Engineering Commons^™

Statistics-Based Anomaly Detection And Correction Method For Amazon Customer Reviews, Ishani Chatterjee

Dissertations

People nowadays use the Internet to project their assessments, impressions, ideas, and observations about various subjects or products on numerous social networking sites. These sites serve as a great source of gathering information for data analytics, sentiment analysis, natural language processing, etc. The most critical challenge is interpreting this data and capturing the sentiment behind these expressions. Sentiment analysis is analyzing, processing, concluding, and inferencing subjective texts with the views. Companies use sentiment analysis to understand public opinions, perform market research, analyze brand reputation, recognize customer experiences, and study social media influence. According to the different needs for aspect granularity, …

On Resource-Efficiency And Performance Optimization In Big Data Computing And Networking Using Machine Learning, Wuji Liu

Dissertations

Due to the rapid transition from traditional experiment-based approaches to large-scale, computational intensive simulations, next-generation scientific applications typically involve complex numerical modeling and extreme-scale simulations. Such model-based simulations oftentimes generate colossal amounts of data, which must be transferred over high-performance network (HPN) infrastructures to remote sites and analyzed against experimental or observation data on high-performance computing (HPC) facility. Optimizing the performance of both data transfer in HPN and simulation-based model development on HPC is critical to enabling and accelerating knowledge discovery and scientific innovation. However, such processes generally involve an enormous set of attributes including domain-specific model parameters, network transport …

Exploiting Building Demand Flexibility Through Machine Learning For Building-To-Grid Integration, Hannah Charlene Fontenot

Dissertations - ALL

Demand flexibility – the ability to adjust a building's load profile across different timescales – is a key aspect of the ongoing effort to increase interconnectivity between buildings and the power grid. By harnessing their demand flexibility, buildings can provide significant benefits to the grid and bolster grid resilience and reliability. To facilitate the transition toward the "smart grid", new and intelligent control approaches are required that can seamlessly integrate building, occupant, and grid data and effectively control multiple building assets to provide grid services while maintaining occupants' required thermal comfort levels and reducing the building's overall energy consumption and …

Deep Learning For Automatic Microscopy Image Analysis, Shenghua He

McKelvey School of Engineering Theses & Dissertations

Microscopy imaging techniques allow for the creation of detailed images of cells (or nuclei) and have been widely employed for cell studies in biological research and disease diagnosis in clinic practices.Microscopy image analysis (MIA), with tasks of cell detection, cell classification, and cell counting, etc., can assist with the quantitative analysis of cells and provide useful information for a cellular-level understanding of biological activities and pathology. Manual MIA is tedious, time-consuming, prone to subject errors, and are not feasible for the high-throughput cell analysis process. Thus, automatic MIA methods can facilitate all kinds of biological studies and clinical tasks. Conventional …

Predictive Computational Materials Modeling With Machine Learning: Creating The Next Generation Of Atomistic Potential Using Neural Networks, Mashroor Shafat Nitol

Theses and Dissertations

Machine learning techniques using artificial neural networks (ANNs) have proven to be effective tools to rapidly mimic first principles calculations. These tools are capable of sub meV/atom accuracy while operating with linear scaling with respect to the system size. Here novel interatomic potentials are constructed based on the rapid artificial neural network (RANN) formalism. This approach generates precise force fields for various metals that have historically been difficult to describe at the atomic scale. These force fields can be utilized in molecular dynamics simulations to provide new physical insights. The RANN formalism, which is incorporated into a LAMMPS molecular dynamics …

Detecting Malware In Memory With Memory Object Relationships, Demarcus M. Thomas Sr.

Theses and Dissertations

Malware is a growing concern that not only affects large businesses but the basic consumer as well. As a result, there is a need to develop tools that can identify the malicious activities of malware authors. A useful technique to achieve this is memory forensics. Memory forensics is the study of volatile data and its structures in Random Access Memory (RAM). It can be utilized to pinpoint what actions have occurred on a computer system.

This dissertation utilizes memory forensics to extract relationships between objects and supervised machine learning as a novel method for identifying malicious processes in a system …

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 …

Trajectory Generation For A Multibody Robotic System: Modern Methods Based On Product Of Exponentials, Aryslan Malik

Doctoral Dissertations and Master's Theses

This work presents several trajectory generation algorithms for multibody robotic systems based on the Product of Exponentials (PoE) formulation, also known as screw theory. A PoE formulation is first developed to model the kinematics and dynamics of a multibody robotic manipulator (Sawyer Robot) with 7 revolute joints and an end-effector.

In the first method, an Inverse Kinematics (IK) algorithm based on the Newton-Raphson iterative method is applied to generate constrained joint-space trajectories corresponding to straight-line and curvilinear motions of the end effector in Cartesian space with finite jerk. The second approach describes Constant Screw Axis (CSA) trajectories which are generated …

Using Custom Ner Models To Extract Dod Specific Entities From Contracts, Kayla P. Haberstich

Theses and Dissertations

The Air Force Sustainment Center collected 3.7 million contracts onto the Air Force Research Laboratory’s high power computers. They are in the format of a .pdf or scanned document, making them unstructured data. The Data Analytics Resource Team extracted the documents into a textual format for use in further analysis. This thesis looks to extract four DOD specific entities (NSN, Part Number, CAGE Code, and Supplier Name) from the contracts using custom NER models. This newly extracted information will allow the Air Force to identify what parts are supplied by which vendors. This information along with historical CLIN pricing for …

A Machine Learning Method For The Prediction Of Melt Pool Geometries Created By Laser Powder Bed Fusion, Jonathan Ciaccio

University of New Orleans Theses and Dissertations

A machine learning model is created to predict melt pool geometries of Ti-6Al-4V alloy created by the laser powder bed fusion process. Data is collected through an extensive literature survey, using results from both experiments and CFD modeling. The model focuses on five key input parameters that influence melt pool geometries: laser power, scanning speed, spot size, powder density, and powder layer thickness. The two outputs of the model are melt pool width and melt pool depth. The model is trained and tested by using the k fold cross validation technique. Multiple regression models are then applied to find the …

Network Management, Optimization And Security With Machine Learning Applications In Wireless Networks, Mariam Nabil

Theses and Dissertations

Wireless communication networks are emerging fast with a lot of challenges and ambitions. Requirements that are expected to be delivered by modern wireless networks are complex, multi-dimensional, and sometimes contradicting. In this thesis, we investigate several types of emerging wireless networks and tackle some challenges of these various networks. We focus on three main challenges. Those are Resource Optimization, Network Management, and Cyber Security. We present multiple views of these three aspects and propose solutions to probable scenarios. The first challenge (Resource Optimization) is studied in Wireless Powered Communication Networks (WPCNs). WPCNs are considered a very promising approach towards sustainable, …

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 …

Machine-Learning-Based Approach To Decoding Physiological And Neural Signals, Elnaz Lashgari

Computational and Data Sciences (PhD) Dissertations

In recent years, machine learning algorithms have been developing rapidly, becoming increasingly powerful tools in decoding physiological and neural signals. The aim of this dissertation is to develop computational tools, and especially machine learning techniques, to identify the most effective methods for feature extraction and classification of these signals. This is particularly challenging due to the highly non-linear, non-stationery, and artifact- and noise-prone nature of these signals.

Among basic human-control tasks, reaching and grasping are ubiquitous in everyday life. I investigated different linear and non-linear dimensionality reduction techniques for feature extraction and classification of electromyography (EMG) during a reach-grasp-lift task. …

Deepfakes Generated By Generative Adversarial Networks, Olympia A. Paul

Honors College Theses

Deep learning is a type of Artificial Intelligence (AI) that mimics the workings of the human brain in processing data such as speech recognition, visual object recognition, object detection, language translation, and making decisions. A Generative adversarial network (GAN) is a special type of deep learning, designed by Goodfellow et al. (2014), which is what we call convolution neural networks (CNN). How a GAN works is that when given a training set, they can generate new data with the same information as the training set, and this is often what we refer to as deep fakes. CNN takes an input …

Benchmarking Small-Dataset Structure-Activity-Relationship Models For Prediction Of Wnt Signaling Inhibition, Mahtab Kokabi

Masters Theses

Quantitative structure-activity relationship (QSAR) models based on machine learning algorithms are powerful tools to expedite drug discovery processes and therapeutics development. Given the cost in acquiring large-sized training datasets, it is useful to examine if QSAR analysis can reasonably predict drug activity with only a small-sized dataset (size < 100) and benchmark these small-dataset QSAR models in application-specific studies. To this end, here we present a systematic benchmarking study on small-dataset QSAR models built for prediction of effective Wnt signaling inhibitors, which are essential to therapeutics development in prevalent human diseases (e.g., cancer). Specifically, we examined a total of 72 two-dimensional (2D) QSAR models based on 4 best-performing algorithms, 6 commonly used molecular fingerprints, and 3 typical fingerprint lengths. We trained these models using a training dataset (56 compounds), benchmarked their performance on 4 figures-of-merit (FOMs), and examined their prediction accuracy using an external validation dataset (14 compounds). Our data show that the model performance is maximized when: 1) molecular fingerprints are selected to provide sufficient, unique, and not overly detailed representations of the chemical structures of drug compounds; 2) algorithms are selected to reduce the number of false predictions due to class imbalance in the dataset; and 3) models are selected to reach balanced performance on all 4 FOMs. These results may provide general guidelines in developing high-performance small-dataset QSAR models for drug activity prediction.

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 …

Searching Extreme Mechanical Properties Using Active Machine Learning And Density Functional Theory, Joshua Ojih

Theses and Dissertations

Materials with extreme mechanical properties leads to future technological advancements. However, discovery of these materials is non-trivial. The use of machine learning (ML) techniques and density functional theory (DFT) calculation for structure properties prediction has helped to the discovery of novel materials over the past decade. ML techniques are highly efficient, but less accurate and density functional theory (DFT) calculation is highly accurate, but less efficient. We proposed a technique to combine ML methods and DFT calculations in discovering new materials with desired properties. This combination improves the search for materials because it combines the efficiency of ML and the …

Machine Learning Based Prediction Of Reinforced Concrete Members’ Shear Friction Capacity, Farah Mohamed

Electronic Theses and Dissertations

Shear friction theory describes the mechanisms by which shear forces are transferred across concrete-to-concrete interfaces. Shear transfer across a plane involves a complex interaction of several phenomena, such as concrete surface condition and cohesion, concrete strength, and steel reinforcement strength and reinforcement ratio. Existing empirical equations for shear friction have been developed using limited sample data sets;thus, their accuracy is limited to the range covered by the data. In order to overcome this limitation, the present thesis proposes two machine learning models drawn from an extensive database to predict the shear friction capacity in reinforced concrete (RC) with a high …

Predicting Pavement Structural Condition Using Machine Learning Methods, Nazmus Sakib Ahmed

Theses and Dissertations

State departments of transportation recognize the need to incorporate pavement structural condition in their pavement performance models and/or decision processes used to select candidate projects for preservation, rehabilitation, or reconstruction at the network level. However, pavement structural condition data are costly to obtain. To this end, this paper develops and evaluates the effectiveness of two machine learning methods, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), for predicting a flexible pavement’s structural condition. The aim is to be able to predict whether a pavement section’s structural condition is poor or not based on Annual Average Daily Traffic (AADT), truck percentage, …

Mixed-Reality Visualization Environments To Facilitate Ultrasound-Guided Vascular Access, Leah Groves

Electronic Thesis and Dissertation Repository

Ultrasound-guided needle insertions at the site of the internal jugular vein (IJV) are routinely performed to access the central venous system. Ultrasound-guided insertions maintain high rates of carotid artery puncture, as clinicians rely on 2D information to perform a 3D procedure. The limitations of 2D ultrasound-guidance motivated the research question: “Do 3D ultrasound-based environments improve IJV needle insertion accuracy”. We addressed this by developing advanced surgical navigation systems based on tracked surgical tools and ultrasound with various visualizations. The point-to-line ultrasound calibration enables the use of tracked ultrasound. We automated the fiducial localization required for this calibration method such that …

Short-Term Crash Risk Prediction Considering Proactive, Reactive, And Driver Behavior Factors, Sina Darban Khales

Dissertations

Providing a safe and efficient transportation system is the primary goal of transportation engineering and planning. Highway crashes are among the most significant challenges to achieving this goal. They result in significant societal toll reflected in numerous fatalities, personal injuries, property damage, and traffic congestion. To that end, much attention has been given to predictive models of crash occurrence and severity. Most of these models are reactive: they use the data about crashes that have occurred in the past to identify the significant crash factors, crash hot-spots and crash-prone roadway locations, analyze and select the most effective countermeasures for reducing …

Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue

Dissertations

The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …

Towards Adversarial Robustness With 01 Lossmodels, And Novel Convolutional Neural Netsystems For Ultrasound Images, Meiyan Xie

Dissertations

This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images.

In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here suggests that 01 loss may be more resilient to adversarial attacks than the hinge loss and further work is required.

In the second part, this dissertation proposes sign activation network with a novel gradient-free stochastic coordinate descent algorithm and its ensembling model. The study here finds that the ensembling model gives a high minimum distortion (as measured by …

Data-Driven Learning For Robot Physical Intelligence, Leidi Zhao

Dissertations

The physical intelligence, which emphasizes physical capabilities such as dexterous manipulation and dynamic mobility, is essential for robots to physically coexist with humans. Much research on robot physical intelligence has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. In this dissertation, a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation is proposed. This method tackles …

Data And Sensor Fusion Using Fmg, Semg And Imu Sensors For Upper Limb Prosthesis Control, Jason S. Gharibo

Electronic Thesis and Dissertation Repository

Whether someone is born with a missing limb or an amputation occurs later in life, living with this disability can be extremely challenging. The robotic prosthetic devices available today are capable of giving users more functionality, but the methods available to control these prostheses restrict their use to simple actions, and are part of the reason why users often reject prosthetic technologies. Using multiple myography modalities has been a promising approach to address these control limitations; however, only two myography modalities have been rigorously tested so far, and while the results have shown improvements, they have not been robust enough …

Scatter Estimation And Correction For Experimental And Simulated Data In Multi-Slice Computed Tomography Using Machine Learning And Minimum Least Squares Methods, Cornelia Wang

McKelvey School of Engineering Theses & Dissertations

Current research aims to reduce the stopping power ratio prediction error in the inputs to the proton therapy planning process to less than 1%, which allows for improved radiation therapy planning. Our present study on reducing SPR error neglects the effect of scattering, which can increase SPR error by as much as 1-1.5%. The idea is that for each source-to-detector pair, 24 mm collimation data is close to 3 mm collimation data but with increased signal due to scattering. The goal is to estimate 3 mm collimation data from 24 mm collimation data. Pairs of sinograms, both experimental data and …

Machine Learning For Analog/Mixed-Signal Integrated Circuit Design Automation, Weidong Cao

McKelvey School of Engineering Theses & Dissertations

Analog/mixed-signal (AMS) integrated circuits (ICs) play an essential role in electronic systems by processing analog signals and performing data conversion to bridge the analog physical world and our digital information world.Their ubiquitousness powers diverse applications ranging from smart devices and autonomous cars to crucial infrastructures. Despite such critical importance, conventional design strategies of AMS circuits still follow an expensive and time-consuming manual process and are unable to meet the exponentially-growing productivity demands from industry and satisfy the rapidly-changing design specifications from many emerging applications. Design automation of AMS IC is thus the key to tackling these challenges and has been …

Generative Learning In Smart Grid, Samer M. El Kababji

Electronic Thesis and Dissertation Repository

If a smart grid is to be described in one word, that word would be ’connectivity’. While electricity production and consumption still depend on a limited number of physical connections, exchanging data is growing enormously. Customers, utilities, sensors, and markets are all different sources of data that are exchanged in a ubiquitous digital setup. To deal with data complexity, many researchers recently focused on machine learning (ML) applications in smart grids. Much of the success in ML is attributed to discriminative learning where models define boundaries to categorize data. Generative learning, however, reveals how data is generated by learning the …

Development Of A Highly Sensitive Pressure Sensing System With Custom-Built Software For Continuous Physiological Measurements, Masoud Panahi

Masters Theses

In this work, a pressure sensing system was designed and fabricated by developing a highly sensitive cone-structured pressure sensor with a custom-built software for physiological monitoring applications. A novel highly sensitive cone structured porous polydimethylsiloxane (PDMS) based pressure sensor capable of detecting very low-pressure ranges was developed for respiration monitoring. The pressure sensor was fabricated using a master mold, a hybrid-structured dielectric layer, and fabric-based electrodes. The master mold with inverted cone structures was created using a rapid and precise three-dimensional (3D) printing technique. The dielectric layer, with pores and cone structures, was prepared by annealing a mixture of PDMS, …

Machine Learning Models For Lodi Indices., Lucas A. Bruns

Electronic Theses and Dissertations

Two indices published monthly by the Logistics and Distribution Institute (LoDI) predict changes in logistics and distribution activity levels nationally and regionally and are useful for organizations when planning projects and expenses. This research validates the current linear regression model, updates the index conversion method, and introduces machine learning models.

New source data are introduced to the models to validate the current linear regression model and a comparative analysis verifies that the current source data are robust. A rolling average is used for index conversion in place of a fixed reference month to reflect recent changes in employment levels.

Three …