Engineering Commons^™

Communicating Uncertain Information From Deep Learning Models In Human Machine Teams, Harishankar V. Subramanian, Casey I. Canfield, Daniel Burton Shank, Luke Andrews, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The role of human-machine teams in society is increasing, as big data and computing power explode. One popular approach to AI is deep learning, which is useful for classification, feature identification, and predictive modeling. However, deep learning models often suffer from inadequate transparency and poor explainability. One aspect of human systems integration is the design of interfaces that support human decision-making. AI models have multiple types of uncertainty embedded, which may be difficult for users to understand. Humans that use these tools need to understand how much they should trust the AI. This study evaluates one simple approach for communicating …

An Explainable And Statistically Validated Ensemble Clustering Model Applied To The Identification Of Traumatic Brain Injury Subgroups, Dacosta Yeboah, Louis Steinmeister, Daniel B. Hier, Bassam Hadi, Donald C. Wunsch, Gayla R. Olbricht, Tayo Obafemi-Ajayi

Electrical and Computer Engineering Faculty Research & Creative Works

We present a framework for an explainable and statistically validated ensemble clustering model applied to Traumatic Brain Injury (TBI). The objective of our analysis is to identify patient injury severity subgroups and key phenotypes that delineate these subgroups using varied clinical and computed tomography data. Explainable and statistically-validated models are essential because a data-driven identification of subgroups is an inherently multidisciplinary undertaking. In our case, this procedure yielded six distinct patient subgroups with respect to mechanism of injury, severity of presentation, anatomy, psychometric, and functional outcome. This framework for ensemble cluster analysis fully integrates statistical methods at several stages of …

Evaluation Of Standard And Semantically-Augmented Distance Metrics For Neurology Patients, Daniel B. Hier, Jonathan Kopel, Steven U. Brint, Donald C. Wunsch, Gayla R. Olbricht, Sima Azizi, Blaine Allen

Electrical and Computer Engineering Faculty Research & Creative Works

Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.

Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by …

Handling Missing Data For Unsupervised Learning With An Application On A Fitbir Traumatic Brain Injury (Tbi) Dataset, Louis Steinmeister, Dacosta Yeboah, Gayla Olbricht, Tayo Obafemi-Ajayi, Bassam Hadi, Daniel Hier, Donald C. Wunsch

Mathematics and Statistics Faculty Research & Creative Works

"The problem of missing data and imputation have been widely discussed amongst specialists. However, many data scientists and applied statisticians fail to appropriately consider this issue. Often, it seems intuitive to discard observations containing missing data or simply to substitute means. This can lead to disastrous consequences, particularly in an era of exponentially increasing data volumes. In the following, we show how inappropriate handling of missing data and an insufficient analysis of the censoring mechanism can lead to a bias, overconfidence in the estimation of parameters, could challenge the reproducibility of obtained results, and may distort the structure of the …

Fiber-Optic Micro-Probes For Measuring Acidity Level, Temperature, And Antigens, Yinfa Ma, Honglan Shi, Qingbo Yang, Hai Xiao

Chemistry Faculty Research & Creative Works

A pH micro-probe, a temperature micro-probe, and an immuno-based micro-probe each include a shaft for transmuting an input light signal and a tip for inserting into a cell or other substance for measuring pH, temperature, and/or antigens. The pH micro-probe and the temperature micro-probe each include a luminescent material positioned on the tip of the micro-probe. The light signal excites the luminescent material so that the luminescent material emits a luminescent light signal. The luminescent light signal has a property value dependent on the pH or temperature being measured and reflects back through the shaft for being measured by a …

Effect Of Subsurface Microseismicity On The Motion Of Surrounding Dispersed Droplets -- Data, Chao Zeng, Wen Deng

Effect of Subsurface Microseismicity on the Motion of Surrounding Dispersed Droplets – Data

Spreadsheet - Data plotted in Figure 4 and Figure 5

Supporting information

System Efficient Esd Design Concept For Soft Failures, Giorgi Maghlakelidze

Doctoral Dissertations

"This research covers the topic of developing a systematic methodology of studying electrostatic discharge (ESD)-induced soft failures. ESD-induced soft failures (SF) are non-destructive disruptions of the functionality of an electronic system. The soft failure robustness of a USB3 Gen 1 interface is investigated, modeled, and improved. The injection is performed directly using transmission line pulser (TLP) with varying: pulse width, amplitude, polarity. Characterization provides data for failure thresholds and a SPICE circuit model that describes the transient voltage and current at the victim. Using the injected current, the likelihood of a SF is predicted. ESD protection by transient voltage suppressor …

Modification Of The Optical Response Of Alpha Quartz Via The Deposition Of Gold Nanoparticles In Etched Ion Tracks, Maria C. Garcia Toro

Doctoral Dissertations

”This study addresses the experimental methods used to develop and characterize plasmonic devices capable of modifying the optical response of alpha quartz via the deposition of gold nanoparticles in etched ion tracks. In the first part of the research, the microstructural characterization of latent and etched ion tracks produced in alpha quartz (α-SiO₂) is presented. Single crystals of α-SiO₂ were irradiated with two highly energetic ions to different nominal fluences. As expected, the morphology of the resulting ion tracks depends on the energy of the incident ion and their stopping powers within the target material. Subsequent chemical …

Continuous-Flow Synthesis Of Fine Chemicals And Pharmaceutical Compounds Over Intelligent Organocatalysts With Bifunctional Reactivity, Abdo-Alslam Alwakwak

Doctoral Dissertations

“Many biological systems that utilize organic active sites to catalyze reactions under mild conditions invoke cooperative catalytic pathways, whereby two or more active sites work together to activate the reactant(s). The use of cooperative (bifunctional) catalysts and continuous flow chemistry (a reaction within the narrow channels of a micro‐ or microfluidic reactor) are commonplace in sustainable chemical transformation and attract a great deal of interest with respect to economic and environmentally-sustainable production of fine chemicals, pharmaceuticals, and agrochemicals, water treatment, as well as upgrading of biomass feedstocks. Although, some methods have been developed for immobilization of bifunctional catalysts for cooperative …

An Integrated Wellbore Stability Study To Mitigate Expensive Wellbore Instability Problems While Drilling Into Zubair Shale/Sand Sequence, Southern Iraq, Ahmed Khudhair Abbas

Doctoral Dissertations

”The Zubair Formation is the most prolific reservoir in Iraq, which is comprised of sandstones interbedded with shale sequences. Due to the weak nature of the shale sequence, the instability of a wellbore is one of the most critical challenges that continuously appears during drilling across this formation. Historically, over 90% of wellbore problems in the Zubair Formation were due to wellbore instability. Problems associated with wellbore instability, such as tight hole, shale caving, stuck logging tools along with subsequent fishing, stuck pipe, and sidetracking result in increasing the non-productive time. This non-productive time has cost an enormous amount of …

Characterization Of A Plasma Source Simulating Solar Wind Plasma In A Vacuum Chamber, Blake Anthony Folta

Masters Theses

"The United States has set an aggressive time line to not only return to the Moon, but also to establish a sustained human presence. In the Apollo missions dust was a significant factor, but the duration of those missions was short so dust and surface charging were problems, but they did not pose an immediate threat. For a long-term mission, these problems instead become incredibly detrimental. Because of this, research needs to be conducted to investigate these phenomena so that mitigation techniques can be developed and tested. To this end, this thesis serves to demonstrate the Gas and Plasma Dynamics …

Enhanced Electrochemical Performance Of Li-Ion Battery Cathodes By Atomic Layer Deposition, Yan Gao

Doctoral Dissertations

”Li-ion battery now plays an irreplaceable role in supplying green and convenient energy. In this work, atomic layer deposition (ALD) was used to modify Li-ion battery cathode particles for performance enhancement.

An ultrathin and conductive CeO₂ ALD film was deposited on Li-rich layered cathode particles, of which the specific capacity and cyclic stability were significantly improved. On the same cathode particles, FeO_x ALD and post-annealing resulted in a stable and conductive surface spinel phase to improve the performance.

Synergetic TiN coating and Ti doping were performed on a LiFePO₄ (LFP) cathode and extended its cycle life. The …

Effect Of Subsurface Microseismicity On The Motion Of Surrounding Dispersed Droplets: Supporting Information, Chao Zeng, Wen Deng

Research Data

The human-induced seismicity has called substantial attention in recent years. The effect of seismicity on the subsurface structure has been extensively studied. However, the effect of seismicity, especially those microseismicity, on surrounding immiscible fluids is rarely investigated. In porous media with two or more immiscible fluids, different amplitudes of vibration induced by seismicity have distinct effects on the dynamic behavior of fluids. Three types of pore-scale models are prevalent in the analysis of the motion of immiscible droplets. The underlying assumptions and accuracy of these models are compared in this study in both frequency domain and time domain. The frequency …

Predictive Geohazard Mapping Using Lidar And Satellite Imagery In Missouri And Oklahoma, Usa, Olufeyisayo B. Ilesanmi

Doctoral Dissertations

”Light Detection and Ranging (LiDAR) and satellite imagery have become the most utilized remote sensing technologies for compiling inventories of surficial geologic conditions. Point cloud data obtained from multi-spectral remote sensing methods provide a detailed characterization of the surface features, in particular, the detailed surface manifestations of underlying geologic structures. When combined, point clouds eliminate bias from visual inconsistencies and/or statistical values. This research explores the competence of point clouds derived from LiDAR and Unmanned Aerial Systems (UAS) as a predictive tool in evaluating various geohazards. It combines these data sets with other remote sensing techniques to evaluate the sensitivity …

Human Behavior Understanding For Worker-Centered Intelligent Manufacturing, Wenjin Tao

Doctoral Dissertations

“In a worker-centered intelligent manufacturing system, sensing and understanding of the worker’s behavior are the primary tasks, which are essential for automatic performance evaluation & optimization, intelligent training & assistance, and human-robot collaboration. In this study, a worker-centered training & assistant system is proposed for intelligent manufacturing, which is featured with self-awareness and active-guidance. To understand the hand behavior, a method is proposed for complex hand gesture recognition using Convolutional Neural Networks (CNN) with multiview augmentation and inference fusion, from depth images captured by Microsoft Kinect. To sense and understand the worker in a more comprehensive way, a multi-modal approach …

Magnetic Control Of Transport Of Particles And Droplets In Low Reynolds Number Shear Flows, Jie Zhang

Doctoral Dissertations

“Magnetic particles and droplets have been used in a wide range applications including biomedicine, biological analysis and chemical reaction. The manipulation of magnetic microparticles or microdroplets in microscale fluid environments is one of the most critical processes in the systems and platforms based on microfluidic technology. The conventional methods are based on magnetic forces to manipulate magnetic particles or droplets in a viscous fluid.

In contrast to conventional magnetic separation method, several recent experimental and theoretical studies have demonstrated a different way to manipulate magnetic non-spherical particles by using a uniform magnetic field in the microchannel. However, the fundamental mechanism …

Development Of A Modeling Algorithm To Predict Lean Implementation Success, Richard Charles Barclay

Doctoral Dissertations

”Lean has become a common term and goal in organizations throughout the world. The approach of eliminating waste and continuous improvement may seem simple on the surface but can be more complex when it comes to implementation. Some firms implement lean with great success, getting complete organizational buy-in and realizing the efficiencies foundational to lean. Other organizations struggle to implement lean. Never able to get the buy-in or traction needed to really institute the sort of cultural change that is often needed to implement change. It would be beneficial to have a tool that organizations could use to assess their …

Studying The Effects Of Various Process Parameters On Early Age Hydration Of Single- And Multi-Phase Cementitious Systems, Rachel Cook

Doctoral Dissertations

”The hydration of multi-phase ordinary Portland cement (OPC) and its pure phase derivatives, such as tricalcium silicate (C₃S) and belite (ß-C₂S), are studied in the context varying process parameters -- for instance, variable water content, water activity, superplasticizer structure and dose, and mineral additive type and particle size. These parameters are studied by means of physical experiments and numerical/computational techniques, such as: thermodynamic estimations; numerical kinetic-based modelling; and artificial intelligence techniques like machine learning (ML) models. In the past decade, numerical kinetic modeling has greatly improved in terms of fitting experimental, isothermal calorimetry to kinetic-based modelling …

Geophysical Characteristics Of Nickel And Copper Deposits In Wadi Al Khadra Prospect, Southwestern Of Saudi Arabia, Abdulrahman Ahmed Aljabbab

Doctoral Dissertations

“Three geophysical datasets (self-potential, magnetics, and time - domain electromagnetics) were acquired at Wadi Al Khadra Ni-Cu prospect in southwest Saudi Arabia, and were processed and interpreted for the Saudi Geological Survey. The primary objectives were to map the distribution of metallic mineralization, map structures, verify the integration of the geophysical interpretations and its signatures in conjunction with boreholes information, distinguish the similarities and differences in the integrated interpretation of geophysical data, and design optimal processing and interpretation data parameters. The self-potential tool was used to map the variation in natural surface potential differences to map lateral variations in the …

Seismic Behavior Of Composite Bridge Columns, Mohanad M. Abdulazeez

Doctoral Dissertations

“This study investigates experimentally and numerically the seismic behavior of large-scale hollow-core fiber-reinforced polymer-concrete-steel (HC-FCS) innovative bridge columns as a sustainable approach to endure and rapidly recover from natural disasters such as earthquakes. The HC-FCS column consisted of a concrete shell sandwiched between an outer fiber-reinforced polymer (GFRP) tube and an inner steel tube to provided continuous confinement for the concrete shell along with the height of the column. The columns have a slender inner steel tube with diameter-to-thickness (D_s/t_s) ratios ranged between 85 to 254. Each steel tube was embedded into the footing, while the …

Observer-Based Event-Triggered And Set-Theoretic Neuro-Adaptive Controls For Constrained Uncertain Systems, Abdul Ghafoor

Doctoral Dissertations

"In this study, several new observer-based event-triggered and set-theoretic control schemes are presented to advance the state of the art in neuro-adaptive controls. In the first part, six new event-triggered neuro-adaptive control (ETNAC) schemes are presented for uncertain linear systems. These comprehensive designs offer flexibility to choose a design depending upon system performance requirements. Stability proofs for each scheme are presented and their performance is analyzed using benchmark examples. In the second part, the scope of the ETNAC is extended to uncertain nonlinear systems. It is applied to a case of precision formation flight of the microsatellites at the Sun-Earth/Moon …

Geophysical Assessment Of The Lake Chesterfield Site, Missouri, Diya Ali Ahmad Alfuqara

Doctoral Dissertations

"Since construction of the Lake Chesterfield, Missouri in 1986, significant leaks have occurred causing the lake to lose substantive volumes of water. Mitigation efforts, have not solved the problem. Indeed, in June of 2017, the water level in Lake Chesterfield dropped at an alarmingly rapid rate. Prior to authorizing additional mitigation work, the Lake Chesterfield. Home Owners Association (LCHOA) decided to acquire geophysical data across the drained and dry lake bed. These information would help a geotechnical engineering firm determine the most appropriate mitigation plan.

In the summer of 2018, electrical resistivity tomography, multichannel analysis of surface wave, and spontaneous-potential …

Computational Model For Neural Architecture Search, Ram Deepak Gottapu

Doctoral Dissertations

"A long-standing goal in Deep Learning (DL) research is to design efficient architectures for a given dataset that are both accurate and computationally inexpensive. At present, designing deep learning architectures for a real-world application requires both human expertise and considerable effort as they are either handcrafted by careful experimentation or modified from a handful of existing models. This method is inefficient as the process of architecture design is highly time-consuming and computationally expensive.

The research presents an approach to automate the process of deep learning architecture design through a modeling procedure. In particular, it first introduces a framework that treats …

Minimizing The Detrimental Effects Of Hydro-Peaking On Riverbank Instability: The Lower Osage River Case, Wesam Sameer Mohammed-Ali

Doctoral Dissertations

"The fluctuation of water level downstream from dams due to hydropower flow releases negatively affects the riverbank stability. Therefore, this research aims to examine the feasibility of using an optimization technique to mitigate the riverbank instability resulting from the outflow variation of hydropower plants. The effects of the water releases from the Bagnell Dam were investigated by computing a series of safety factors for 78 cross sections along the 81-mile stretch of the lower Osage River in relation to outflow events by using the integrated BSTEM model incorporated into the HEC-RAS model. The 1-D sediment transport and unsteady flow in …

Characterization Of Neutron Irradiated Accident Tolerant Nuclear Fuel Cladding Silicon Carbide & Radiation Detector Deadtime, Bader Almutairi

Doctoral Dissertations

“In part I, the pulse shape characteristics generated by a Geiger Muller (GM) detector and recorded by an oscilloscope manually, were investigated. The objective of part I was (1) to find a correlation between pulse shape and the operating voltage; and (2) to assess if pulse shape properties followed distinct patterns comparable to detector deadtime findings reported by a previous study. It was observed that (1) there is a strong correlation between pulse shape and operating voltage, and (2) pulse shape falls in three distinct regions similar to detector deadtime. Furthermore, parts II and III are companions and share the …

An Approach To System Of Systems Resiliency Using Architecture And Agent-Based Behavioral Modeling, Paulette Bootz Acheson

Doctoral Dissertations

”In today’s world it is no longer a question of whether a system will be compromised but when the system will be compromised. Consider the recent compromise of the Democratic National Committee (DNC) and Hillary Clinton emails as well as the multiple Yahoo breaches and the break into the Target customer database. The list of exploited vulnerabilities and successful cyber-attacks goes on and on. Because of the amount and frequency of the cyber-attacks, resiliency has taken on a whole new meaning. There is a new perspective within defense to consider resiliency in terms of Mission Success.

This research develops a …

Development Of Tools For Water Management In The Hatra Watershed (Northwestern Iraq) Using Satellite Technologies, Majid S. Mohamod

Doctoral Dissertations

“All around the world the demand for water is increasing, especially in arid and semi-arid regions, including Iraq which subject to continuous desertification that is worsening, more importantly the Jezira region in northwestern Iraq. Thus, it’s crucial to have a better strategy for water management. One of these strategies is to promote groundwater recharge for restoring the aquifer depletion. The successful groundwater recharge is limited by some potential data such as the annual water budge and precipitation measurements. The atomospheric and hydrological observations are limited by sparse population which tends to be less in arid and semi-arid regions. Therefore, an …

Transition Metal Chalcogenide Hybrid Systems As Catalysts For Energy Conversion And Biosensing, Siddesh Umapathi

Doctoral Dissertations

"Generation of hydrogen and oxygen through catalyst-aided water splitting which has immense applications in metal air batteries, PEM fuel cells and solar to fuel energy production, has been one of the critical topics in recent times. The state of art oxygen evolution reaction (OER), oxygen reduction reaction (ORR), hydrogen evolution reaction (HER) catalysts are mostly comprised of precious metals. The current challenge lies in replacing these precious metal-based catalysts with non-precious earth-abundant materials without compromising catalytic efficiency.

This research explores mixed metal selenides containing Fe-Ni, Fe-Co and RhSe which were hydrothermally synthesized and/or electrodeposited and tested for OER and ORR …

Deep Learning For Digitized Histology Image Analysis, Sudhir Sornapudi

Doctoral Dissertations

“Cervical cancer is the fourth most frequent cancer that affects women worldwide. Assessment of cervical intraepithelial neoplasia (CIN) through histopathology remains as the standard for absolute determination of cancer. The examination of tissue samples under a microscope requires considerable time and effort from expert pathologists. There is a need to design an automated tool to assist pathologists for digitized histology slide analysis. Pre-cervical cancer is generally determined by examining the CIN which is the growth of atypical cells from the basement membrane (bottom) to the top of the epithelium. It has four grades, including: Normal, CIN1, CIN2, and CIN3. In …