Engineering Commons^™

Comparing Human Text Classification Performance And Explainability With Large Language And Machine Learning Models Using Eye-Tracking, Jeevithashree Divya Venkatesh, Aparajita Jaiswal, Gaurav Nanda

Purdue University Libraries Open Access Publishing Fund

To understand the alignment between reasonings of humans and artificial intelligence (AI) models, this empirical study compared the human text classification performance and explainability with a traditional machine learning (ML) model and large language model (LLM). A domain-specific noisy textual dataset of 204 injury narratives had to be classified into 6 cause-of-injury codes. The narratives varied in terms of complexity and ease of categorization based on the distinctive nature of cause-of-injury code. The user study involved 51 participants whose eye-tracking data was recorded while they performed the text classification task. While the ML model was trained on 120,000 pre-labelled injury …

Cellular Energy Cycle Mediates An Advection-Like Forward Cell Flow To Support Collective Invasion, Jian Zhang, Jenna Mosier, Yusheng Wu, Logan Waddle, Paul V. Taufelele, Wenjun Wang, Heng Sun, Cynthia A. Reinhart-King

Biomedical Engineering Faculty Publications and Presentations

Collective cell migration is a model for nonequilibrium biological dynamics, which is important for morphogenesis, pattern formation, and cancer metastasis. The current understanding of cellular collective dynamics is based primarily on cells moving within a 2D epithelial monolayer. However, solid tumors often invade surrounding tissues in the form of a stream-like 3D structure, and how biophysical cues are integrated at the cellular level to give rise to this collective streaming remains unclear. Here, it is shown that cell cycle-mediated bioenergetics drive a forward advective flow of cells and energy to the front to support 3D collective invasion. The cell division …

Study On The Tribological Properties Of Din 16mncr5 Steel After Duplex Gas-Nitriding And Pack Boriding, Rafael Carrera Espinoza, Melvyn Alvarez-Vera, Marc Wettlaufer, Manuel Kerl, Stefan Barth, Pablo Moreno Garibaldi, Juan Carlos Díaz Guillen, Héctor Manuel Hernández García, Rita Muñoz Arroyo, Javier A. Ortega

Mechanical Engineering Faculty Publications

DIN 16MnCr5 is commonly used in mechanical engineering contact applications such as gears, joint parts, shafts, gear wheels, camshafts, bolts, pins, and cardan joints, among others. This study examined the microstructural and mechanical properties and tribological behavior of different surface treatments applied to DIN 16MnCr5 steel. The samples were hardened at 870 °C for 15 min and then quenched in water. The surface conditions evaluated were as follows: quenched and tempered DIN 16MnCr5 steel samples without surface treatments (control group), quenched and tempered DIN 16MnCr5 steel samples with gas-nitriding at 560 °C for 6 h, quenched and tempered DIN 16MnCr5 …

Rotational Rheometry Test Of Portland Cement-Based Materials – A Systematic Literature Review, Laura Silvestro, Artur Spat Ruviaro, Geannina Lima, Luís Urbano Durlo Tambara Júnior, Dimitri Feys, Ana Paula Kirchheim

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

This Study Systematically Reviews 62 Papers on the Use of Rotational Rheometry to Assess the Fresh State Behavior of Portland Cement-Based Materials. the Research Highlights the Wide Variation in Test Methods and Aims to Provide a Comprehensive overview. Findings Reveal that 50.0% of Studies Employed Vane Geometry, despite its Limitations in Providing Transformation Equations. Regarding Dynamic Shearing Tests, 67.0% Followed a Consensus using a Pre-Shearing Step and a Stepwise Routine with Stabilization Times ≥ 10 S. While the Bingham Model is Commonly Used, the Study Emphasizes the Importance of Considering Shear-Thinning Behavior in Cementitious Materials. Models Like Herschel-Bulkley and Modified …

Cognitive Manufacturing: Definition And Current Trends, Fadi El Kalach, Ibrahim Yousif, Thorsten Wuest, Amit Sheth, Ramy Harik

Publications

Manufacturing systems have recently witnessed a shift from the widely adopted automated systems seen throughout industry. The evolution of Industry 4.0 or Smart Manufacturing has led to the introduction of more autonomous systems focused on fault tolerant and customized production. These systems are required to utilize multimodal data such as machine status, sensory data, and domain knowledge for complex decision making processes. This level of intelligence can allow manufacturing systems to keep up with the ever-changing markets and intricate supply chain. Current manufacturing lines lack these capabilities and fall short of utilizing all generated data. This paper delves into the …

Enhancing Contractor Selection Through Fuzzy Topsis And Fuzzy Saw Techniques, Mohammadsoroush Tafazzoli, Ayoub Hazrati, Kishor Shrestha, Krishna Kisi

Civil Engineering & Construction: Faculty Publications

Contractors play an integral role in construction projects, and their qualifications directly impact various aspects of a project’s success. The unbiased selection of contractors is a challenge in the construction industry worldwide, particularly in public projects where impartiality in the final selection is essential. Numerous factors must be considered when evaluating contractors, making the selection process challenging for the human brain. This paper introduces and compares two methods for assessing contractor prequalification by applying the fuzzy theory. The idea is to facilitate using human judgments in a mathematical system for decision-making with regard to selecting contractors. The method is based …

Stretching The Limits Of Mri—Stretchable And Modular Coil Array Using Conductive Thread Technology, Folk W. Narongrit, Thejas Vishnu Ramesh, Joseph V. Rispoli

Purdue University Libraries Open Access Publishing Fund

Objective: We propose a modular stretchable coil design using conductive threads and commercially available embroidery machines. The coil design increases customizability of coil arrays for individual patients and each body part. Methods: Eight rectangular coils were constructed with custom-fabricated stretchable tinsel copper threads incorporated onto textile. Tune, match, and detune circuits were incorporated on the coil. A hook-and-loop mechanism was used to attach and decouple the modular coils. Phantom and in vivo scans at various anatomical flexion angles were acquired to highlight performance, and a temperature test was performed to verify safety. Results: In vivo MRI experiments demonstrate high sensitivity …

Exploring Differences In Perceived Learning For Students In Online Versus Face-To-Face Collegiate Pilot Ground Schools: A Quantitative Causal-Comparative Study, Christopher Komsa

Doctoral Dissertations and Projects

The purpose of this quantitative, causal-comparative study was to determine if there was a difference in the perceived learning of students completing online versus face-to-face collegiate pilot ground schools. Higher education institutions with pilot training programs are highly invested in student success and Federal Aviation Administration (FAA) compliance. A growing number of students are taking online courses in college, and this shift was accelerated by the COVID-19 pandemic. Perceived learning was quantified using a web-based survey that collected perceived learning data as measured by the Cognitive, Affective, and Psychomotor (CAP) Perceived Learning Scale. A sample of 86 students at University …

Water Quality Impacts Of Recycling Nutrients Using Organic Fertilizers In Circular Agricultural Scenarios, W. Lisenbee, A. Saha, P. Mohammadpour, R. Cibin, Jason Philip Kaye, C. Grady, Indrajeet Chaubey

Biological and Agricultural Engineering Faculty Publications and Presentations

CONTEXT

OBJECTIVE

METHODS

Turbine Cooling System With Energy Separation, James L. Rutledge, Matthew N. Fuqua, Carol M. Bryant

AFIT Patents

A method and system for cooling an engine and/or vehicle using energy separation is disclosed herein. An energy separation device is operable for separating a compressed gaseous coolant stream into a first relatively cooler coolant flow stream and a second relatively hotter coolant flow stream. The relative cooler coolant flow stream is directed to a first region requiring increased cooling and the relative hotter coolant flow stream is directed to a second region requiring lower cooling than the first region in the engine or vehicle.

Extreme Value Statistics Analysis Of Process Defects In Additive Manufacturing Materials, Ayorinde E. Olatunde, Kristen Hernandez, Austin Ngo, Arafath Nihar, Thomas G. Ciardi, Rachel Yamamoto, Pawan K. Tripathi, Roger H. French, John J. Lewandowski, Anirban Mondal

Faculty Scholarship

Fatigue and fracture studies focused on process defects that occur in Additive Manufacturing (AM) materials have shown that defect populations possess features which are better measured with extreme value statistics (EVS). In AM alloys, defect occurrences increase with material volume. This situation facilitates the need to model process defects in the path of fatigue crack growth with suitable statistical tools, such as EVS, which is more cost-effective when compared to destructive experiments. The application of EVS on defect space features helps determine the difference in defects present on fracture surfaces. As the fatigue quality of any material depends on its …

Spectral Behavior Of Fiber Bragg Gratings During Embedding In 3d-Printed Metal Tensile Coupons And Cyclic Loading, Farid Ahmed, Md Shahriar Forhad, Mahmudul Hasan Porag

Manufacturing & Industrial Engineering Faculty Publications

Additive manufacturing (AM) enables the spatially configurable 3D integration of sensors in metal components to realize smart materials and structures. Outstanding sensing capabilities and size compatibility have made fiber optic sensors excellent candidates for integration in AM components. In this study, fiber Bragg grating (FBG) sensors were embedded in Inconel 718 tensile coupons printed using laser powder bed fusion AM. On-axis (fiber runs through the coupon’s center of axis) and off-axis (fiber is at 5° and 10° to the coupon’s center of axis) sensors were buried in epoxy resin inside narrow channels that run through the coupons. FBGs’ spectral evolutions …

Enhancing Urban Parking Efficiency Through Machine Learning Model Integration, Sai Sneha Channamallu, Sharareh Kermanshachi, Jay Michael Rosenberger, Apurva Pamidimukkala

Open Initiatives Grant Funded Publications-Archive

An increase in vehicular traffic and a scarcity of parking spaces are creating significant challenges for urban parking management. This study aims to tackle these issues that escalate congestion and pollution and decrease urban productivity, by utilizing machine learning models to accurately predict parking space availability and categorize occupancy levels. It employs a dataset from a college campus garage collected from January 2022 to June 2023 and analyzes the performance of random forest, decision tree, linear regression, and support vector models by comparing them, using multiple evaluation metrics. The results revealed that the random forest model was the most reliable, …

Refining Transversal Skills Through Engineering Design Projects: A Case For Authentic Assessment, Gerald Gallagher, Kevin Delaney, David Salter, Mingzhu Chen

Conference Papers

Transversal skills were typically not the focus of traditional engineering education, where strong technical prowess by students tended to be emphasised in undergraduate and postgraduate study. However, the importance of developing these skills, having application across multiple career trajectories, is becoming a key area of development in engineering education. An engineering design module presented in this work has been refined to act as a vehicle to help students develop and practice these transversal skills while simultaneously reinforcing their abilities in mechanical design. This paper describes how the module has been structured and operationalised, through approximations of practice and authentic assessment, …

Editorial: Mitral Valve Disease: Mechanisms To Therapies, Maria Carmo Nunes, Hoda Hatoum, Alison M. Pouch, Muralidhar Padala

Michigan Tech Publications

No abstract provided.

Detection Of Wintertime Green Vegetated Cover Using Object-Based Classification With Open-Source Remote Sensing And Geospatial Technologies, Jae Sung Kim, Sara P. Syswerda, Sigrid D. P. Smith

Michigan Tech Publications

It is important to detect wintertime green vegetated cover (WGVC), since it includes cover crop information, which is one of the most important agricultural best management practices used today. Related to this, cover crop area, which is part of WGVC, has been estimated using survey methods traditionally, but remote sensing can be used as a more time- and cost-effective assessment. Previously developed pixel-based methods to assess cover crops using remote sensing can have a salt-and-pepper effect, which lowers classification accuracy. Therefore, object-based classification was applied to estimate the spatial distribution of WGVC across the entire state of Delaware. To reduce …

A Country-Level Primary-Final-Useful (Cl-Pfu) Energy And Exergy Database: Overview Of Its Construction And 1971–2020 World-Level Efficiency Results, Paul E. Brockway, Matthew Kuperus Heun, Zeke Marshall, Emmanuel Aramendia, Paul Steenwyk, Thomas Relph, Michelle Widjanarko, Jeonghoo (James) Kim, Anjana Sainju, Julian Irtube

University Faculty Publications and Creative Works

Societal exergy analysis examines the flows of energy and exergy through societies, from primary (e.g. oil) to final (e.g. gasoline) to useful (e.g. propulsion) energy stages. By extending the study of energy to the useful stage, new insights into the under-represented role of energy in economic growth have been made. However, currently (a) country coverage is patchy and incomplete, (b) available data are based on varying methods and assumptions including efficiencies based on economic rather than engineering data, and (c) datasets are constructed using piecemeal computational approaches. To address these gaps, we construct a country-level primary-final-useful (CL-PFU) energy and exergy …

Direct Evaporative Cooling For Sustainability And Environmental Conservation, Iman El-Mahallawi, Hesham Safwat, Mahmoud Elsayed, Mahmoud Alghrieb

Mechanical Engineering

This work presents the results of experimental work on cellulose cooling pads with honeycomb structure to study their evaporative cooling effect which is one of the partial solutions for achieving the SDG goals 2030. The paper outlines various types of evaporative cooling materials, highlighting their distinctions and potential applications. Furthermore, it offers a comparative analysis of the cooling effects between wide hole and narrow hole cellulose cooling pads, both individually and in combination. The experimental setup results are thoroughly examined to provide insights into the performance of the cooling pads. Results showed up that direct evaporative cooling have a significant …

New Generation Graphenes In Cement-Based Materials: Production, Property Enhancement, And Life Cycle Analysis, Sahil Surehali, Sayee Srikarah Volaity, Aswathy Simon, Ranjith Divigalpitiya, Aditya Kumar, Narayanan Neithalath

Materials Science and Engineering Faculty Research & Creative Works

Several studies have explored the use of graphene to improve the properties of cement-based materials. However, most commercially available graphenes are expensive, not amenable to mass production, and have high embodied energy and emissions, making their use in concrete less attractive, despite the beneficial mechanical property attributes. This paper discusses the use of two novel graphene types, fractal graphene (FG) and reactive graphene (RG), obtained through a cost-effective and scalable detonation synthesis, in cement-based materials. FG and RG are sheets containing 6-10 layers, with lateral dimensions of 20-50 nm and a z-axis thickness of RG, when added at very small …

Aging-Related Changes In The Mechanical Properties Of Single Cells, Amarnath Singam, Chandrabali Bhattacharya, Seungman Park

Mechanical Engineering Faculty Research

Mechanical properties, along with biochemical and molecular properties, play crucial roles in governing cellular function and homeostasis. Cellular mechanics are influenced by various factors, including physiological and pathological states, making them potential biomarkers for diseases and aging. While several methods such as AFM, particle-tracking microrheology, optical tweezers/stretching, magnetic tweezers/twisting cytometry, microfluidics, and micropipette aspiration have been widely utilized to measure the mechanical properties of single cells, our understanding of how aging affects these properties remains limited. To fill this knowledge gap, we provide a brief overview of the commonly used methods to measure single-cell mechanical properties. We then delve into …

Atom Probe Tomography Of Segregation At Grain Boundaries And Gas Bubbles In Neutron Irradiated U-10 Wt% Mo Fuel, Maalavan Arivu, Andrew Hoffman, Mukesh Bachhav, Assel Aitkaliyeva, Yaqiao Wu, Brandon Miller, Dennis Keiser, Jian Gan, Haiming Wen

Materials Science and Engineering Faculty Research & Creative Works

During Neutron Irradiation to Fission Densities > 5.2 X 1021 Fiss/cm3, Xe Agglomerates Forming Gas Bubbles of Varying Size within the U-Mo Fuel Matrix. Herein, Segregation of Fission Products to Xe Bubbles and Grain Boundaries (GB) Were Studied using Atom Probe Tomography (APT). Segregation Behavior Was Found to Vary among GBs, Small Bubbles (<10 >Nm), and Larger Bubbles (>10 Nm). Solid Fission Products Were Enriched at GBs and Larger Bubbles, But Not at Small Bubbles. a Denuded Zone Was Identified Adjacent to a > 10 Nm Xe Gas Bubble and a GB.

Design, Prototyping, And Characterization Of A Micro-Force Sensor Intended For Tissue Assessment In Confined Spaces, Shashank S. Kumat, Panos S. Shiakolas

Open Initiatives Grant Funded Publications-Archive

The quantitative characterization of soft tissue viscoelastic properties can aid in disease prognosis and diagnosis. Existing technologies present challenges to measuring localized in vivo tissue relaxation data while meeting load and geometric constraints. This research presents the design, prototype, and characterization of a micro-force sensor that could enable better access to confined spaces of the human body. The novel design of the uniaxial micro-force sensor has an external diameter of less than or equal to 3.5 mm and 1 N load capacity for transurethral palpation of the bladder interior wall. The conceptual design of the micro-force sensor and a finite …

Optimization Using Central Composite Design For Continuous Absorption Of Co2 Gas With Green Sodium Silicate In A Packed Bed Column, Dalia A. Ali Eng, Mohamed Essam Ibrahim Eng.

Chemical Engineering

If absolutely nothing is taken to reduce carbon dioxide (CO2) emissions, atmospheric concentrations of carbon dioxide will rise to 550 parts per million by 2050, which will have disastrous effects on the world's climate and food production. An apparatus has been designed and setup to convert CO2 into a useful and vital product which was silica. The effect of different experimental factors on the compositions by weight percent of SiO2 and Na2CO3 were studied including the CO2 gas flow rate (1.037, 1.648 and 2.26 L/min), initial concentration of sodium silicate (Na2SiO3) solution (5, 7.5 and 10 %wt) and the packing …

Evaluation Of Insurance Policies In The Saudi Arabian Construction Contracts, Ahmed Gouda Mohamed

Civil Engineering

The construction sector is more complicated and prone to risk than many other industries due to the size of the projects and the financial capital involved. Arranging insurance is the prudent course of action for risk management in the construction sector. There is a lack of clarity in insurance policies for public construction projects in the Kingdom of Saudi Arabia (KSA), which poses additional risks to all involved contracting parties. The aim of this research is to evaluate insurance policies in the KSA's public construction projects to identify the key deficiencies and obstacles and provide a road map for improvement …

Sensitization Of Europium Oxide Nanoparticles Enhances Signal-To- Noise Over Autofluorescence With Time-Gated Luminescence Detection, Hunter Miller, Jessica Q. Wallace, Hui Li, Xing-Zhong Li, Ana De Bettencourt-Dias, Forrest Kievit

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Clinical translation of nanoparticle-based therapeutics has been limited, and a lack of preclinical delivery characterization is partly to blame, limiting our understanding of the mechanisms of failure. The improvement of the preclinical delivery assessment requires nanoparticles with higher detectability. This work focused on the exploration of several aromatic carboxylic ligands (terephthalic acid, quinaldic acid, and kynurenic acid) for the sensitization of europium oxide nanoparticles with a long emission lifetime to overcome cellular autofluorescence, a key confounder of detection in luminescence-based bioimaging. A facile one-pot synthesis and ligand exchange process generated and sensitized ultrasmall Eu₂O₃ cores. As reflected …

Kernel Ridge Regression In Predicting Railway Crossing Accidents, Ethan Villalobos, Constantine Tarawneh, Jia Chen, Evangelos E. Papalexakis, Ping Xu

Mechanical Engineering Faculty Publications

Expanding on the insights from our initial investigation into railway accident patterns, this paper delves deeper into the predictive capabilities of machine learning to forecast potential accident trends in railway crossings. Focusing on critical factors such as “Highway User Position” and “Equipment Involved,” we integrate Kernel Ridge Regression (KRR) models tailored to distinct clusters, as well as a global model for the entire dataset. These models, trained on historical data, discern patterns and correlations that might elude traditional statistical methods. Our findings are compelling: certain clusters, despite limited data points, showcase remarkably Root Mean Squared Error (RMSE) values between predictions …

Spectral Clustering In Railway Crossing Accidents Analysis, Ethan Villalobos, Hector Lugo Iii, Biqian Cheng, Miguel Gutierrez, Constantine Tarawneh, Ping Xu, Jia Chen, Evangelos E. Papalexakis

Mechanical Engineering Faculty Publications

This study employs graph mining and spectral clustering to analyze patterns in railway crossing accidents, utilizing a comprehensive dataset from the US Department of Transportation. By constructing a graph of implicit relationships between railway companies based on shared accident localities, we apply spectral clustering to identify distinct clusters of companies with similar accident patterns. This offers nuanced insight into the underlying structure of these incidents. Our results indicate that “Highway User Position” and “Equipment Involved” play pivotal roles in accident clustering, while temporal elements like “Date” and “Time” exert a diminished impact. This research not only sheds light on potential …

Development Of Rail Anchor Testing Through Literature Review Of Cwr Buckling Resistance Evaluation, Juan Rodriguez, Siang Zhou, Constantine Tarawneh, Alberto Sanchez, Teresa Salazar-Flores, S. Mustapha Rahmaninezhad, Hameem Gorabi

Mechanical Engineering Faculty Publications

Continuously welded rail (CWR) is among the most used railroad systems worldwide with great improvements compared to jointed tracks, including refined ride quality, increased fatigue life of track and rolling stock, and reduced maintenance costs. Rail buckling is one of the key remaining issues for CWRs to further reduce safety hazards and infrastructure deterioration, and save required track retrofit material and efforts. CWR buckling is induced by combined longitudinal, lateral, and torsional forces on the track that are caused by the synergy of rail components, the loading from moving trains, the interaction between track and substructure, and the effect of …

Department Chairs As Change Agents: A Virtual Cross-Institutional Professional Development Model For Chairs, Cinzia Cervato, Stephanie Peterson, Carrie Ann Johnson, Canan Bilen-Green, Carla Koretsky, Adrienne Minerick, Gul Okudan Kremer

Michigan Tech Publications

Department chairs are crucial in impacting departmental climate, conveying expectations, and providing merit assessments. Therefore, they have the most influence in retaining highly qualified faculty. Most department chairs come from the faculty ranks and lack formal training in key management, communication, and administrative skills, including performance reviews, resource allocation and budgeting, legal and compliance issues, promotion and tenure determinations, conflict resolution, and the inclusive management of people with diverse identities. Recognizing the critical role of department chairs and the evident gap in their training, we developed a series of chair workshops to provide ongoing professional development for department chairs across …

Experimental Investigation Of Lateral Load Effects On Railway Tapered Roller Bearing Performance, Abel David Sanchez Trinidad, Constantine Tarawneh, Diego Aguila, Arturo A. Fuentes, Santanna Guiterrez, Curtis Pena, Daniel Reyna

Mechanical Engineering Faculty Publications

In the quest to maintain the reliability and safety of railway systems, vibration signatures emerge as a crucial diagnostic tool for identifying and tracking the progression of railway bearing health. It is important to note that, in the case of spall deterioration, temperature variations may only become noticeable once spalling has spread extensively across the raceway. Hence, a comprehensive understanding of the effects of lateral loading under various train speeds at empty and full railcar loads is important. Surprisingly, limited research has been carried out or made publicly available on the effects of lateral loading on the performance of railroad …