Engineering Commons^™

Non-Destructive Evaluation Of White Striping And Microbial Spoilage Of Broiler Breast Meat Using Structured-Illumination Reflectance Imaging, Ebenezer O. Olaniyi

Theses and Dissertations

Manual inspection is a prevailing practice for quality assessment of poultry meat, but it is labor-intensive, tedious, and subjective. This thesis aims to assess the efficacy of an emerging structured illumination reflectance imaging (SIRI) technique with machine learning approaches for assessing WS and microbial spoilage in broiler breast meat. Broiler breast meat samples were imaged by an in house-assembled SIRI platform under sinusoidal illumination. In first experiment, handcrafted texture features were extracted from direct component (DC, corresponding to conventional uniform illumination) and amplitude component (AC, unique to the use of sinusoidal illumination) images retrieved from raw SIRI pattern images build …

Utilizing Deep Learning Methods In The Identification And Synthesis Of Gene Regulations, Jiandong Wang

Theses and Dissertations

Gene expression is the fundamental differentiation and development process of life. Although all cells in an organism have essentially the same DNA, cell types and activities vary due to changes in gene expression. Gene expression can be influenced by many gene regulations. RNA editing contributes to the variety of RNA and proteins by allowing single nucleotide substitution. Reverse transcription can alter the expression status of genes by inducing genetic diversity and polymorphism via novel insertions, deletions, and recombination events. Gene regulation is critical to normal development because it enables cells to respond rapidly to environmental changes. However, identifying gene regulations …

Machine Learning Models To Automate Radiotherapy Structure Name Standardization, Priyankar Bose

Theses and Dissertations

Structure name standardization is a critical problem in Radiotherapy planning systems to correctly identify the various Organs-at-Risk, Planning Target Volumes and `Other' organs for monitoring present and future medications. Physicians often label anatomical structure sets in Digital Imaging and Communications in Medicine (DICOM) images with nonstandard random names. Hence, the standardization of these names for the Organs at Risk (OARs), Planning Target Volumes (PTVs), and `Other' organs is a vital problem. Prior works considered traditional machine learning approaches on structure sets with moderate success. We compare both traditional methods and deep neural network-based approaches on the multimodal vision-language prostate cancer …

A Machine Learning Approach For Identification Of Low-Head Dams, Salvador Augusto Vinay Mollinedo

Theses and Dissertations

Identifying Low-head dams (LHD) and creating an inventory become a priority as fatalities continue to occur at these structures. Because obstruction inventories do not specifically identify LHDs, and they are not assigned a hazard classification, there is not an official inventory of LHD. However, there is a multi-agency taskforce that is creating an inventory of LHD. All efforts have been performed by manually identifying LHD on Google Earth Pro (GE Pro). The purpose of this paper is to assess whether a machine learning approach can accelerate the national inventory. We used a machine learning approach to implement a high-resolution remote …

Principles For Using Remote Data Collection Devices And Deep Learning In Evaluating Social Impact Indicators Of Engineered Products For Global Development, Bryan J. Stringham

Theses and Dissertations

Evaluating the social impacts of engineered products, or effects products have on the daily lives of individuals, is critical to ensuring that products are having positive impacts while avoiding negative impacts and to learning how to improve product designs for a more positive social impact. One approach to quantifying a product's social impact is to use social impact indicators that combine user data in a meaningful way to give insight into the current social condition of an individual or population. However, determining social impact indicators relative to engineered products and individuals in developing countries can be difficult when there is …

Use Of Machine Learning And Natural Language Processing To Enhance Traffic Safety Analysis, Md Abu Sayed

Theses and Dissertations

Despite significant advances in vehicle technologies, safety data collection and analysis, and engineering advancements, tens of thousands of Americans die every year in motor vehicle crashes. Alarmingly, the trend of fatal and serious injury crashes appears to be heading in the wrong direction. In 2021, the actual rate of fatalities exceeded the predicted rate. This worrisome trend prompts and necessitates the development of advanced and holistic approaches to determining the causes of a crash (particularly fatal and major injuries). These approaches range from analyzing problems from multiple perspectives, utilizing available data sources, and employing the most suitable tools and technologies …

Image Restoration Under Adverse Illumination For Various Applications, Lan Fu

Theses and Dissertations

Many images are captured in sub-optimal environment, resulting in various kinds of degradations, such as noise, blur, and shadow. Adverse illumination is one of the most important factors resulting in image degradation with color and illumination distortion or even unidentified image content. Degradation caused by the adverse illumination makes the images suffer from worse visual quality, which might also lead to negative effects on high-level perception tasks, e.g., object detection.

Image restoration under adverse illumination is an effective way to remove such kind of degradations to obtain visual pleasing images. Existing state-of-the-art deep neural networks (DNNs) based image restoration …

Identifying And Discovering Curve Pattern Designs From Fragments Of Pottery, Jun Zhou

Theses and Dissertations

The surface of many cultural heritage objects, such as pottery sherds found in the Southeastern Woodlands, were embellished with curve patterns. The original full designs of these patterns reflect rich historical and cultural information. However, in practice, most objects are fragmentary, making the complete underlying designs unknowable at the scale of the sherd fragment. The challenge to reconstruct and study complete designs is stymied because 1) most pottery sherds contain only a small portion of the underlying full design, 2) curve patterns detected on a sherd are usually incomplete and noisy, and 3) in the case of a stamping application, …

Automated Pre-Play Analysis Of American Football Formations Using Deep Learning, Jacob Deloy Newman

Theses and Dissertations

Annotation and analysis of sports videos is a time consuming task that, once automated, will provide benefits to coaches, players, and spectators. American football, as the most watched sport in the United States, could especially benefit from this automation. Manual annotation and analysis of recorded video of American football games is an inefficient and tedious process. Currently, most college football programs focus on annotating offensive formation. As a first step to further research for this unique application, we use computer vision and deep learning to analyze an overhead image of a football play immediately before the play begins. This analysis …

Machine Learning Based Surrogate Model For Hurricane Storm Surge Forecasting In The Laguna Madre, Cesar E. Davila Hernandez

Theses and Dissertations

Texas coastal communities are at constant risk of hurricane impacts every storm season. It is especially important to model and predict storm surge variations during hurricane and storm events. Traditionally, hurricane storm surge predictions have been the result of numerical hydrodynamics based simulations. This type of simulations often requires high amounts of computational resources and complex ocean modelling efforts. Recently, machine learning techniques are being explored and are gaining popularity in hydrologic and ocean engineering modelling fields based on their performance to model nonlinear relationships and low computational requirements for prediction. Advances in machine learning and artificial intelligence (A.I.) demand …

Forecasting Salinity In The Laguna Madre Using Deep Learning, Martin J. Flores Jr.

Theses and Dissertations

Salinity is an important metric in the Laguna Madre for establishing the long term health of the local ecological population. By utilizing Deep Learning (DL) techniques, the predicted and forecasted salinity in the Laguna Madre is generated from data provided by the Moderate Resolution Imaging Spectroradiometer (MODIS)-Aqua satellite.

Currently, only one other DL model has been used to forecast Sea Surface Salinity (SSS), being a Recurrent Neural Network (RNN). However, the RNN model requires the prediction of a full area of salinity to function.

As such, several model architectures were tested, with the best one, being a Multi-input MPNN, utilized …

Deep Learning Approach To Multi-Phenomenological Nuclear Fuel Cycle Signals For Nonproliferation Applications, Preston J. Dicks

Theses and Dissertations

In order to reduce the time required for data analysis and decision-making relevant to nuclear proliferation detection, Artificial Intelligence (AI) techniques are applied to multi-phenomenological signals emitted from nuclear fuel cycle facilities to identify non-human readable characteristic signatures of operations for use in detecting proliferation activities. Seismic and magnetic emanations were collected in the vicinity of the High Flux Isotope Reactor (HFIR) and the McClellan Nuclear Research Center (MNRC). A novel bi-phenomenology DL network is designed to test the viability of transfer learning between nuclear reactor facilities. It is found that the network produces an 84.1% accuracy (99.4% without transient …

Extractive Text Summarization On Single Documents Using Deep Learning, Shehab Mostafa Abdel-Salam Mohamed

Theses and Dissertations

The task of summarization can be categorized into two methods, extractive and abstractive summarization. Extractive approach selects highly meaningful sentences to form a summary while the abstractive approach interprets the original document and generates the summary in its own words. The task of generating a summary, whether extractive or abstractive, has been studied with different approaches such as statistical-based, graph-based, and deep-learning based approaches. Deep learning has achieved promising performance in comparison with the classical approaches and with the evolution of neural networks such as the attention network or commonly known as the Transformer architecture, there are potential areas for …

Using A Systemic Skills Model To Build An Effective 21st Century Workforce: Factors That Impact The Ability To Navigate Complex Systems, Morteza Nagahi

Theses and Dissertations

The growth of technology and the proliferation of information made modern complex systems more fragile and vulnerable. As a result, competitive advantage is no longer achieved exclusively through strategic planning but by developing an influential cadre of technical people who can efficiently manage and navigate modern complex systems. The dissertation aims to provide educators, practitioners, and organizations with a model that helps to measure individuals’ systems thinking skills, complex problem solving, personality traits, and the impacting demographic factors such as managerial and work experience, current occupation type, organizational ownership structure, and education level. The intent is to study how these …

Uncertainty-Aware Deep Learning For Prediction Of Remaining Useful Life Of Mechanical Systems, Samuel J. Cornelius

Theses and Dissertations

Remaining useful life (RUL) prediction is a problem that researchers in the prognostics and health management (PHM) community have been studying for decades. Both physics-based and data-driven methods have been investigated, and in recent years, deep learning has gained significant attention. When sufficiently large and diverse datasets are available, deep neural networks can achieve state-of-the-art performance in RUL prediction for a variety of systems. However, for end users to trust the results of these models, especially as they are integrated into safety-critical systems, RUL prediction uncertainty must be captured. This work explores an approach for estimating both epistemic and heteroscedastic …

A Data-Driven Approach For The Investigation Of Microstructural Effects On The Effective Piezoelectric Responses Of Additively Manufactured Triply Periodic Bi-Continuous Piezocomposite, Wenhua Yang

Theses and Dissertations

A two-scale model consisting of ceramic grain scale and composite scale are developed to systematically evaluate the effects of microstructures (e.g., residual pores, grain size, texture) and geometry on the piezoelectric responses of the polarized triply periodic bi-continuous (TPC) piezocomposites. These TPC piezocomposites were fabricated by a recently developed additive manufacturing (AM) process named suspension-enclosing projection-stereolithography (SEPS) under different process conditions. In the model, the Fourier spectral iterative perturbation method (FSIPM) and the finite element method will be adopted for the calculation at the grain and composite scale, respectively. On the grain scale, a DL approach based on stacked generative …

Unsupervised Learning For Anomaly Detection In Remote Sensing Imagery, Husam A. Alfergani

Theses and Dissertations

Landfill fire is a potential hazard of waste mismanagement, and could occur both on and below the surface of active and closed sites. Timely identification of temperature anomalies is critical in monitoring and detecting landfill fires, to issue warnings that can help extinguish fires at early stages. The overarching objective of this research is to demonstrate the applicability and advantages of remote sensing data, coupled with machine learning techniques, to identify landfill thermal states that can lead to fire, in the absence of onsite observations. This dissertation proposed unsupervised learning techniques, notably variational auto-encoders (VAEs), to identify temperature anomalies from …

Deep Learning For Weather Clustering And Forecasting, Nathaniel R. Beveridge

Theses and Dissertations

Clustering weather data is a valuable endeavor in multiple respects. The results can be used in various ways within a larger weather prediction framework or could simply serve as an analytical tool for characterizing climatic differences of a particular region of interest. This research proposes a methodology for clustering geographic locations based on the similarity in shape of their temperature time series over a long time horizon of approximately 11 months. To this end an emerging and powerful class of clustering techniques that leverages deep learning, called deep representation clustering (DRC), are utilized. Moreover, a time series specific DRC algorithm …

Wound Image Classification Using Deep Convolutional Neural Networks, Behrouz Rostami

Theses and Dissertations

Artificial Intelligence (AI) includes subfields like Machine Learning (ML) and DeepLearning (DL) and discusses intelligent systems that mimic human behaviors. ML has been used in a wide range of fields. Particularly in the healthcare domain, medical images often need to be carefully processed via such operations as classification and segmentation. Unlike traditional ML methods, DL algorithms are based on deep neural networks that are trained on a large amount of labeled data to extract features without human intervention. DL algorithms have become popular and powerful in classifying and segmenting medical images in recent years. In this thesis, we shall study …

Surface Defect Detection In Aircraft Skin & Visual Navigation Based On Forced Feature Selection Through Segmentation, Tyler B. Hussey

Theses and Dissertations

Visual inspection of aircraft skin for surface defects is an area of maintenance that is particularly intensive for time and manpower. One novel way to combat this problem is through the use of computer vision and the advent of Artificial Neural Networks (ANN), or more specifically, semantic segmentation via Convolutional Neural Networks (CNN). The research in the paper explores the use of semantic segmentation of aerial imagery as a way to force feature selection onto key areas of an image that might be more likely to correspond under seasonal variations. Utilizing feature selection and matching on the masked aerial image …

Deep Learning Assisted Intelligent Visual And Vehicle Tracking Systems, Liang Xu

Theses and Dissertations

Sensor fusion and tracking is the ability to bring together measurements from multiple sensors of the current and past time to estimate the current state of a system. The resulting state estimate is more accurate compared with the direct sensor measurement because it balances between the state prediction based on the assumed motion model and the noisy sensor measurement. Systems can then use the information provided by the sensor fusion and tracking process to support more-intelligent actions and achieve autonomy in a system like an autonomous vehicle. In the past, widely used sensor data are structured, which can be directly …

Traffic Time Headway Prediction And Analysis: A Deep Learning Approach, Saumik Sakib Bin Masud

Theses and Dissertations

In the modern world of Intelligent Transportation System (ITS), time headway is a key traffic flow parameter affecting ITS operations and planning. Defined as “the time difference between any two successive vehicles when they cross a given point”, time headway is used in various traffic and transportation engineering research domains, such as capacity analysis, safety studies, car-following, and lane-changing behavior modeling, and level of service evaluation describing stochastic features of traffic flow. Advanced travel and headway information can also help road users avoid traffic congestion through dynamic route planning, for instance. Hence, it is crucial to accurately model headway distribution …

Deep Learning-Based, Passive Fault Tolerant Control Facilitated By A Taxonomy Of Cyber-Attack Effects, Dean C. Wardell

Theses and Dissertations

In the interest of improving the resilience of cyber-physical control systems to better operate in the presence of various cyber-attacks and/or faults, this dissertation presents a novel controller design based on deep-learning networks. This research lays out a controller design that does not rely on fault or cyber-attack detection. Being passive, the controller’s routine operating process is to take in data from the various components of the physical system, holistically assess the state of the physical system using deep-learning networks and decide the subsequent round of commands from the controller. This use of deep-learning methods in passive fault tolerant control …

Joint 1d And 2d Neural Networks For Automatic Modulation Recognition, Luis M. Rosario Morel

Theses and Dissertations

The digital communication and radar community has recently manifested more interest in using data-driven approaches for tasks such as modulation recognition, channel estimation and distortion correction. In this research we seek to apply an object detector for parameter estimation to perform waveform separation in the time and frequency domain prior to classification. This enables the full automation of detecting and classifying simultaneously occurring waveforms. We leverage a lD ResNet implemented by O'Shea et al. in [1] and the YOLO v3 object detector designed by Redmon et al. in [2]. We conducted an in depth study of the performance of these …

Graphical Convolution Network Based Semi-Supervised Methods For Detecting Pmu Data Manipulation Attacks, Wenyu Wang

Theses and Dissertations

With the integration of information and communications technologies (ICTs) into the power grid, electricity infrastructures are gradually transformed towards smart grid and power systems become more open to and accessible from outside networks. With ubiquitous sensors, computers and communication networks, modern power systems have become complicated cyber-physical systems. The cyber security issues and the impact of potential attacks on the smart grid have become an important issue. Among these attacks, false data injection attack (FDIA) becomes a growing concern because of its varied types and impacts. Several detection algorithms have been developed in the last few years, which were model-based, …

Medical Image Segmentation With Deep Learning, Chuanbo Wang

Theses and Dissertations

Medical imaging is the technique and process of creating visual representations of the body of a patient for clinical analysis and medical intervention. Healthcare professionals rely heavily on medical images and image documentation for proper diagnosis and treatment. However, manual interpretation and analysis of medical images is time-consuming, and inaccurate when the interpreter is not well-trained. Fully automatic segmentation of the region of interest from medical images have been researched for years to enhance the efficiency and accuracy of understanding such images. With the advance of deep learning, various neural network models have gained great success in semantic segmentation and …

Object Detection With Deep Learning To Accelerate Pose Estimation For Automated Aerial Refueling, Andrew T. Lee

Theses and Dissertations

Remotely piloted aircraft (RPAs) cannot currently refuel during flight because the latency between the pilot and the aircraft is too great to safely perform aerial refueling maneuvers. However, an AAR system removes this limitation by allowing the tanker to directly control the RP A. The tanker quickly finding the relative position and orientation (pose) of the approaching aircraft is the first step to create an AAR system. Previous work at AFIT demonstrates that stereo camera systems provide robust pose estimation capability. This thesis first extends that work by examining the effects of the cameras' resolution on the quality of pose …

Improving Aeromagnetic Calibration Using Artificial Neural Networks, Mitchell C. Hezel

Theses and Dissertations

The Global Positioning System (GPS) has proven itself to be the single most accurate positioning system available, and no navigation suite is found without a GPS receiver. Even basic GPS receivers found in most smartphones can easily provide high quality positioning information at any time. Even with its superb performance, GPS is prone to jamming and spoofing, and many platforms requiring accurate positioning information are in dire need of other navigation solutions to compensate in the event of an outage, be the cause hostile or natural. Indeed, there has been a large push to achieve an alternative navigation capability which …

Improved Ground-Based Monocular Visual Odometry Estimation Using Inertially-Aided Convolutional Neural Networks, Josiah D. Watson

Theses and Dissertations

While Convolutional Neural Networks (CNNs) can estimate frame-to-frame (F2F) motion even with monocular images, additional inputs can improve Visual Odometry (VO) predictions. In this thesis, a FlowNetS-based [1] CNN architecture estimates VO using sequential images from the KITTI Odometry dataset [2]. For each of three output types (full six degrees of freedom (6-DoF), Cartesian translation, and transitional scale), a baseline network with only image pair input is compared with a nearly identical architecture that is also given an additional rotation estimate such as from an Inertial Navigation System (INS). The inertially-aided networks show an order of magnitude improvement over the …

Scatter Reduction By Exploiting Behaviour Of Convolutional Neural Networks In Frequency Domain, Carlos Ivan Jerez Gonzalez

Theses and Dissertations

In X-ray imaging, scattered radiation can produce a number of artifacts that greatly

undermine the image quality. There are hardware solutions, such as anti-scatter grids.

However, they are costly. A software-based solution is a better option because it is

cheaper and can achieve a higher scatter reduction. Most of the current software-based

approaches are model-based. The main issues with them are the lack of flexibility, expressivity, and the requirement of a model. In consideration of this, we decided to apply

Convolutional Neural Networks (CNNs), since they do not have any of the previously

mentioned issues.

In our approach we split …