Engineering Commons^™

Designing Explainable Ai To Improve Human-Ai Team Performance: A Medical Stakeholder-Driven Scoping Review, Harishankar V. Subramanian, Casey I. Canfield, Daniel Burton Shank

Engineering Management and Systems Engineering Faculty Research & Creative Works

The rise of complex AI systems in healthcare and other sectors has led to a growing area of research called Explainable AI (XAI) designed to increase transparency. In this area, quantitative and qualitative studies focus on improving user trust and task performance by providing system- and prediction-level XAI features. We analyze stakeholder engagement events (interviews and workshops) on the use of AI for kidney transplantation. From this we identify themes which we use to frame a scoping literature review on current XAI features. The stakeholder engagement process lasted over nine months covering three stakeholder group's workflows, determining where AI could …

Stochastic Modeling Of Decarbonizing Strategy, Policy, And Market-Induced Incentives For The Us Electricity Sector, Jessica W.A. Azure, Samuel Frimpong, Mahelet G. Fikru

Mining Engineering Faculty Research & Creative Works

In line with the global pursuit of achieving net-zero carbon emissions, integrating carbon capture and storage (CCS) and renewable energy (RE) technologies is important in power production. This study evaluates the profitability of CCS and RE technologies as alternative ways of achieving climate change goals. While past research focused on costs, technological advancements, and capture methods, there is a need for more studies on assessing the financial feasibility of these climate change solutions under uncertain conditions, alongside specific performance goals and strategies to entice power producers. Using a comprehensive framework featuring deterministic and stochastic modeling approaches, this research explores the …

Don’T Touch That Dial: Psychological Reactance, Transparency, And User Acceptance Of Smart Thermostat Setting Changes, Matthew Heatherly, Denise A. Baker, Casey I. Canfield

Psychological Science Faculty Research & Creative Works

Automation inherently removes a certain amount of user control. If perceived as a loss of freedom, users may experience psychological reactance, which is a motivational state that can lead a person to engage in behaviors to reassert their freedom. In an online experiment, participants set up and communicated with a hypothetical smart thermostat. Participants read notifications about a change in the thermostat's setting. Phrasing of notifications was altered across three dimensions: strength of authoritative language, deviation of temperature change from preferences, and whether or not the reason for the change was transparent. Authoritative language, temperatures outside the user's preferences, and …

Evaluating Barriers To And Impacts Of Rural Broadband Access, Javier Valentín-Sívico

Doctoral Dissertations

"The lack of adequate broadband infrastructure persists in many rural communities. Beyond funding, additional barriers persist, such as digital literacy and community-level self-efficacy. As a result, the first contribution articulates barriers at the organizational level. This work proposes a framework based on the Theory of Planned Behavior to highlight stakeholder dynamics that have constrained Regional Planning Commissions from advancing broadband infrastructure in rural areas. One approach to address these barriers is to provide stakeholders with analytical tools to evaluate the benefits and costs of various broadband options for their community since there is not a one-size-fits-all solution. To this end, …

Advances In Energy Hybridization For Resilient Supply: A Sustainable Approach To The Growing World Demand, Haider Al-Rubaye, Joseph D. Smith, Mohammed H.S. Zangana, Prashant Nagapurkar, Yishu Zhou, Gregory M. Gelles

Chemical and Biochemical Engineering Faculty Research & Creative Works

Energy poverty, defined as a lack of access to reliable electricity and reliance on traditional biomass resources for cooking, affects over a billion people daily. The World Health Organization estimates that household air pollution from inefficient stoves causes more premature deaths than malaria, tuberculosis, and HIV/AIDS. Increasing demand for energy has led to dramatic increases in emissions. The need for reliable electricity and limiting emissions drives research on Resilient Hybrid Energy Systems (RHESs), which provide cleaner energy through combining wind, solar, and biomass energy with traditional fossil energy, increasing production efficiency and reliability and reducing generating costs and emissions. Microgrids …

Guiding A Human Follower With Interaction Forces: Implications On Physical Human-Robot Interaction, George L. Holmes, Keyri Moreno Bonnett, Amy Costa, Devin Michael Burns, Yun Seong Song

Psychological Science Faculty Research & Creative Works

This work challenges the common assumption in physical human-robot interaction (pHRI) that the movement intention of a human user can be simply modeled with dynamic equations relating forces to movements, regardless of the user. Studies in physical human-human interaction (pHHI) suggest that interaction forces carry sophisticated information that reveals motor skills and roles in the partnership and even promotes adaptation and motor learning. In this view, simple force-displacement equations often used in pHRI studies may not be sufficient. To test this, this work measured and analyzed the interaction forces (F) between two humans as the leader guided the blindfolded follower …

State Level Trends In Renewable Energy Procurement Via Solar Installation Versus Green Electricity, Eric Michael Hanson

Masters Theses

“In the past 5 years, consumer options for procuring renewable energy have increased, ranging from rooftop solar installation to utility green pricing to Community Choice Aggregation. These options vary in terms of costs and benefits to the consumer as well as grid integration implications. However, little is known regarding how the presence of a wide range of options for utility-scale renewable procurement affects demand for distributed residential solar installations. In theory, there are three possible relationships, (1) positive correlation, where utility-scale and distributed resources complement each other to increase overall production, (2) negative correlation, where utility-scale and distributed resources are …

Industry 4.0 Remanufacturing: A Novel Approach Towards Smart Remanufacturing, Prashansa Ragampeta

Masters Theses

“Smart remanufacturing has become more popular in recent years as a result of its multiple benefits and the growing need for society to encourage a circular economy that leads to sustainability. One of the most common end-of-life (EoL) choices that can lead to a circular economy is remanufacturing. As a result, at the end-of-life stage of a product, it is critical to prioritize this choice over other accessible options because it is the only recovery option that retains the same quality as a new product. This work focuses on the numerous technologies that can aid in the improvement of smart …

Sensing Small Interaction Forces Through Proprioception, Fazlur Rashid, Devin Michael Burns, Yun Seong Song

Psychological Science Faculty Research & Creative Works

Understanding the human motor control strategy during physical interaction tasks is crucial for developing future robots for physical human-robot interaction (pHRI). In physical human-human interaction (pHHI), small interaction forces are known to convey their intent between the partners for effective motor communication. The aim of this work is to investigate what affects the human's sensitivity to the externally applied interaction forces. The hypothesis is that one way the small interaction forces are sensed is through the movement of the arm and the resulting proprioceptive signals. A pHRI setup was used to provide small interaction forces to the hand of seated …

Reducing Kidney Discard With Artificial Intelligence Decision Support: The Need For A Transdisciplinary Systems Approach, Richard Threlkeld, Lirim Ashiku, Casey I. Canfield, Daniel Burton Shank, Mark A. Schnitzler, Krista L. Lentine, David A. Axelrod, Anil Choudary Reddy Battineni, Henry Randall, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

Purpose of Review: A transdisciplinary systems approach to the design of an artificial intelligence (AI) decision support system can more effectively address the limitations of AI systems. By incorporating stakeholder input early in the process, the final product is more likely to improve decision-making and effectively reduce kidney discard.

Recent Findings: Kidney discard is a complex problem that will require increased coordination between transplant stakeholders. An AI decision support system has significant potential, but there are challenges associated with overfitting, poor explainability, and inadequate trust. A transdisciplinary approach provides a holistic perspective that incorporates expertise from engineering, social science, and …

Findings Report: Virtual Workshop On ‘Resilient Supply Of Critical Minerals’, Marek Locmelis, Angela D. Lueking, Michael S. Moats, Kwame Awuah-Offei, Lana Z. Alagha, Mark W. Fitch, Alanna Krolikowski, Shelby Clark

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

Executive Summary
On August 2-3, 2021, the Thomas J. O’Keefe Institute for Sustainable Supply of Strategic Minerals at Missouri University of Science and Technology (Missouri S&T) hosted the NSF-funded virtual workshop ‘Resilient Supply of Critical Minerals’. The workshop was convened via Zoom and attracted 158 registrants, including 108 registrants from academia (61 students), 30 registrants from government agencies, and 20 registrants from the private sector. Four topical sessions were covered:

A. Mineral Exploration and Source Diversification.
B. Supply Chain and Policy Issues.
C. Improving Mineral Recycling and Reprocessing Technologies.
D. Technological Alternatives to Critical Minerals.

Each topical session was composed …

The Implementation Of Energy Sharing Using A System Of Systems Approach, Julia Morgan

Doctoral Dissertations

"There is an increasing demand for renewable energy and consumers need more procurement options to meet their needs. Energy sharing provides a peer-to-peer (P2P) marketplace where prosumer electricity is redistributed to fellow energy-sharing community participants. This redistribution of prosumer electricity provides consumers with additional electricity suppliers, while also decreasing the load on the utility company. Though significant progress has been made regarding research and implementation of energy sharing, there is still room for growth when evaluating energy-sharing communities and defining appropriate community coordination based on end-user needs. The first contribution in this work identified nine characteristics of energy-sharing communities as …

Agent-Based Model Of Broadband Adoption In Unserved And Underserved Areas, Ankit Agarwal

Masters Theses

"In the last two decades, demand for broadband internet has far outpaced its availability. The Federal Communications Commission’s (FCC) 2020 Broadband Deployment report suggests that at least 22 million Americans living in rural areas lack access to broadband internet. With the COVID-19 pandemic affecting normal life, there is an overwhelming need to enable unserved and underserved communities to adapt to the “new normal”. To address this challenge, federal and state agencies are funding internet service providers (ISPs) to deploy infrastructure in rural communities. However, policymakers and ISPs need open-source tools to predict take-rates of broadband service and formulate effective strategies …

Gis And Remote Sensing Groundwater Potentiality Investigation Of Gulu District, Uganda Using Synthetic Aperture Radar And Magnetic Geophysics, Rachel Ann Jones

Doctoral Dissertations

“Developing countries have few resources for ground-based hydrological investigations to determine optimal placement of boreholes for community water access. Remote sensing data are available at a variety of resolutions and sense different parameters, and are useful inputs for hydrologic models, but these data are rarely obtainable in developing countries with the parameters or resolutions necessary for hydrologic applications. This research seeks to use and improve existing remote sensing and GIS techniques to identify areas of optimal water supply in locations with limited geologic or hydrologic information, such as Gulu District, Uganda. Fusing different remotely sensed data sets can produce higher …

Infrastructure Systems Modeling Using Data Visualization And Trend Extraction, Jacob Marshal Hale

Doctoral Dissertations

“Current infrastructure systems modeling literature lacks frameworks that integrate data visualization and trend extraction needed for complex systems decision making and planning. Critical infrastructures such as transportation and energy systems contain interdependencies that cannot be properly characterized without considering data visualization and trend extraction.

This dissertation presents two case analyses to showcase the effectiveness and improvements that can be made using these techniques. Case one examines flood management and mitigation of disruption impacts using geospatial characteristics as part of data visualization. Case two incorporates trend analysis and sustainability assessment into energy portfolio transitions.

Four distinct contributions are made in this …

A Markov Chain Approach For Forecasting Progression Of Opioid Addiction, Abhijit Gosavi, Susan L. Murray, N. Karagiannis

Engineering Management and Systems Engineering Faculty Research & Creative Works

The U.S. is currently facing an opioid crisis. Naltrexone is a common treatment for drug addiction; it reduces the desire to take opiates. However, addicts often stop treatment or continue to use opioids while in treatment. This results in increased fatalities and associated costs. A Markov-chain model is presented to analyze the progression of opioid addiction to assist the medical community in developing appropriate treatments. The model includes patients who continue opiate use while on naltrexone (blocked patients) and those who use opiates after missing naltrexone doses (unblocked patients). The other types of patients are abstinent (the best-case scenario) and …

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 …

Framing Energy And Minerals For Future Pathways, Michelle Michot Foss, Michael S. Moats, Kwame Awuah-Offei

Materials Science and Engineering Faculty Research & Creative Works

We present a challenge for Group of Twenty (G20) discussions that entails (1) greater awareness of the role of non-fuel minerals in the global economy overall, but specifically in the energy sector; and (2) the introduction and acceleration of alternative energy sources and technologies. We focus on chemical battery energy storage, given its prominence in all views and outlooks of energy futures, especially for mobility. We present recommendations for G20 discussions and actions on battery materials, and the crucial underlying supply chains for mineral commodities.

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 …

Trunk Velocity-Dependent Light Touch Reduces Postural Sway During Standing, Anirudh Saini, Devin Michael Burns, Darian Emmett, Yun Seong Song

Psychological Science Faculty Research & Creative Works

Light Touch (LT) has been shown to reduce postural sway in a wide range of populations. While LT is believed to provide additional sensory information for balance modulation, the nature of this information and its specific effect on balance are yet unclear. In order to better understand LT and to potentially harness its advantages for a practical balance aid, we investigated the effect of LT as provided by a haptic robot. Postural sway during standing balance was reduced when the LT force (~ 1 N) applied to the high back area was dependent on the trunk velocity. Additional information on …

Notes On The Economics Of Residential Hybrid Energy System, Mahelet G. Fikru, Gregory M. Gelles, Ana M. Ichim, Joseph D. Smith

Economics Faculty Research & Creative Works

Despite advances in small-scale hybrid renewable energy technologies, there are limited economic frameworks that model the different decisions made by a residential hybrid system owner. We present a comprehensive review of studies that examine the techno-economic feasibility of small-scale hybrid energy systems, and we find that the most common approach is to compare the annualized life-time costs to the expected energy output and choose the system with the lowest cost per output. While practical, this type of benefit—cost analysis misses out on other production and consumption decisions that are simultaneously made when adopting a hybrid energy system. In this paper, …

A Systems And Cost Analysis Of Human Rated Mars Entry, Descent, And Landing Vehicles, Paul Daniel Friz

Doctoral Dissertations

"Cost is one of the biggest obstacles to sending humans to Mars. However, spacecraft costs are typically not taken into consideration until after the preliminary vehicle and mission concepts have been designed. Once costs have been estimated, managers and project teams often lack confidence that the final cost of the mission will match the preliminary estimates. The present work provides a robust methodology for using cost as a valid metric early in the design phase of future human Mars Entry, Descent, and Landing (EDL) vehicles. This is done in three parts. First, state of the art parametric costing methods are …

Less Is More: Beating The Market With Recurrent Reinforcement Learning, Louis Kurt Bernhard Steinmeister

Masters Theses

"Multiple recurrent reinforcement learners were implemented to make trading decisions based on real and freely available macro-economic data. The learning algorithm and different reinforcement functions (the Differential Sharpe Ratio, Differential Downside Deviation Ratio and Returns) were revised and the performances were compared while transaction costs were taken into account. (This is important for practical implementations even though many publications ignore this consideration.) It was assumed that the traders make long-short decisions in the S&P500 with complementary 3-month treasury bill investments. Leveraged positions in the S&P500 were disallowed. Notably, the Differential Sharpe Ratio and the Differential Downside Deviation Ratio are risk …

The Behavior Of Suas Under Explosive Loading Conditions And Implications For Safe Operating Procedures, Ashok Em Sudhakar

Doctoral Dissertations

"Drones are increasingly being used for tasks previously unimagined and the beneficial uses are evolving. The United States Congress has envisioned the possible uses of drones for both combating and conveying explosive threats and other harmful and destructive activities. Congress' intent is reflected in new laws (2018) and policies (2019).

All civilian available Small Unmanned Aerial Systems sUASs (Drones), weighing less than 55 pounds, in the current market are not designed for operations in explosive environments. This first of a kind research focuses on further understanding of sUASs response to explosive loading and the public policy implications. This research measured …

Military Applications Of Geological Engineering, Stephen H. Tupper

Doctoral Dissertations

"This work examines the premise that military engineering and geological engineering are intellectually paired and overlapped in practice to a significant extent. Geological engineering is an established, albeit young, academic discipline that enjoys wide industry and civil demand and is supported by many professional organizations. In contrast, military engineering is an ancient, empirically derived training or "OJT" program with practice-based trade-associations that has narrow government-only utility. The premise is formed by decades-long observation of U. S. Army military engineer officers completing a Master of Science degree in geological engineering as a complement to their practice-based training in military engineering at …

Extending Time Series Forecasting Methods Using Functional Principal Components Analysis, Isaac Michael Wagner-Muns

Masters Theses

"Traffic volume forecasts are used by many transportation analysis and management systems to better characterize and react to fluctuating traffic patterns. Most current forecasting methods do not take advantage of the underlying functional characteristics of the time series to make predictions. This paper presents a methodology that uses Functional Principal Components Analysis (FPCA) to create smooth and differentiable daily traffic forecasts. The methodology is validated with a data set of 1,813 days of 15 minute aggregated traffic volume time series. Both the FPCA based forecasts and the associated prediction intervals outperform traditional Seasonal Autoregressive Integrated Moving Average (SARIMA) based methods"--Abstract, …

Development Of A Variogram Approach To Spatial Outlier Detection Using A Supplemental Digital Elevation Model Dataset, Zane Daniel Helwig

Masters Theses

"When developing a ground water model, the quality of the dataset should first be evaluated. Spatial outliers can lead to predictions which are not representative of actual conditions. In order to isolate misrepresentative points, a method is presented which examines the experimental variogram of a ground water elevation dataset. To define a threshold variance between pairs of ground water elevation measures, ground elevation values from a digital elevation model (DEM) are used to determine a maximum reasonable variance expected to occur on the experimental variogram. To determine appropriate DEM parameters, a separate study was also done which observed characteristic behavior …

Specialist Communities In China’S Aerospace Technology And Innovation System: The Cultural Dimension, Alanna Krolikowski

History and Political Science Faculty Research & Creative Works

Only two decades ago, China was a marginal player in the global aerospace industry. Today, the pace of China’s space programs is unparalleled and it has joined the sector’s leading ranks. China is the only country after the Soviet Union/Russia and the United States to independently send humans into orbit and a rover to touch down on the Moon. A Chinese station will likely soon be only the only long-term human habitat circling the Earth alongside the International Space Station. Within a decade, China could become only the second country in history to land a person on the Moon’s surface. …

Cognition-Based Approaches For High-Precision Text Mining, George John Shannon

Doctoral Dissertations

"This research improves the precision of information extraction from free-form text via the use of cognitive-based approaches to natural language processing (NLP). Cognitive-based approaches are an important, and relatively new, area of research in NLP and search, as well as linguistics. Cognitive approaches enable significant improvements in both the breadth and depth of knowledge extracted from text. This research has made contributions in the areas of a cognitive approach to automated concept recognition in.

Cognitive approaches to search, also called concept-based search, have been shown to improve search precision. Given the tremendous amount of electronic text generated in our digital …

Managing Risks Of Market Price Uncertainty For A Microgrid Operation, Sriram Raghavan

Masters Theses

"After deregulation of electricity in the United States, the day-ahead and real-time markets allow load serving entities and generation companies to bid and purchase/sell energy under the supervision of the independent system operator (ISO). The electricity market prices are inherently uncertain, and can be highly volatile. The main objective of this thesis is to hedge against the risk from the uncertainty of the market prices when purchasing/selling energy from/to the market. The energy manager can also schedule distributed generators (DGs) and storage of the microgrid to meet the demand, in addition to energy transactions from the market. The risk measure …