Engineering Commons^™

A Hybrid Neural Network For Stock Price Direction Forecasting, Daniel Devine

Dissertations

The volatility of stock markets makes them notoriously difficult to predict and is the reason that many investors sell out at the wrong time. Contrary to the efficient market hypothesis (EMH) and the random walk theory, contribution to the study of machine learning models for stock price forecasting has shown evidence of stock markets predictability with varying degrees of success. Contemporary approaches have sought to use a hybrid of convolutional neural network (CNN) for its feature extraction capabilities and long short-term memory (LSTM) neural network for its time series prediction. This comparative study aims to determine the predictability of stock …

Identifying Significant Features For Player Evaluation In Nfl Comparing Anns And Traditional Models, Ronan Walsh

Dissertations

The evaluation of player performance in sports is popular and important in modern sports, enabling teams to use real data in the construction of their rosters. This dissertation proposes to apply machine learning algorithms to predicting the player evaluations from a leading NFL analytics company who use a combination of statistics and expert evaluation. In addition, it will investigate what features are significant in the evaluation of a position. Data for the dissertation is obtained from multiple online sources - Pro Football Reference and Pro Football Focus (the the NFL analytics company). These data sets are combined and analysed before …

Identifying Roles Of Software Developers From Their Answers On Stack Overflow, Dean Power

Dissertations

Stack Overflow is the world’s largest community of software developers. Users ask and answer questions on various tagged topics of software development. The set of questions a site user answers is representative of their knowledge base, or “wheelhouse”. It is proposed that clustering users by their wheelhouse yields communities of similar software developers by skill-set. These communities represent the different roles within software development and could be used as the basis to define roles at any point in time in an ever-evolving landscape of software development. A network graph of site users, linked if they answered questions on the same …

Can Generative Adversarial Networks Help Us Fight Financial Fraud?, Sean Mciver

Dissertations

Transactional fraud datasets exhibit extreme class imbalance. Learners cannot make accurate generalizations without sufficient data. Researchers can account for imbalance at the data level, algorithmic level or both. This paper focuses on techniques at the data level. We evaluate the evidence of the optimal technique and potential enhancements. Global fraud losses totalled more than 80 % of the UK’s GDP in 2019. The improvement of preprocessing is inherently valuable in fighting these losses. Synthetic minority oversampling technique (SMOTE) and extensions of SMOTE are currently the most common preprocessing strategies. SMOTE oversamples the minority classes by randomly generating a point between …

Performance Comparison Between A Distributed Particle Swarm Algorithm And A Centralised Algorithm, Ciarán O’Loughlin

Dissertations

Particle Swarm optimisation (PSO) is a particular form of swarm intelligence, which itself is an innovative intelligent paradigm for solving optimization problems. PSO is generally used to find a global optimum in a single optimisation function. This typically occurs on one node(machine) but there has been a significant body of research into creating distributed implementations of the PSO algorithm. Such research has often focused on the creation and performance of the distributed implementation in an isolated manner or compared to different distributed algorithms.

This research piece aims to bridge a gap in the existing literature, by testing a distributed implementation …

Event-Driven Servers Using Asynchronous, Non-Blocking Network I/O: Performance Evaluation Of Kqueue And Epoll, Lorcan Leonard

Dissertations

This research project evaluates the performance of kqueue and epoll in the context of event-driven servers. The evaluation is done through benchmarking and tracing which are used to measure throughput and execution time respectively. The experiment is repeated for both a virtualised and native server environment. The results from the experiment are statistically analysed and compared. These results show significant differences between kqueue and epoll, and a profound impact of virtualisation as a variable.

A Comparison Of Instructional Efficiency Models In Third Level Education, Murali Rajendran

Dissertations

This study investigates the validity and sensitivity of a novel model of instructional efficiency: the parabolic model. The novel model is compared against state-of-the-art models present in instructional design today; Likelihood model, Deviational model and Multidimensional model. This models is based on the assumption that optimal mental workload and high performance leads to high efficiency, while other models assume that low mental workload and high performance leads to high efficiency. The investigation makes use of two instructional design conditions: a direct instructions approach to learning and its extension with a collaborative activity. A control group received the former instructional design …

Coordination, Adaptation, And Complexity In Decision Fusion, Weiqiang Dong

Dissertations

A parallel decentralized binary decision fusion architecture employs a bank of local detectors (LDs) that access a commonly-observed phenomenon. The system makes a binary decision about the phenomenon, accepting one of two hypotheses (H0 (“absent”) or H1 (“present”)). The k 1 LD uses a local decision rule to compress its local observations yk into a binary local decision uk; uk = 0 if the k 1 LD accepts H0 and uk = 1 if it accepts H1. The k 1 LD sends its decision uk over a noiseless dedicated channel to a Data Fusion Center (DFC). The DFC combines the …

Development Of Novel Inks And Approaches For Printing Tissues And Organs, Shen Ji

Dissertations

Tissue engineering is a multidisciplinary field that investigates and develops new methods to repair, regenerate and replace damaged tissues and organs, or to develop biomaterial platforms as in vitro models. Tissue engineering approaches require the fabrication of scaffolds using biomaterials or fabrication of living tissues using cells. As the demands of customized, implantable tissue/organs are increasing and becoming more urgent, conventional scaffold fabrication approaches are difficult to meet the requirements, especially for complex large-scale tissue fabrication. In this regard, three-dimensional (3D) printing attracted more interest over the past decades due to its unrivaled ability to fabricate highly customized tissues or …

Drone-Assisted Emergency Communications, Di Wu

Dissertations

Drone-mounted base stations (DBSs) have been proposed to extend coverage and improve communications between mobile users (MUs) and their corresponding macro base stations (MBSs). Different from the base stations on the ground, DBSs can flexibly fly over and close to MUs to establish a better vantage for communications. Thus, the pathloss between a DBS and an MU can be much smaller than that between the MU and MBS. In addition, by hovering in the air, the DBS can likely establish a Line-of-Sight link to the MBS. DBSs can be leveraged to recover communications in a large natural disaster struck area …

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Human-Robot Interaction For Assistive Robotics, Jiawei Li

Dissertations

This dissertation presents an in-depth study of human-robot interaction (HRI) withapplication to assistive robotics. In various studies, dexterous in-hand manipulation is included, assistive robots for Sit-To-stand (STS) assistance along with the human intention estimation. In Chapter 1, the background and issues of HRI are explicitly discussed. In Chapter 2, the literature review introduces the recent state-of-the-art research on HRI, such as physical Human-Robot Interaction (HRI), robot STS assistance, dexterous in hand manipulation and human intention estimation. In Chapter 3, various models and control algorithms are described in detail. Chapter 4 introduces the research equipment. Chapter 5 presents innovative theories and …

Experiments And Modeling Of The Chemo-Mechanically Coupled Behavior Of Polymeric Gels, Nikola Bosnjak

Dissertations

Polymeric materials consist of mutually entangled or chemically crosslinked long njitmolecular chains which form a polymer network. Due to their molecular structure, the njitpolymeric materials are known to undergo large deformation in response to various njitenvironmental stimuli, such as temperature, chemical potential and light.

When a polymer network is exposed to a suitable chemical solvent, the solvent molecules are able to diffuse inside the network, causing it to undergo a large volumetric deformation, known as swelling. In addition to volumetric deformation, this process involves the chemical mixing of the polymer network and solvent molecules, and is typically environmentally responsive. A …

High-Speed Rail Safety Analysis Based On Dual-Weighted Complex Network, Liu Lv

Dissertations

This study uses a complex network model to analyze the causes of accidents in high-speed railway operations. By identifying the key factors that led to high-speed railway accidents, hidden safety hazards were discovered. This will help improve the operational safety of the U.S. high-speed rail line under construction.

The analysis uses the regional high-speed railway network in Guangzhou, China as a case study, including the railway (including high-speed railway) accidents that occurred in the company's jurisdiction from 2013 to 2017. With comparative analysis between general railways and high-speed railways, the changes of high-speed railway safety factors are explored. Data analysis …

Dances And Escape Of The Vortex Quartet, Brandon Behring

Dissertations

This dissertation considers the linear stability of a one-parameter family of periodic solutions of the four-vortex problem known as 'leapfrogging' orbits. These solutions, which consist of two pairs of identical yet oppositely-signed vortices, were known to W. Gröbli (1877) and A. E. H. Love (1883) and can be parameterized by a dimensionless parameter related to the geometry of the initial configuration. Simulations by Acheson and numerical Floquet analysis by Tophøj and Aref both indicate, to many digits, that the bifurcation occurs at a value related to the inverse square of the golen ratio. Acheson observed that, after an initial period …

Online Fulfillment: F-Warehouse Order Consolidation And Bops Store Picking Problems, Wen Zhu

Dissertations

Fulfillment of online retail orders is a critical challenge for retailers since the legacy infrastructure and control methods are ill suited for online retail. The primary performance goal of online fulfillment is speed or fast fulfillment, requiring received orders to be shipped or ready for pickup within a few hours. Several novel numerical problems characterize fast fulfillment operations and this research solves two such problems. Order fulfillment warehouses (F-Warehouses) are a critical component of the physical internet behind online retail supply chains. Two key distinguishing features of an F-Warehouse are (i) Explosive Storage Policy – A unique item can be …

Characterizing Reactive Iron Mineral Coatings And Their Roles In Natural Attenuation At A Site With Historical Contamination, Han Hua

Dissertations

Reactive iron mineral coatings in redox transition zones play an important role in contaminant attenuation. These mineral coatings include poorly crystalline to crystalline iron sulfides, carbonates, and oxyhydroxides, and are a signature of the biogeochemical processes occurring. To better understand these processes, reactive iron mineral coatings are characterized in an 18-m Anaerobic Core collected from a contaminated industrial site. This study targets redox transition zones uncovered in the core. A suite of complementary analyses is applied to distinguish the surface coating mineralogy using X-ray Diffraction, X-ray fluorescence, and field-emission scanning electron microscopy (FESEM) with energy dispersive X-ray analyzer (EDX). In …

The Aging And Impacts Of Atmospheric Soot: Closing The Gap Between Experiments And Models, Ogochukwu Yvonne Enekwizu

Dissertations

The main goal of this dissertation is to generate data and parameterizations to accurately represent soot aerosols in atmospheric models. Soot from incomplete combustion of fossil fuels and biomass burning is a major air pollutant and a significant contributor to climate warming. The environmental impacts of soot are strongly dependent on the particle morphology and mixing state, which evolve continuously during atmospheric transport via a process known as aging. To make predictions of soot impacts on the environment, most atmospheric models adopt simplifications of particle structure and mixing state, which lead to substantial uncertainties. Using an experimentally constrained modeling approach, …

Performance Optimization Of Big Data Computing Workflows For Batch And Stream Data Processing In Multi-Clouds, Huiyan Cao

Dissertations

Workflow techniques have been widely used as a major computing solution in many science domains. With the rapid deployment of cloud infrastructures around the globe and the economic benefits of cloud-based computing and storage services, an increasing number of scientific workflows have migrated or are in active transition to clouds. As the scale of scientific applications continues to grow, it is now common to deploy various data- and network-intensive computing workflows such as serial computing workflows, MapReduce/Spark-based workflows, and Storm-based stream data processing workflows in multi-cloud environments, where inter-cloud data transfer oftentimes plays a significant role in both workflow performance …

The Stability Of Nanobubbles And Its Application In Contaminated Sediment Treatment, Shaini Dilsha Aluthgun Hewage

Dissertations

This dissertation consists of two sections. First, nanobubbles' stability and behavior are studied using experimental and theoretical approaches. Second, nanobubbles application combined with ultrasound to remediate contaminated sediments is discussed.

The stability study consists of four sections. (i). Laboratory investigation to determine bubble size distributions and zeta potentials for different gases, pH levels, temperatures, and salt conditions. (ii). A theoretical study based on the diffused double layer theory to explain nanobubbles' behavior in different NaCl concentrations. (iii). Nanobubbles' stability in electrolyte solutions under different ion valencies using deionized water, NaCl, Na₂SO₄, Na₃PO₄, …

Modeling Mass Transfer And Chemical Reaction In Industrial Nitrocellulose Manufacturing Processes, Francis Patrick Sullivan

Dissertations

A series of models are proposed to describe the production of military grade nitrocellulose from dense cellulose materials in mixtures of nitric acid, sulfuric acid, and water. This effort is conducted to provide a predictive capability for analyzing the rate and extent of reaction achieved under a range of reaction conditions used in the industrial nitrocellulose manufacturing process for sheeted cellulose materials. Because this capability does not presently exist, nitrocellulose producers have historically relied on a very narrow range of cellulose raw materials and resorted to trial and error methods to develop processing conditions for new materials. This tool enables …

Blast Shock-Wave Characterization In Experimental Shock Tubes, Sudeepto Kahali

Dissertations

Blast-induced traumatic brain injuries have affected U.S. soldiers deployed for extended periods in the gulf and Afghanistan wars. To identify the biomechanical and biochemical mechanisms of injury, critical in the identification of diagnostic and therapeutic tools, compressed gas-driven shock tubes are used by investigators to study shockwave-animal specimen interactions and its biological consequences. However, shock tubes are designed and operated in a variety of geometry with a range of process parameters, and the quality of shock wave characteristics relevant to field conditions and therefore the study of blast-induced traumatic brain injuries suffered by soldiers is affected by those conditions. Lab-to-lab …

Semantic, Integrated Keyword Search Over Structured And Loosely Structured Databases, Xinge Lu

Dissertations

Keyword search has been seen in recent years as an attractive way for querying data with some form of structure. Indeed, it allows simple users to extract information from databases without mastering a complex structured query language and without having knowledge of the schema of the data. It also allows for integrated search of heterogeneous data sources. However, as keyword queries are ambiguous and not expressive enough, keyword search cannot scale satisfactorily on big datasets and the answers are, in general, of low accuracy. Therefore, flat keyword search alone cannot efficiently return high quality results on large data with structure. …

Countering Internet Packet Classifiers To Improve User Online Privacy, Sina Fathi-Kazerooni

Dissertations

Internet traffic classification or packet classification is the act of classifying packets using the extracted statistical data from the transmitted packets on a computer network. Internet traffic classification is an essential tool for Internet service providers to manage network traffic, provide users with the intended quality of service (QoS), and perform surveillance. QoS measures prioritize a network's traffic type over other traffic based on preset criteria; for instance, it gives higher priority or bandwidth to video traffic over website browsing traffic. Internet packet classification methods are also used for automated intrusion detection. They analyze incoming traffic patterns and identify malicious …

Development Of Novel Membranes For Nanocarbon Enhanced Separation With Application In Biofuels And Solvent Recover, Oindrila Gupta

Dissertations

Pharmaceutical industries historically have had one of the highest amounts of solvent waste generated per unit of drug manufactured. Energy requirements and carbon footprint of current solvent recycling processes tend to be quite high, and the incineration of the solvents for waste disposal produces toxic air emissions. Also, rapidly increasing demand for energy and strict regulation on engine pollutant emissions have necessitated the use of alcohol as carbon-neutral fuels. Thermal distillation is one of the most common methods for the separation of alcohol-water mixtures. However, its application is limited due to energy requirements and high operating costs, and heating to …

Predicting Bulk-Scale Properties Of Pharmaceutical Powders From Their Particle-Scale Dimensionless Measures, Kuriakose T. Kunnath

Dissertations

Loose powder packing and flowability are both important bulk properties to consider in relation to pharmaceutical tablet and capsule manufacturing. These properties as well as cohesive powder agglomeration tendency impact the efficiency of various processes such as feeding, blending, conveying, and compaction, and could have an adverse effect on final drug product. Pharmaceutical powders are often milled to fine sizes (<100 gm) for dissolution improvements via increased available surface area. However, such particle size reductions lead to inadequate bulk powder properties due to high cohesion among the individual particles. Recent work has demonstrated the ability of nano-silica dry coating techniques to significantly decrease interparticle forces without changes in particle size. In this work, the ability to predict properties such as powder bed porosity, flowability, and particle agglomeration both before and after nano-silica dry coating is examined, along with assessment of the extent of property enhancements after dry coating. Previous studies have utilized empirical approaches to build property prediction models. However, such approaches lack physical fundamentals which dictate bulk powder behavior and would be unable to account for the effects of dry powder coating. Incorporation of physics can be done via computation of the granular Bond number, as is done in this study for a large dataset of commonly used pharmaceutical powders, with wide variations in particle size, shape, density, and surface roughness. Predictive capability of current Bond number models is investigated, reasons for outliers are elucidated, and amendments to improve prediction is attempted. Overall, the aim of this work is to expand generalizability of Bond number models to a wider variety of particles, and extend its use from single powders to multi-component mixtures. The major outcome of this work is the development of a predictive framework that is expected to simplify pharmaceutical dry powder formulation development, reduce required experimental testing, and provide quantifiable estimates to aid processing route decision making.

Practical Adhesion Measurements In Organic Coatings; Advancing Understanding And Mechanical Methods Development, Diana Gottschalk

Dissertations

“Adhesion” can be considered either a mechanical or chemical phenomenon. The mechanical interpretation describes the difficulty of separating surfaces and is useful for quantifying performance within applications that depend on bulk and interfacial properties. Chemical adhesion describes interfacial resistance to chemical attack and does not depend on bulk properties. Predicting chemical failure through mechanical measurement is confounded by the influence of bulk properties. However, the prospect is attractive because of the robust tolerance for sample geometries, allowing experiments to resemble an end-use system. The present work's primary goal was to elevate mechanical methods to provide a detailed interfacial characterization of …

Atmospheric Turbulence Distortion In Video: Restoration Utilizing Sparse Analysis, Benjamin J. Sanda

Dissertations

The removal of atmospheric turbulence (AT) distortion in long range imaging is one of the most challenging areas of research in imaging processing with an immediate need for solutions in several applications such as in military and transportation systems. AT exacerbates distortion due to non-linear geometric blur and scintillations in long-distance images and videos, severely reducing image quality and information interpretation. AT negatively impacts both human and computer vision systems, compromising visibility essential for accurate object identification and tracking.

In this dissertation, a novel sparse analysis framework is developed to address efficient AT blur and scintillation removal in video. Operating …

Objectively Determining The Language-Related Communication Challenges For In-Flight Operations, Fehime Utkan

Dissertations

Communication breakdowns between pilots and air traffic controllers (ATCs) have been identified as primary factors in fatal airplane accidents (Wu et. al., 2019; Bauh & Stolzer, 2018; Ritter, 1996; Eurocontrol, 2011). Although there are various aspects that have affected communication efficiency, language-related issues have been mostly associated with transmissions involved in serious incidents, especially in multicultural flight environments (Sexton & Helmrich, 2000). More than 2,000 people have died in accidents where miscommunication was a primary factor (Bauh & Stolzer, 2018; Patty, 2016). By the year of 2025, the air transportation system is projected to become more complex, and the volume …

Development Of Functional Materials And Devices On Flexible Platforms Using Additive Print Manufacturing Processes For Biomedical And Environmental Applications, Dinesh Maddipatla

Dissertations

In recent years, considerable research has been vested into the development of printed electronics (PE) to explore the best ways of fabricating electronic devices on flexible platforms using additive print manufacturing processes. PE produces flexible devices that are compatible with complex geometries, foldable applications and conformal to curved surfaces, with a promising potential for large‐area device fabrication at relatively lower manufacturing costs. This dissertation focuses majorly on the design and fabrication of novel flexible functional materials and devices for biomedical and environmental applications using additive printing processes.

Initially, a simple paper-based low cost and rapid prototypable platform with oxygen sensors …