Methanol In A Wall-Coated Microreactor, Kelly Cohen

LSU Doctoral Dissertations

This project used an integrated mixer-reactor-heat exchanger microtube scalable module for the non-catalytic direct partial oxidation of methane in natural gas to methanol at elevated pressures (70-95 bar), reaction temperatures of 380-460C, reactant methane:air ratios of 0.5-4.4 and reaction zone residence times on the order of 1 min. Currently, methane in remote locations is often flared in large quantities rather than transported or converted to the more easily transportable methanol. However, if this gaseous methane were converted to liquid methanol at the wellhead, it could be transported in ways other than pipeline or used onsite.

Additionally, methane is currently converted …

Integration Of Agile Approach Into The Implementation Of The Iso/Sae 21434 On Top Of The V-Model To Enable Continuous Secure-By-Design Automotive Cybersecurity Development, Pooja Patil

Master's Theses and Doctoral Dissertations

The rapid evolution of technology is revolutionizing the automotive industry, with connected and autonomous vehicles at the forefront. These vehicles rely on complex digital ecosystems to enhance safety and efficiency but are increasingly vulnerable to cybersecurity threats. Addressing these challenges requires following robust development methodologies, while complying with cybersecurity standards. This study introduces a framework that merges the widely used agile methodology practices with the ISO/SAE 21434 standard to support secure-by-design automotive product development. Traditional development approaches like the V-model provide structured and linear project phases, but they often lack the flexibility and the ability to adapt to evolving security …