Engineering Commons^™

Convolution And Autoencoders Applied To Nonlinear Differential Equations, Noah Borquaye

Electronic Theses and Dissertations

Autoencoders, a type of artificial neural network, have gained recognition by researchers in various fields, especially machine learning due to their vast applications in data representations from inputs. Recently researchers have explored the possibility to extend the application of autoencoders to solve nonlinear differential equations. Algorithms and methods employed in an autoencoder framework include sparse identification of nonlinear dynamics (SINDy), dynamic mode decomposition (DMD), Koopman operator theory and singular value decomposition (SVD). These approaches use matrix multiplication to represent linear transformation. However, machine learning algorithms often use convolution to represent linear transformations. In our work, we modify these approaches to …

Dual-Site Photoplethysmography Sensing For Noninvasive Continuous-Time Blood Pressure Monitoring Using Artificial Neural Network, Anas Mohmmad Rabab’Ah

Theses

Millions of people worldwide struggle from high blood pressure, often known as hypertension, and it is a major health concern that can lead to serious cardiovascular diseases, including heart attacks and many other consequences. Blood pressure monitoring that is reliable and accurate is crucial to the detection and management of hypertension. Although invasive techniques, such as arterial catheterization, are considered to be the most accurate means of evaluating blood pressure, they can be painful, time-consuming and carry a risk of complications.
This thesis presents the development of a real time non-invasive blood pressure monitoring system based on commercially available microcontroller …

A Long-Term Funds Predictor Based On Deep Learning, Shuiyi Kuang

Electronic Theses, Projects, and Dissertations

Numerous neural network models have been created to predict the rise or fall of stocks since deep learning has gained popularity, and many of them have performed quite well. However, since the share market is hugely influenced by various policy changes or unexpected news, it is challenging for investors to use such short-term predictions as a guide. In this paper, we try to find a suitable long-term predictor for the funds market by testing different kinds of neural network models, including the Long Short-Term Memory(LSTM) model with different layers, the Gated Recurrent Units(GRU) model with different layers, and the combination …

Deep Learning For Power Flow Estimation And High Impedance Fault Detection, Kun Yang

Electronic Theses and Dissertations

My thesis is divided into two parts.

The first part is: “Optimal Power Flow Estimation Using One-Dimensional Convolutional Neural Network [1]“. Optimal power flow (OPF) is an important research topic in power system operation and control decisions. Traditional OPF problems are solved through dynamic optimization with nonlinear programming techniques. For a large power system with large amounts of variables and constraints, the solving process would take a long time. This paper presents a new method to quickly estimate the OPF results using a one-dimensional convolutional neural network (1D-CNN). The OPF problem is treated as a high-dimensional mapping between the load …

Comparing The Performance Of Different Machine Learning Models In The Evaluation Of Solder Joint Fatigue Life Under Thermal Cycling, Jason Scott Ross

Dissertations and Theses

Predicting the reliability of board-level solder joints is a challenging process for the designer because the fatigue life of solder is influenced by a large variety of design parameters and many nonlinear, coupled phenomena. Machine learning has shown promise as a way of predicting the fatigue life of board-level solder joints. In the present work, the performance of various machine learning models to predict the fatigue life of board-level solder joints is discussed. Experimental data from many different solder joint thermal fatigue tests are used to train the different machine learning models. A web-based database for storing, sharing, and uploading …

Prediction Of Blast-Induced Ground Vibrations: A Comparison Between Empirical And Artificial-Neural-Network Approaches, Luis F. Velasquez

Theses and Dissertations--Mining Engineering

Ground vibrations are a critical factor in the rock blasting process. The instantaneous load application exerted by the gas pressure during the detonation process acts on the blasthole walls creating dynamic stresses in the adjacent rock. This triggers different sorts of stress waves, mainly divided into two categories: body and surface waves. The first comprises the P and the S waves, while the second comprises Rayleigh waves. These waves spread concentrically starting at the blast location and move along the ground surface and its interior, being attenuated as they reach further distances.

In most cases, and accepting the hypothesis that …

Estimating Air Pollution Levels Using Machine Learning, Srujay Rao Devaraneni

Master's Projects

Air pollution has emerged as a substantial concern, especially in developing countries worldwide. An important aspect of this issue is the presence of PM2.5. Air pollutants with a diameter of 2.5 or less micrometers are known as PM2.5. Due to their size, these particles are a serious health risk and can quickly infiltrate the lungs, leading to a variety of health problems. Due to growing concerns about air pollution, technology like automatic air quality measurement can offer beneficial assistance for both personal and business decisions. This research suggests an ensemble machine learning model that can efficiently replace the standard air …

Machine Learning Strategies For Potential Development In High-Entropy Driven Nickel-Based Superalloys, Marium Mostafiz Mou

MSU Graduate Theses

In this study, I developed Deep Learning interatomic potentials to model a multi-phase and multi-component system of Ni-based Superalloys. The system has up to three major phase constituents, namely Gamma, Gamma Prime, and Transition-metal rich Carbide. I utilized invariant scalar-based and/or equivariant, tensor-based neural network (NN) approach as implemented in DEEPMD, NEQUIP/ALLEGRO codes, respectively, and Moment Tensor Potential (MTP). For the training and validation sets, I employed the ab-initio molecular dynamics (AIMD) trajectory results and ground state DFT calculations, including the energy, force, and virial database from highly diverse compositions, temperatures, and pressures following a “High Entropy Strategy.” The Deep …

Neural Network Based Reactive Control Of Point Absorber Wave Energy Converters, Abdelmoamen Ali Nasser

Theses

The main objective of this work is to develop a neural-network-based Reactive Control (RC) system for wave energy converters. The ability to maximize the power output of WEC while maintaining operation constraints, which can be physical or thermal, is crucial to the development of deployable control strategies. Having a control method that is robust, which means it handles uncertainty and noise very well, is one of the main performance criteria in evaluating the method. Therefore, this work starts by deriving an averaged WEC model to be simulated in MATLAB/Simulink. Additionally, the concepts of resistive loading control and reactive control (approximate …

Artificial Neural Networks And Their Applications To Intelligent Fault Diagnosis Of Power Transmission Lines, Fatemeh Mohammadi Shakiba

Dissertations

Over the past thirty years, the idea of computing based on models inspired by human brains and biological neural networks emerged. Artificial neural networks play an important role in the field of machine learning and hold the key to the success of performing many intelligent tasks by machines. They are used in various applications such as pattern recognition, data classification, stock market prediction, aerospace, weather forecasting, control systems, intelligent automation, robotics, and healthcare. Their architectures generally consist of an input layer, multiple hidden layers, and one output layer. They can be implemented on software or hardware. Nowadays, various structures with …

One-Stage Blind Source Separation Via A Sparse Autoencoder Framework, Jason Anthony Dabin

Dissertations

Blind source separation (BSS) is the process of recovering individual source transmissions from a received mixture of co-channel signals without a priori knowledge of the channel mixing matrix or transmitted source signals. The received co-channel composite signal is considered to be captured across an antenna array or sensor network and is assumed to contain sparse transmissions, as users are active and inactive aperiodically over time. An unsupervised machine learning approach using an artificial feedforward neural network sparse autoencoder with one hidden layer is formulated for blindly recovering the channel matrix and source activity of co-channel transmissions. The BSS sparse autoencoder …

Recognizing Traffic Signaling Gestures Through Automotive Sensors., Benjamin James Bartlett

Theses and Dissertations

As technology advances with each new day, so do the applications and uses of the different modalities of technology, including transportation, particularly in ADAS vehicles. These systems allow the vehicle to avoid collisions, change lanes, adjust the vehicle’s speed, and more without the need of driver input. However, each sensor type has a weakness, and most advanced driver- assisted system (ADAS) vehicles rely heavily on sensors, such as RGB cameras, radars, and LiDAR sensors. These visual-based sensors may collect very noisy data in cloudy, raining, foggy, or other obscuring phenomena. Radar, on the other hand, does not rely on visual …

Predicting The Likelihood And Scale Of Wildfires In California Using Meteorological And Vegetation Data, Matthew Walters

Graduate Theses and Dissertations

Wildfires have devastating ecological, environmental, economical, and public health impacts through the deterioration of water and air quality, CO2 emissions, property damage, and lung illnesses. The early detection and prevention of wildfires allow for the minimization of these risks. The use of Artificial Intelligence (AI) in wildfire detection and prediction has been highly researched as a tool to assist firefighters in stopping wildfires in its early stages. The three common wildfire prediction categories include image and video detection, behavior prediction, and susceptibility prediction. Data such as climate, weather, vegetation, satellite images, and historical wildfire data is most commonly used. Many …

Forecasting Hypotension By Learning From Multivariate Mixed Responses.., Jodie Ritter

Electronic Theses and Dissertations

Blood Pressure is the main determinant of blood flow to organs. Hypotension is defined as a systolic blood pressure less than 90 mmHg or a diastolic blood pressure less than 50 mmHg. The severity and duration of hypotension is associated with low blood flow to organs often result in organ damage and a high mortality rate. Predicting hypotension prior to surgery and during the surgery can reduce the incidence and duration resulting in better patient outcomes. This thesis uses preoperative bloodwork and vital signs as well as perioperative vital signs in 5-minute increments as inputs to forecast hypotension. Hypotension can …

Design, Development And Benchmarking Of Machine Learning Algorithms In Biomedical Applications, Qi Sun

Theses and Dissertations--Computer Science

Machine learning algorithms are becoming the most effective methods for knowledge discovery from high dimensional datasets. Machine learning seeks to construct predictive models through the analysis of large-scale heterogeneous data. While machine learning has been widely used in many domains including computer vision, natural language processing, product recommendation, its application in biomedical science for clinical diagnosis and treatment is only emerging. However, the wealthy amount of data in the biomedical domain offers not only challenges but also opportunities for machine learning. In this dissertation, we focus on three biomedical applications from vastly different domains to understand the opportunities and challenges …

Evaluating Similarity Of Cross-Architecture Basic Blocks, Elijah L. Meyer

Browse all Theses and Dissertations

Vulnerabilities in source code can be compiled for multiple processor architectures and make their way into several different devices. Security researchers frequently have no way to obtain this source code to analyze for vulnerabilities. Therefore, the ability to effectively analyze binary code is essential. Similarity detection is one facet of binary code analysis. Because source code can be compiled for different architectures, the need can arise for detecting code similarity across architectures. This need is especially apparent when analyzing firmware from embedded computing environments such as Internet of Things devices, where the processor architecture is dependent on the product and …

Effects On Vehicle Ride Comfort Of An Adaptive Suspension System Using Neural Networks, Sylvia Yin Zhixian

Electronic Theses and Dissertations

Suspension systems in the auto industry have always been a topic of interest, as they relate to so many aspects of vehicles. Various types of suspension are commonly used now, such as passive suspensions, semi-active suspensions and active suspensions. However, the current technology mainly focuses on the change of damping ratio. The aim of this thesis is to consider both spring and damper properties for suspensions of an off-road vehicle. In order to do this, a 10-degree of freedom model was built using the EoM software in Julia. The output state space matrices from EoM were used as an input …

Crash Injury Severity Prediction With Artificial Neural Networks, Rima Abisaad

Dissertations

Motor vehicle crashes are one of our nation's most serious social, economic and health issues. They are the leading cause of death among children and young adults, killing approximately 1.35 million people each year. Providing a safe and efficient transportation system is the primary goal of transportation engineering and planning. To help reduce traffic fatalities and injuries on roadways, crash prediction models are used to forecast the injury severity of potential crashes and apply precautionary countermeasures accordingly. Most of these models are reactive as they use historical crash data to categorize crash-related factors. Recently, advancements have been made in developing …

Short-Term Memory And Olfactory Signal Processing, Lijun Zhang

McKelvey School of Engineering Theses & Dissertations

Modern neural recording methodologies, including multi-electrode and optical recordings, allow us to monitor the large population of neurons with high temporal resolution. Such recordings provide rich datasets that are expected to understand better how information about the external world is internally represented and how these representations are altered over time. Achieving this goal requires the development of novel pattern recognition methods and/or the application of existing statistical methods in novel ways to gain insights into basic neural computational principles. In this dissertation, I will take this data-driven approach to dissect the role of short-term memory in olfactory signal processing in …

Quantum State Estimation And Tracking For Superconducting Processors Using Machine Learning, Shiva Lotfallahzadeh Barzili

Computational and Data Sciences (PhD) Dissertations

Quantum technology has been rapidly growing; in particular, the experiments that have been performed with superconducting qubits and circuit QED have allowed us to explore the light-matter interaction at its most fundamental level. The study of coherent dynamics between two-level systems and resonator modes can provide insight into fundamental aspects of quantum physics, such as how the state of a system evolves while being continuously observed. To study such an evolving quantum system, experimenters need to verify the accuracy of state preparation and control since quantum systems are very fragile and sensitive to environmental disturbance. In this thesis, I look …

Nonlinear Intelligent Model Predictive Control Of Mobile Robots, Benjamin Albia

Theses and Dissertations

This thesis presents a framework for an artificial neural network (ANN) model-based nonlinear model predictive control of mobile ground robots. A computer vision analysis module was first developed to extract quantitative position information from onboard camera feed with respect to a prescribed path. Various strategies were developed to construct nonlinear physical plant models for model predictive control (MPC), including the physics-based model (PBM), the ANN trained on PBM-generated data, the ANN trained on test-captured data, and the ANN initially trained on PBM-generated data and then retrained with captured data. All the models predict physical states and positions of the robot …

Research On Power System State Estimation Problems – Series-Compensated Transmission Line Parameter And Load Model Parameter Estimation, Yiqi Zhang

Theses and Dissertations--Electrical and Computer Engineering

Transmission line and load model parameters are essential inputs to power system modeling and simulation, control, protection, operation, optimization, and planning. These parameters usually vary over time or under different operating conditions. Thus, reliable estimation methods are desired to ensure the accuracy of those parameters. This research focuses on estimation for transmission line parameters and the ZIP load model. The proposed estimation methods can use both online measurements and historical data of a specified duration. The parameters of long transmission lines with different series-compensation configurations are estimated using linear methods and optimal estimators with bad data detection capability. Additionally, Kalman …

Deep Learning For Compressive Sar Imaging With Train-Test Discrepancy, Morgan R. Mccamey

Browse all Theses and Dissertations

We consider the problem of compressive synthetic aperture radar (SAR) imaging with the goal of reconstructing SAR imagery in the presence of under sampled phase history. While this problem is typically considered in compressive sensing (CS) literature, we consider a variety of deep learning approaches where a deep neural network (DNN) is trained to form SAR imagery from limited data. At the cost of computationally intensive offline training, on-line test-time DNN-SAR has demonstrated orders of magnitude faster reconstruction than standard CS algorithms. A limitation of the DNN approach is that any change to the operating conditions necessitates a costly retraining …

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

Electrical & Computer Engineering Theses & Dissertations

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 can …

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 …

Human Facial Emotion Recognition System In A Real-Time, Mobile Setting, Claire Williamson

Honors Theses

The purpose of this project was to implement a human facial emotion recognition system in a real-time, mobile setting. There are many aspects of daily life that can be improved with a system like this, like security, technology and safety.

There were three main design requirements for this project. The first was to get an accuracy rate of 70%, which must remain consistent for people with various distinguishing facial features. The second goal was to have one execution of the system take no longer than half of a second to keep it as close to real time as possible. Lastly, …

Analysis Of Feature Extraction In Knee Cartilage Semantic Segmentation Convolutional Neural Networks, Logan Thorneloe

Undergraduate Honors Theses

Recent advances in deep learning and convolutional neural networks (CNNs) have shown promise for automatic segmentation in magnetic resonance images. However, because of the stochastic nature of the training process, it is difficult to interpret what information networks learn to represent. This study explores multiple difference metrics between networks to determine semantic relationships between knee cartilage tissues. It explores how differences in learned weights and output activations between networks can be used to express these relationships. These findings are further supported by training multi-class networks to segment multiple tissues to compare network accuracy across different tissue combinations. This study shows …

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 …

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 …

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 …