Engineering Commons^™

Meta-Algorithms In Machine Learning, Vishnu Pendyala

Open Educational Resources

This presentation explores how to make the best of models impacted by bias and variance. Meta-learning minimizes loss. Ensemble methods, including Bagging, Adaboost, Random Forest, Gradient Boosting, and Stacking, are discussed. These methods perturb data (X or Y) using techniques like bootstrap sampling, k-fold sampling, weighted sampling, and random subspaces. Models are generated in parallel or sequentially, with aggregation strategies such as mean, mode, weighted response, and metamodel. The presentation also touches upon deep learning and one-shot learning, and explains how distances become less meaningful in high dimensions.

More details: https://events.vtools.ieee.org/m/315184

Video Recording: https://ieeetv.ieee.org/video/meta-algorithms-in-machine-learning

Application Of Crowdsourcing And Machine Learning To Predict Sentiments In Textual Student Feedback In Large Computer Science Classes, Robert Kasumba

McKelvey School of Engineering Graduate Student Theses & Dissertations

With the increasing enrollment numbers into popular computer science courses, there is a need to bridge the similarly increasing feedback gap between individual students and course instructors. One way to address this challenge is for instructors to collect feedback from students in form of textual reviews or unit-of-study reflections – however, manually reading these reviews is time-consuming, and self-reported Likert scale responses are noisy. Rule-based approaches to sentiment analysis such as VADER (Valence Aware Dictionary and sEntiment Reasoner) have been used to capture the sentiments conveyed in textual feedback, they however fail to capture contextual differences as many words have …

Application Of Machine Learning For Predicting Iemi Upset In Multi-Architecture Microcontrollers, Daniel S. Guillette

Electrical and Computer Engineering ETDs

Four microcontrollers were programmed to execute a simple counting program. Pulsed RF signals – also known as Intentional ElectroMagnetic Interference (IEMI) – were injected into the clock input of the microcontrollers. At the same time, the output lines were monitored to determine whether the IEMI signal altered the output of the counting program – referred to as an upset. A state-of-the-art automated testing apparatus was used to collect and process 120,960 samples of IEMI upset data. The data was used to perform a traditional upset trends study and train a series of machine learning (ML) techniques – k-Nearest Neighbors, Support …

A Data-Based Framework For Monitoring And Controlling Particulate Systems, Vidhyadhar Manee

LSU Doctoral Dissertations

One of the limitations of conventional monitoring tools in crystallization is the inability to deal with high solids concentration. Image-based monitoring, in which RGB images of the solution are captured and analyzed by an object detection software, has been a promising alternative. The software used in these tools primarily depends on hand-coded heuristics to distinguish between the signal and the noise. With the recent success of supervised deep learning, a newer paradigm has emerged in which the heuristics can be learnt from labeled images. This approach is founded on the idea that it is easier to develop labels for data …

A Quantitative Comparison Of Algorithmic And Machine Learning Network Flow Throughput Prediction, Cayden Wagner

All Theses

Applications ranging from video meetings, live streaming, video games, autonomous vehicle operations, and algorithmic trading heavily rely on low latency communication to operate optimally. A solution to fully support this growing demand for low latency is called dual-queue active queue management (AQM). Dual-queue AQM's functionality is reduced without network traffic throughput prediction.

Perhaps due to the current popularity of machine learning, there is a trend to adopt machine learning models over traditional algorithmic throughput prediction approaches without empirical support. This study tested the effectiveness of machine learning as compared to time series forecasting algorithms in predicting per-flow network traffic throughput …

Supervised Representation Learning For Improving Prediction Performance In Medical Decision Support Applications, Phawis Thammasorn

Graduate Theses and Dissertations

Machine learning approaches for prediction play an integral role in modern-day decision supports system. An integral part of the process is extracting interest variables or features to describe the input data. Then, the variables are utilized for training machine-learning algorithms to map from the variables to the target output. After the training, the model is validated with either validation or testing data before making predictions with a new dataset. Despite the straightforward workflow, the process relies heavily on good feature representation of data. Engineering suitable representation eases the subsequent actions and copes with many practical issues that potentially prevent the …

Predicting The Progression Of Diabetes Mellitus Using Dynamic Plantar Pressure Parameters, Mathew Sunil Varre

UNLV Theses, Dissertations, Professional Papers, and Capstones

Introduction: Diabetic peripheral neuropathy is one of the common complications of type-2 diabetes mellitus (DM). Changes in the intrinsic plantar tissue coupled with repetitive mechanical loads and loss of sensation may lead to foot related complications (skin break down, ulcerations, and amputations) in persons with neuropathy if left untreated. The purpose of this dissertation was to stratify individuals with pre-diabetes, diabetes with and without neuropathy using dynamic plantar pressure parameters during walking, using machine learning algorithms.Methods: Plantar pressure data was collected from one hundred participants during walking with pressure measuring insoles fixed between the feet and thin socks. Simultaneously high-definition …

Generative Designs Of Lightweight Air-Cooled Heat Exchangers, Connor Miller

Mechanical Engineering Undergraduate Honors Theses

The development of high-performance air-cooled heat exchangers is required to permit the rapid growth of vehicle and aircraft electrification. In electric vehicles and airliners, the motors and power electronics are integrated into a compact space, leading to unprecedently high power density. To achieve higher overall thermal efficiency, the heat exchangers must be extremely light while maintaining their heat transfer performance and mechanical robustness. Recently advances in 3D metal printing, e.g., direct metal laser sintering, and selective laser melting, have enabled the manufacturing of high-performance robust heat exchangers by eliminating thermal boundary resistance and ensuring a uniform thermal expansion coefficient. Nonetheless, …

Material Synthesis And Machine Learning For Additive Manufacturing, Jaime Eduardo Regis

Open Access Theses & Dissertations

The goal of this research was to address three key challenges in additive manufacturing (AM), the need for feedstock material, minimal end-use fabrication from lack of functionality in commercially available materials, and the need for qualification and property prediction in printed structures. The near ultraviolet-light assisted green reduction of graphene oxide through L-ascorbic acid was studied with to address the issue of low part strength in additively manufactured parts by providing a functional filler that can strengthen the polymer matrix. The synthesis of self-healing epoxy vitrimers was done to adapt high strength materials with recyclable properties for compatibility with AM …

Machine Learning Analysis Of Acoustic Attenuation Measurements For Cellular Characterization., John T. Moore

Electronic Theses and Dissertations

T-cell therapies have been gaining popularity in recent years due to their cancer fighting potential. With remission rates improving in this field of immunotherapy, the demand for T-cell therapies has also increased; however, the cell processing techniques for these therapeutic products have yet to rise to the level of demand. The manufacturing process takes too long and a significant amount of processed cell batches can fail to meet safety requirements. These limitations of cell processing can be detrimental to patients seeking T-cell therapies. While current products have improved the time it takes to manufacture these therapeutic products, there is still …

Performing Memory Forensics For Object Recovery From Android Application Memory, Sneha Sudhakaran

LSU Doctoral Dissertations

The analysis of application-specific behavior has become an increasingly important technique in cyber forensics and incident response. The ability to determine the precise actions taken by a user can be the difference between a successful analysis and one that fails to meet its goals. The precise actions includes URLs visited, files downloaded, messages sent and received, images viewed, and data accessed. Evidence extraction from application memory at runtime is an effective solution to successfully extract valuable objects allocated by each application, and it is evident that there is a need for more Android forensics analysis tools that support recovering evidence …

Art To Influence Creativity In Algorithmic Composition, Tyler Braithwaite

Honors Theses

Advances in Recurrent Neural Network (RNN) techniques have caused an explosion of problems posed that revolve around the mass analysis and generation of sequential data, including symbolic music. Building off the work of Nathaniel Patterson’s Musical Autocomplete: An LSTM Approach, we extend this problem of continuing a composition by examining the creative impact that injecting latent-space encoded image data, specifically fine art from the WikiArt Dataset, has on the musical output of RNN architectures designed for autocomplete. For comparison purposes with Patterson, we will also be using a corpus of Erik Satie’s piano music for training, validation, and testing.

An Analytical Methodology To Security Constraints Management In Power System Operation, Shubo Zhang

ETD Archive

In a deregulated electricity market, Independent System Operators (ISOs) are responsible for dispatching power to the load securely, efficiently, and economically. ISO performs Security Constrained Unit Commitment (SCUC) to guarantee sufficient generation commitment, maximized social welfare and facilitating market-driven economics. A large number of security constraints would render the model impossible to solve under time requirements. Developing a method to identify the minimum set of security constraints without overcommitting is necessary to reduce Mixed Integer Linear Programming (MILP) solution time. To overcome this challenge, we developed a powerful tool called security constraint screening. The proposed approach effectively filters out non-dominating …

Remote Crop Disease Detection Using Deep Learning With Iot, Ivy Chung, Anoushka Gupta

Electrical and Computer Engineering Senior Theses

Agriculture is such a vital part of our society, and according to the United Nations’ Food and Agricultural Organization (FAO), plant diseases are considered one of the two main causes of decreasing food availability. This paper explores not only the methods and findings of building a CNN-based disease detection model, but that of building a deployable remote crop disease detection system incorporating IoT technology. By using transfer learning with AlexNet, we were able to predict with 89.8% accuracy tomato plant images into one of the ten pre-defined disease classes. Our proposed system tracks plant health throughout the day by using …

Conditional Variational Autoencoder (Cvae) For The Augmentation Of Ecl Biosensor Data, Matthew Dulcich

Honors Theses

Machine Learning (ML) is vastly improving the world, from computer vision to fully self-driving cars, we are now able accomplish objectives that were thought to only be dreams. In order to train ML models accurately, they require mountains of information to work with, but sometimes it becomes impossible to collect the data needed, so we turn to data augmentation. In this project we use a conditional variational auto encoder to supplement the original video electrochemiluminescence biosensor dataset, in order to increase the accuracy of a future classification model. In other words, using a cVAE we will create unique realistic videos …

Deep Learning Based Generative Materials Design, Yong Zhao

Theses and Dissertations

Discovery of novel functional materials is playing an increasingly important role in many key industries such as lithium batteries for electric vehicles and cell phones. However experimental tinkering of existing materials or Density Functional Theory (DFT) based screening of known crystal structures, two of the major current materials design approaches, are both severely constrained by the limited scale (around 250,000 in ICSD database) and diversity of existing materials and the lack of a sufficient number of materials with annotated properties. How to generate a large number of physically feasible, stable, and synthesizable crystal materials and build accurate property prediction models …

Exploring The Efficiency Of Neural Architecture Search (Nas) Modules, Joshua Dulcich

Honors Theses

Machine learning is obscure and expensive to develop. Neural architecture search (NAS) algorithms automate this process by learning to create premier ML networks, minimizing the bias and necessity of human experts. From this recently emerging field, most research has focused on optimizing a promisingly unique combination of NAS’s three segments. Despite regularly acquiring state of the art results, this practice sacrifices computing time and resources for slight increases in accuracy; this also obstructs performance comparison across papers. To resolve this issue, we use NASLib’s modular library to test the efficiency per module in a unique subset of combinations. Each NAS …

Quadratic Neural Network Architecture As Evaluated Relative To Conventional Neural Network Architecture, Reid Taylor

Senior Theses

Current work in the field of deep learning and neural networks revolves around several variations of the same mathematical model for associative learning. These variations, while significant and exceptionally applicable in the real world, fail to push the limits of modern computational prowess. This research does just that: by leveraging high order tensors in place of 2nd order tensors, quadratic neural networks can be developed and can allow for substantially more complex machine learning models which allow for self-interactions of collected and analyzed data. This research shows the theorization and development of mathematical model necessary for such an idea to …

Seabem: An Artificial Intelligence Powered Web Application To Predict Cover Crop Biomass, Aime Christian Tuyishime, Andrea Basche

Honors Program: Senior Projects (Public)

SEABEM, the Stacked Ensemble Algorithms Biomass Estimator Model, is a web application with a stacked ensemble of Machine Learning (ML) algorithms running on the backend to predict cover crop biomass for locations in Sub-Saharan. The SEABEM model was developed using a previously developed database of crop growth and yield that included site characteristics such as latitude, longitude, soil texture (sand, silt, and clay percentages), temperature, and precipitation. The goal of SEABEM is to provide global farmers, mainly small-scale African farmers, the knowledge they need before practicing and benefiting from cover crops while avoiding the expensive and time-consuming operations that come …

Project Leanness Score: A Machine Learning Approach, Julia Said

Theses and Dissertations

The construction industry is known to have several inadequacies in resource utilization leading to cost and schedule overruns. One of the popular recent methods that attempts to eliminate these inadequacies is lean construction principles, techniques and tools. Lean construction is a philosophy, backed with principles and tools, aiming at maximizing value, eliminating waste, optimizing efficiency, and seeking continuous improvement. Lean construction techniques (such as pull planning, just-in-time delivery, fail safe for quality, etc.) are widely researched and well developed. However, their implementation in construction sites is tricky as their success depends on several other factors such as the level of …

An Intelligent Distributed Ledger Construction Algorithm For Iot, Charles Rawlins, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

Blockchain is the next generation of secure data management that creates near-immutable decentralized storage. Secure cryptography created a niche for blockchain to provide alternatives to well-known security compromises. However, design bottlenecks with traditional blockchain data structures scale poorly with increased network usage and are extremely computation-intensive. This made the technology difficult to combine with limited devices, like those in Internet of Things networks. In protocols like IOTA, replacement of blockchain's linked-list queue processing with a lightweight dynamic ledger showed remarkable throughput performance increase. However, current stochastic algorithms for ledger construction suffer distinct trade-offs between efficiency and security. This work proposed …

Hybridization Of Biologically Inspired Algorithms For Discrete Optimisation Problems, Elihu Essian-Thompson

Dissertations

In the field of Optimization Algorithms, despite the popularity of hybrid designs, not enough consideration has been given to hybridization strategies. This paper aims to raise awareness of the benefits that such a study can bring. It does this by conducting a systematic review of popular algorithms used for optimization, within the context of Combinatorial Optimization Problems. Then, a comparative analysis is performed between Hybrid and Base versions of the algorithms to demonstrate an increase in optimization performance when hybridization is employed.

A Machine Learning Approach To Intended Motion Prediction For Upper Extremity Exoskeletons, Justin Berdell

Graduate Research Theses & Dissertations

A fully solid-state, software-defined, one-handed, handle-type control device built around a machine-learning (ML) model that provides intuitive and simultaneous control in position and orientation each in a full three degrees-of-freedom (DOF) is proposed in this paper. The device, referred to as the “Smart Handle”, and it is compact, lightweight, and only reliant on low-cost and readily available sensors and materials for construction. Mobility chairs for persons with motor difficulties could make use of a control device that can learn to recognize arbitrary inputs as control commands. Upper-extremity exoskeletons used in occupational settings and rehabilitation require a natural control device like …

Modeling Crash Severity And Collision Types Using Machine Learning, Amit Kumar, Hari Krishnan Melempat Kalapurayil

Data

Traffic safety analysis is the fundamental step for reducing economic, social, and environmental cost incurred due to traffic accidents. The essence of traffic safety is understanding the factors affecting crash occurrence, injury severity and collision type and their underlying relationships and predict-prevent future crash instances. Crash injury severity studies in past have utilized numerous statistical, econometric and Machine Learning (ML) and Artificial Intelligence (AI) tools to extract the underlying relationship between the crash causal factors and the consequent severity or collision type. The study aims to explore the Multi-Label Classification (MLC) tool from the domain of Artificial Intelligence (AI) for …

Modeling Crash Severity And Collision Types Using Machine Learning, Amit Kumar, Hari Krishnan Melempat Kalapurayil

Publications

Traffic safety analysis is the fundamental step for reducing economic, social, and environmental cost incurred due to traffic accidents. The essence of traffic safety is understanding the factors affecting crash occurrence, injury severity and collision type and their underlying relationships and predict-prevent future crash instances. Crash injury severity studies in past have utilized numerous statistical, econometric and Machine Learning (ML) and Artificial Intelligence (AI) tools to extract the underlying relationship between the crash causal factors and the consequent severity or collision type. The study aims to explore the Multi-Label Classification (MLC) tool from the domain of Artificial Intelligence (AI) for …

Modeling Nonlinear Dynamic Systems Using Bss-Anova Gaussian Process, Kyle Matthew Hayes

Graduate Theses, Dissertations, and Problem Reports (ETD)

Nonlinear dynamic systems are some of the most common variety of systems encountered in the sciences, but are the potentially more onerous to model through system identification than static systems due to their added complexity, sensitivity to initial conditions, and the potential application of new dynamic and nonlinear behavior through any time dependent forcing functions. The BSS-ANOVA Gaussian Process is a Machine Learning method for dynamic system ID that possesses several attributes that make it a natural candidate for this variety of problem. BSS-ANOVA is fully Bayesian, works best for continuous tabular datasets, and fast training and inference times and …

Efficacy Of Reported Issue Times As A Means For Effort Estimation, Paul Phillip Maclean

Graduate Theses, Dissertations, and Problem Reports (ETD)

Software effort is a measure of manpower dedicated to developing and maintaining and software. Effort estimation can help project managers monitor their software, teams, and timelines. Conversely, improper effort estimation can result in budget overruns, delays, lost contracts, and accumulated Technical Debt (TD). Issue Tracking Systems (ITS) have become mainstream project management tools, with over 65,000 companies using Jira alone. ITS are an untapped resource for issue resolution effort research. Related work investigates issue effort for specific issue types, usually Bugs or similar. They model their developer-documented issue resolution times using features from the issues themselves. This thesis explores a …

Combustion Feature Characterization Using Computer Vision Diagnostics Within Rotating Detonation Combustors, Kristyn B. Johnson May

Graduate Theses, Dissertations, and Problem Reports (ETD)

In recent years, the possibilities of higher thermodynamic efficiency and power output have led to increasing interest in the field of pressure gain combustion (PGC). Currently, a majority of PGC research is concerned with rotating detonation engines (RDEs), devices which may theoretically achieve pressure gain across the combustor. Within the RDE, detonation waves propagate continuously around a cylindrical annulus, consuming fresh fuel mixtures supplied from the base of the RDE annulus. Through constant-volume heat addition, pressure gain combustion devices theoretically achieve lower entropy generation compared to Brayton cycle combustors. RDEs are being studied for future implementation in gas turbines, where …

Use Of Image Processing Techniques And Machine Learning For Better Understanding Of T Gondii Biology, Amer Asiri

Theses and Dissertations--Biomedical Engineering

Almost one in every three people worldwide is infected with Toxoplasma gondii (T. gondii). The biology and growth of the parasite’s bradyzoite form in host tissue cysts are not well understood. T. gondii’s metabolic state influences the morphology of its single mitochondrion, which can be visualized using fluorescence microscopy with specific dyes. Hence, fluorescence microscopy images of cysts purified from infected mouse brains carry biological information about bradyzoites, the poorly understood form of the parasite within them. With the help of fluorescence microscopy techniques, previous studies extracted images of the mitochondrion, nucleus, and the inner membrane complex (IMC) …

Molecular Modeling Of High-Performance Thermoset Polymer Matrix Composites For Aerospace Applications, Prathamesh P. Deshpande

Dissertations, Master's Theses and Master's Reports

The global efforts from major space agencies to transport humans to Mars will require a novel lightweight and ultra-high strength material for the spacecraft structure. Three decades of research with the carbon nanotubes (CNTs) have proved that the material can be an ideal candidate for the composite reinforcement if certain shortcomings are overcome. Also, the rapid development of the polymer resin industry has introduced a wide range of high-performance resins that show high compatibility with the graphitic surface of the CNTs. This research explores the computational design of these materials and evaluates their efficacy as the next generation of aerospace …