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

Engineering Commons

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

Theses/Dissertations

Neural network

Discipline
Institution
Publication Year
Publication

Articles 1 - 30 of 47

Full-Text Articles in Engineering

Secure Mobile Computing By Using Convolutional And Capsule Deep Neural Networks, Rui Ning Aug 2020

Secure Mobile Computing By Using Convolutional And Capsule Deep Neural Networks, Rui Ning

Electrical & Computer Engineering Theses & Disssertations

Mobile devices are becoming smarter to satisfy modern user's increasing needs better, which is achieved by equipping divers of sensors and integrating the most cutting-edge Deep Learning (DL) techniques. As a sophisticated system, it is often vulnerable to multiple attacks (side-channel attacks, neural backdoor, etc.). This dissertation proposes solutions to maintain the cyber-hygiene of the DL-Based smartphone system by exploring possible vulnerabilities and developing countermeasures.

First, I actively explore possible vulnerabilities on the DL-Based smartphone system to develop proactive defense mechanisms. I discover a new side-channel attack on smartphones using the unrestricted magnetic sensor data. I demonstrate that attackers ...


Evaluating And Improving The Seu Reliability Of Artificial Neural Networks Implemented In Sram-Based Fpgas With Tmr, Brittany Michelle Wilson Jun 2020

Evaluating And Improving The Seu Reliability Of Artificial Neural Networks Implemented In Sram-Based Fpgas With Tmr, Brittany Michelle Wilson

Theses and Dissertations

Artificial neural networks (ANNs) are used in many types of computing applications. Traditionally, ANNs have been implemented in software, executing on CPUs and even GPUs, which capitalize on the parallelizable nature of ANNs. More recently, FPGAs have become a target platform for ANN implementations due to their relatively low cost, low power, and flexibility. Some safety-critical applications could benefit from ANNs, but these applications require a certain level of reliability. SRAM-based FPGAs are sensitive to single-event upsets (SEUs), which can lead to faults and errors in execution. However there are techniques that can mask such SEUs and thereby improve the ...


Brian Valdez - Dynamics And Control Of A 3-Dof Manipulator With Deep Learning Feedback, Brian Orlando Valdez Jan 2020

Brian Valdez - Dynamics And Control Of A 3-Dof Manipulator With Deep Learning Feedback, Brian Orlando Valdez

Open Access Theses & Dissertations

With the ever-increasing demands in the space domain and accessibility to low-cost small satellite platforms for educational and scientific projects, efforts are being made in various technology capacities including robotics and artificial intelligence in microgravity. The MIRO Center for Space Exploration and Technology Research (cSETR) prepares the development of their second nanosatellite to launch to space and it is with that opportunity that a 3-DOF robotic arm is in development to be one of the payloads in the nanosatellite. Analyses, hardware implementation, and testing demonstrate a potential positive outcome from including the payload in the nanosatellite and a deep learning ...


Design, Modeling And Optimization Of Reciprocating Tubular Permanent Magnet Linear Generators For Free Piston Engine Applications, Jayaram Subramanian Jan 2020

Design, Modeling And Optimization Of Reciprocating Tubular Permanent Magnet Linear Generators For Free Piston Engine Applications, Jayaram Subramanian

Graduate Theses, Dissertations, and Problem Reports

Permanent Magnet Linear Generators (PMLG) are electric generators which convert the linear motion into electricity. One of the applications of the PMLG system is with free piston engines. Here, the piston is moved by the expander using an internal combustion engine or a Stirling engine. Other applications of the PMLG are wave energy conversion, micro energy harvesters, and supercritical CO2 expander systems. The most common technology of the electric generators is a rotary electric generator. The current technology of the engine-generators (GENSET) is of a rotary type which uses a crankshaft to convert the linear motion to rotary motion ...


Fault Detection And Classification Of A Single Phase Inverter Using Artificial Neural Networks, Ayomikun Samuel Orukotan Jan 2020

Fault Detection And Classification Of A Single Phase Inverter Using Artificial Neural Networks, Ayomikun Samuel Orukotan

All Graduate Theses, Dissertations, and Other Capstone Projects

The detection of switching faults of power converters or the Circuit Under Test (CUT) is real-time important for safe and efficient usage. The CUT is a single-phase inverter. This thesis presents two unique methods that rely on backpropagation principles to solve classification problems with a two-layer network. These mathematical algorithms or proposed networks are able to diagnose single, double, triple, and multiple switching faults over different iterations representing range of frequencies. First, the fault detection and classification problems are formulated as neural network-based classification problems and the neural network design process is clearly described. Then, neural networks are trained over ...


Instructor Activity Recognition Using Smartwatch And Smartphone Sensors, Zayed Uddin Chowdhury Jan 2020

Instructor Activity Recognition Using Smartwatch And Smartphone Sensors, Zayed Uddin Chowdhury

Electronic Theses and Dissertations

During a classroom session, an instructor performs several activities, such as writing on the board, speaking to the students, gestures to explain a concept. A record of the time spent in each of these activities could be valuable information for the instructors to virtually observe their own style of instruction. It can help in identifying activities that engage the students more, thereby enhancing teaching effectiveness and efficiency. In this work, we present a preliminary study on profiling multiple activities of an instructor in the classroom using smartwatch and smartphone sensor data. We use 2 benchmark datasets to test out the ...


Exploitation Of Robust Aoa Estimation And Low Overhead Beamforming In Mmwave Mimo System, Yuyan Zhao Nov 2019

Exploitation Of Robust Aoa Estimation And Low Overhead Beamforming In Mmwave Mimo System, Yuyan Zhao

Electronic Thesis and Dissertation Repository

The limited spectral resource for wireless communications and dramatic proliferation of new applications and services directly necessitate the exploitation of millimeter wave (mmWave) communications. One critical enabling technology for mmWave communications is multi-input multi-output (MIMO), which enables other important physical layer techniques, specifically beamforming and antenna array based angle of arrival (AoA) estimation. Deployment of beamforming and AoA estimation has many challenges. Significant training and feedback overhead is required for beamforming, while conventional AoA estimation methods are not fast or robust. Thus, in this thesis, new algorithms are designed for low overhead beamforming, and robust AoA estimation with significantly reduced ...


Unsupervised-Learning Assisted Artificial Neural Network For Optimization, Varun Kote Jul 2019

Unsupervised-Learning Assisted Artificial Neural Network For Optimization, Varun Kote

Mechanical & Aerospace Engineering Theses & Dissertations

Innovations in computer technology made way for Computational Fluid Dynamics (CFD) into engineering, which supported the development of new designs by reducing the cost and time by lowering the dependency on experimentation. There is a further need to make the process of development more efficient. One such technology is Artificial Intelligence. In this thesis, we explore the application of Artificial Intelligence (AI) in CFD and how it can improve the process of development.

AI is used as a buzz word for the mechanism which can learn by itself and make the decision accordingly. Machine learning (ML) is a subset of ...


Quantitative Hyperspectral Imaging Pipeline To Recover Surface Images From Crism Radiance Data, Linyun He May 2019

Quantitative Hyperspectral Imaging Pipeline To Recover Surface Images From Crism Radiance Data, Linyun He

Engineering and Applied Science Theses & Dissertations

Hyperspectral data are important for remote applications such as mineralogy, geology, agriculture and surveillance sensing. A general pipeline converting measured hyperspectral radiance to the surface reflectance image can provide planetary scientists with clean, robust and repeatable products to work on.

In this dissertation, the surface single scattering albedos (SSAs), the ratios of scattering eciency to scattering plus absorption eciences of a single particle, are selected to describe the reflectance. Moreover, the IOF, the ratio of measured spectral radiance (in the unit of watts per squared-meter and micrometer) to the solar spectral radiance (in the unit of watts per squared-meter and ...


American Sign Language Recognition Using Machine Learning And Computer Vision, Kshitij Bantupalli, Ying Xie Feb 2019

American Sign Language Recognition Using Machine Learning And Computer Vision, Kshitij Bantupalli, Ying Xie

Master of Science in Computer Science Theses

Speech impairment is a disability which affects an individual’s ability to communicate using speech and hearing. People who are affected by this use other media of communication such as sign language. Although sign language is ubiquitous in recent times, there remains a challenge for non-sign language speakers to communicate with sign language speakers or signers. With recent advances in deep learning and computer vision there has been promising progress in the fields of motion and gesture recognition using deep learning and computer vision-based techniques. The focus of this work is to create a vision-based application which offers sign language ...


Air Void Clustering In Retempering Concrete And Its Contribution To Compressive Strength, Wen Sun Jan 2019

Air Void Clustering In Retempering Concrete And Its Contribution To Compressive Strength, Wen Sun

Graduate Theses and Dissertations

Air void clustering is a phenomenon in concrete in which air bubbles accumulate around the coarse aggregate. It is considered as a major cause of reduction of concrete strength.

This thesis focuses on the effect of different variables on air void clustering and its contribution to the performance of concrete. Six variables were considered in the study, including cement type (low alkali cement and TIL cement), fly ash (fly ash A and B), coarse aggregate type (lime stone and river gravel), chemical admixture type (admixture 1 and 2) , mixing water temperature (70℉ and 90℉), and retempering (with and without). A ...


Application Of Sensor Fusion For Si Engine Diagnostics And Combustion Feedback, Fnu Muralidhar Nischal Jan 2019

Application Of Sensor Fusion For Si Engine Diagnostics And Combustion Feedback, Fnu Muralidhar Nischal

Dissertations, Master's Theses and Master's Reports

Shifting consumer mindsets and evolving government norms are forcing automotive manufacturers the world over to improve vehicle performance and also reduce greenhouse gas emissions. A critical aspect of achieving future fuel economy and emission targets is improved powertrain control and diagnostics.

This study focuses on using a sensor fusion based approach to improving control and diagnostics in a gasoline engine. A four cylinder turbocharged engine was instrumented with a suite of sensors including ion sensors, exhaust pressure sensors, crank position sensors and accelerometers. The diagnostic potential of these sensors was studied in detail. The ability of these sensors to detect ...


Efficient Machine Learning: Models And Accelerations, Zhe Li Dec 2018

Efficient Machine Learning: Models And Accelerations, Zhe Li

Dissertations - ALL

One of the key enablers of the recent unprecedented success of machine learning is the adoption of very large models. Modern machine learning models typically consist of multiple cascaded layers such as deep neural networks, and at least millions to hundreds of millions of parameters (i.e., weights) for the entire model. The larger-scale model tend to enable the extraction of more complex high-level features, and therefore, lead to a significant improvement of the overall accuracy. On the other side, the layered deep structure and large model sizes also demand to increase computational capability and memory requirements. In order to ...


Amplifying The Prediction Of Team Performance Through Swarm Intelligence And Machine Learning, Erick Michael Harris Dec 2018

Amplifying The Prediction Of Team Performance Through Swarm Intelligence And Machine Learning, Erick Michael Harris

Master's Theses

Modern companies are increasingly relying on groups of individuals to reach organizational goals and objectives, however many organizations struggle to cultivate optimal teams that can maximize performance. Fortunately, existing research has established that group personality composition (GPC), across five dimensions of personality, is a promising indicator of team effectiveness. Additionally, recent advances in technology have enabled groups of humans to form real-time, closed-loop systems that are modeled after natural swarms, like flocks of birds and colonies of bees. These Artificial Swarm Intelligences (ASI) have been shown to amplify performance in a wide range of tasks, from forecasting financial markets to ...


Leveraging Eye Structure And Motion To Build A Low-Power Wearable Gaze Tracking System, Addison Mayberry Oct 2018

Leveraging Eye Structure And Motion To Build A Low-Power Wearable Gaze Tracking System, Addison Mayberry

Doctoral Dissertations

Clinical studies have shown that features of a person's eyes can function as an effective proxy for cognitive state and neurological function. Technological advances in recent decades have allowed us to deepen this understanding and discover that the actions of the eyes are in fact very tightly coupled to the operation of the brain. Researchers have used camera-based eye monitoring technology to exploit this connection and analyze mental state across across many different metrics of interest. These range from simple things like attention and scene processing, to impairments such as a fatigue or substance use, and even significant mental ...


Identification And Optimal Linear Tracking Control Of Odu Autonomous Surface Vehicle, Nadeem Khan Jul 2018

Identification And Optimal Linear Tracking Control Of Odu Autonomous Surface Vehicle, Nadeem Khan

Mechanical & Aerospace Engineering Theses & Dissertations

Autonomous surface vehicles (ASVs) are being used for diverse applications of civilian and military importance such as: military reconnaissance, sea patrol, bathymetry, environmental monitoring, and oceanographic research. Currently, these unmanned tasks can accurately be accomplished by ASVs due to recent advancements in computing, sensing, and actuating systems. For this reason, researchers around the world have been taking interest in ASVs for the last decade. Due to the ever-changing surface of water and stochastic disturbances such as wind and tidal currents that greatly affect the path-following ability of ASVs, identification of an accurate model of inherently nonlinear and stochastic ASV system ...


Neural Network On Virtualization System, As A Way To Manage Failure Events Occurrence On Cloud Computing, Khoi Minh Pham Jun 2018

Neural Network On Virtualization System, As A Way To Manage Failure Events Occurrence On Cloud Computing, Khoi Minh Pham

Electronic Theses, Projects, and Dissertations

Cloud computing is one important direction of current advanced technology trends, which is dominating the industry in many aspects. These days Cloud computing has become an intense battlefield of many big technology companies, whoever can win this war can have a very high potential to rule the next generation of technologies. From a technical point of view, Cloud computing is classified into three different categories, each can provide different crucial services to users: Infrastructure (Hardware) as a Service (IaaS), Software as a Service (SaaS), and Platform as a Service (PaaS). Normally, the standard measurements for cloud computing reliability level is ...


An Investigation Of The Cortical Learning Algorithm, Anthony C. Samaritano May 2018

An Investigation Of The Cortical Learning Algorithm, Anthony C. Samaritano

Theses and Dissertations

Pattern recognition and machine learning fields have revolutionized countless industries and applications from biometric security to modern industrial assembly lines. The fields continue to accelerate as faster, more efficient processing hardware becomes commercially available. Despite the accelerated growth of the pattern recognition and machine learning fields, computers still are unable to learn, reason, and perform rudimentary tasks that humans and animals find routine. Animals are able to move fluidly, understand their environment, and maximize their chances of survival through adaptation - animals demonstrate intelligence. A primary argument in this thesis that we have not yet achieved a level of intelligence similar ...


Comparison Of Google Image Search And Resnet Image Classification Using Image Similarity Metrics, David Smith May 2018

Comparison Of Google Image Search And Resnet Image Classification Using Image Similarity Metrics, David Smith

Computer Science and Computer Engineering Undergraduate Honors Theses

In this paper, we compare the results of ResNet image classification with the results of Google Image search. We created a collection of 1,000 images by performing ten Google Image searches with a variety of search terms. We classified each of these images using ResNet and inspected the results. The ResNet classifier predicted the category that matched the search term of the image 77.5% of the time. In our best case, with the search term “forklift”, the classifier categorized 92 of the 100 images as forklifts. In the worst case, for the category “hammer”, the classifier matched the ...


Real Time Traffic Congestion Detection Using Images, Revanth Ayala Somayajula Jan 2018

Real Time Traffic Congestion Detection Using Images, Revanth Ayala Somayajula

Creative Components

There is an increasing demand to utilize modern technology in the eld of transportation to help decrease congestion on roads so that proper measures can be pursued to facilitate lower travel times and an effective utilization of the transportation network. This project aims to develop a solution for real time detection of traffic congestion on a road. The solution captures images from the live feed of traffic cameras situated at various locations and runs a deep learning algorithm to detect whether an image shows traffic congestion. Using a set of these images and a persistence check, the application identifies the ...


Developing A Recurrent Neural Network With High Accuracy For Binary Sentiment Analysis, Kevin Cunanan Jan 2018

Developing A Recurrent Neural Network With High Accuracy For Binary Sentiment Analysis, Kevin Cunanan

CMC Senior Theses

Sentiment analysis has taken on various machine learning approaches in order to optimize accuracy, precision, and recall. However, Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) account for the context of a sentence by using previous predictions as additional input for future sentence predictions. Our approach focused on developing an LSTM RNN that could perform binary sentiment analysis for positively and negatively labeled sentences. In collaboration with Mariam Salloum, I developed a collection of programs to classify individual sentences as either positive or negative. This paper additionally looks into machine learning, neural networks, data preprocessing, implementation, and resulting comparisons.


Query Expansion Techniques For Enterprise Search, Eric M. Domke Dec 2017

Query Expansion Techniques For Enterprise Search, Eric M. Domke

Masters Theses

Although web search remains an active research area, interest in enterprise search has waned. This is despite the fact that the market for enterprise search applications is expected to triple within the next six years, and that knowledge workers spend an average of 1.6 to 2.5 hours each day searching for information. To improve search relevancy, and hence reduce this time, an enterprise- focused application must be able to handle the unique queries and constraints of the enterprise environment. The goal of this thesis research was to develop, implement, and study query expansion techniques that are most effective ...


Nonlinear Model-Based Control For Neuromuscular Electrical Stimulation, Ruzhou Yang Nov 2017

Nonlinear Model-Based Control For Neuromuscular Electrical Stimulation, Ruzhou Yang

LSU Doctoral Dissertations

Neuromuscular electrical stimulation (NMES) is a technology where skeletal muscles are externally stimulated by electrodes to help restore functionality to human limbs with motor neuron disorder. This dissertation is concerned with the model-based feedback control of the NMES quadriceps muscle group-knee joint dynamics. A class of nonlinear controllers is presented based on various levels of model structures and uncertainties. The two main control techniques used throughout this work are backstepping control and Lyapunov stability theory.

In the first control strategy, we design a model-based nonlinear control law for the system with the exactly known passive mechanical that ensures asymptotical tracking ...


Automated Quantification Of White Blood Cells In Light Microscopic Images Of Injured Skeletal Muscle, Yang Jiao Aug 2017

Automated Quantification Of White Blood Cells In Light Microscopic Images Of Injured Skeletal Muscle, Yang Jiao

UNLV Theses, Dissertations, Professional Papers, and Capstones

Muscle regeneration process tracking and analysis aim to monitor the injured muscle tissue section over time and analyze the muscle healing procedure. In this procedure, as one of the most diverse cell types observed, white blood cells (WBCs) exhibit dynamic cellular response and undergo multiple protein expression changes. The characteristics, amount, location, and distribution compose the action of cells which may change over time. Their actions and relationships over the whole healing procedure can be analyzed by processing the microscopic images taken at different time points after injury. The previous studies of muscle regeneration usually employ manual approach or basic ...


Models For Pedestrian Trajectory Prediction And Navigation In Dynamic Environments, Jeremy N. Kerfs May 2017

Models For Pedestrian Trajectory Prediction And Navigation In Dynamic Environments, Jeremy N. Kerfs

Master's Theses

Robots are no longer constrained to cages in factories and are increasingly taking on roles alongside humans. Before robots can accomplish their tasks in these dynamic environments, they must be able to navigate while avoiding collisions with pedestrians or other robots. Humans are able to move through crowds by anticipating the movements of other pedestrians and how their actions will influence others; developing a method for predicting pedestrian trajectories is a critical component of a robust robot navigation system. A current state-of-the-art approach for predicting pedestrian trajectories is Social-LSTM, which is a recurrent neural network that incorporates information about neighboring ...


Identification Of Critical Locations And Reduced Model State Estimation For Power System Analysis, Amamihe Onwuachumba Aug 2016

Identification Of Critical Locations And Reduced Model State Estimation For Power System Analysis, Amamihe Onwuachumba

Electronic Theses and Dissertations

In order to reduce the carbon footprint and the cost of electric energy, the owners of electric power utilities today are faced with the task of reducing the use of expensive and carbon intensive fossil fuels and significantly increasing the amount of energy from renewable sources in their grids while meeting an increase in electricity demand. To deal with increase in demand, electric utilities operate very close to their maximum capacities and this sometimes results in violating security limits. Therefore, the integration of intermittent renewable energy into the utility grids poses serious concerns that must be addressed to ensure grid ...


Driver Engagement In Secondary Tasks: Behavioral Analysis And Crash Risk Assessment, Mengqiu Ye Jan 2016

Driver Engagement In Secondary Tasks: Behavioral Analysis And Crash Risk Assessment, Mengqiu Ye

LSU Master's Theses

Distracted driving has long been acknowledged as one of the leading causes of death or injury in roadway crashes. The focus of past research has been mainly on the change in driving performance due to distracted driving. However, only a few studies attempted to predict the type of distraction based on driving performance measures. In addition, past studies have proven that driving performance is influenced by the drivers’ socioeconomic characteristics, while not many studies have attempted to quantify that influence. In essence, this study utilizes the rich SHRP 2 Naturalistic Driving Study (NDS) database to (a) develop a model for ...


Forecasting Obsolescence Risk And Product Lifecycle With Machine Learning, Connor Patrick Jennings Jan 2015

Forecasting Obsolescence Risk And Product Lifecycle With Machine Learning, Connor Patrick Jennings

Graduate Theses and Dissertations

Rapid changes in technology have led to an increasingly fast pace of product introductions. New components offering added functionality, improved performance and quality are routinely available to a growing number of industry sectors (e.g., electronics, automotive, and defense industries). For long-life systems such as planes, ships, nuclear power plants, and more, these rapid changes help sustain the useful life, but at the same time, present significant challenges associated with managing change. Obsolescence of components and/or subsystems can be technical, functional, related to style, etc., and occur in nearly any industry. Over the years, many approaches for forecasting obsolescence ...


Energy Management In Electric Vehicles: Development And Validation Of An Optimal Driving Strategy, Warren Santiago Vaz Jan 2015

Energy Management In Electric Vehicles: Development And Validation Of An Optimal Driving Strategy, Warren Santiago Vaz

Doctoral Dissertations

Electric vehicles (EVs) are a promising alternative energy mode of transportation for the future. However, due to the limited range and relatively long charging time, it is important to use the stored battery energy in the most optimal manner possible. Existing research has focused on improvements to the hardware or improvements to the energy management strategy (EMS). However, EV drivers may adopt a driving strategy that causes the EMS to operate the EV hardware in inefficient regimes just to fulfil the driver demand. The present study develops an optimal driving strategy to help an EV driver choose a driving strategy ...


A Model-Based Framework To Control The Crystal Size Distribution, Navid Ghadipasha Jan 2015

A Model-Based Framework To Control The Crystal Size Distribution, Navid Ghadipasha

LSU Master's Theses

Crystallization is an old unit operation in the industry which is widely used as a separation process due to its ability to produce highly valued chemical with high purity. Despite the long history of batch crystallization, industry still relies on rule of- thumb techniques for their crystallization processes. Thus, any method to improve the products characteristics such as size and morphology will be highly valued. Advances in robustness and accuracy of automated in situ sensors give the possibility to move towards an engineering based approach by implementing the real-time monitoring and control of the process. The research undertaken here investigates ...