Engineering Commons^™

Centralized Deep Reinforcement Learning For Homogeneous Multi-Component Maintenance Optimization, Joseph W. Wittrock

Theses and Dissertations

This thesis explores an application of reinforcement learning (RL) in maintenance optimization. Recent advances in hardware-accelerated computation and deep learning have made RL a powerful tool for solving optimization problems which are too complex for traditional methods. Maintenance optimization involves improving the efficiency and effectiveness of maintenance activities through data-driven approaches, ultimately reducing costs and increasing asset availability. Making informed maintenance decisions is crucial to long-term sustainability.

A desirable maintenance policy maximizes a utility signal while minimizing the cost of maintenance. Techniques in sequential decision making such as dynamic programming (DP) and RL have found success in optimizing these maintenance …

Private Property Vs. Public Access: Socio-Engineering Framework For Managing Non-Meandering Waters In South Dakota’S Prairie Pothole Region, Lydia Loken, Sushant Mehan

The Journal of Undergraduate Research

This study addresses the growing importance of balancing private ownership and public interest of Non-Meandering Waters (NMWs) overlaying private property in the South Dakota Prairie Pothole Region (PPR) through both a legal and socio-engineering lens. This study aims to develop an integrated management framework for Non-Meandering Waters in the South Dakota Prairie Pothole Region that combines water allocation principles, the Public Trust Doctrine, and water quality objectives to guide policy decisions, ensuring equitable access, long-term sustainability, and a balanced approach to both public and private interests. Data collection from October 2024 through February 2025 and included a literature review of …

Hardware Implementation Of An Efficient Frequency Comb Generator For Microwave Kinetic Inductance Detectors, Frank Atobrah Danso

Open Access Master's Theses

The frequency comb generator is an essential component in the readout of superconducting detectors. This component is responsible for generating the resonant frequencies necessary to detect photon interaction with the detectors. This component however has not received the much needed attention in terms of readout systems optimization. Conventional implementations rely on either inverse fast Fourier transform (IFFT) engines, which scale poorly in power with increasing frequency resolution requirement but allow flexible tone updates, or lookup tables (LUTs), which demand large memory for high frequency resolution.

Microwave Kinetic Inductance Detectors (MKIDs) are superconducting detectors which have gained significant interest for cryogenic …

Temporal Machine Learning For Predicting Accidents And Violations In The Mining Industry, Nathan T. Kelley

Theses and Dissertations--Mining Engineering

This thesis examines the predictive capability of a temporal machine learning model for forecasting future accidents and violations at individual mines, based on historical data. Mine accidents were categorized by accident classification and violations were categorized by the Part Section. The primary datasets utilized were the mine safety and health administration’s (MSHA’s) Accident Injuries and Violations datasets. The available datasets were cleaned and organized by mine type and commodity, then divided into separate subsets for training, validating, and testing. Different models, cutoff metrics, learning rates, number of hidden layers, data processing methods, data processing divisions, number of points observed …

High-Altitude Balloon-Launched Uncrewed Aircraft System Measurements Of Atmospheric Turbulence And Qualitative Comparison With Infrasound Microphone Response, Anisa Haghighi

Theses and Dissertations--Mechanical and Aerospace Engineering

This study explores the use of a balloon-launched uncrewed aircraft system (UAS) to measure atmospheric turbulence in the troposphere and lower stratosphere using both wind velocity measurements and infrasonic acoustic energy. The UAS, a glider configured for autonomous descent along a predefined trajectory, had on board, in situ sensors to capture thermodynamic and kinematic atmospheric parameters. Additionally, it carried an infrasonic microphone to evaluate its potential for remotely detecting clear-air turbulence by capturing infrasonic waves. The system’s performance was assessed over the course of three test flights conducted in New Mexico, USA, in 2021. The descent enabled high-resolution profiling, with …

Integrating Sustainability Into Aviation Training: Perspectives From Industry Professionals, Eva Maleviti, Sarah Talley

Publications

This paper is part of a broader research project aimed at identifying the most appropriate training materials, formats, and delivery methods for aviation sustainability content for future aviation professionals, starting from the early stages of their training. The current paper presents the data analysis and results of a short online survey targeting aviation professionals. Specifically, it provides preliminary data on sustainability perspectives from global aviation professionals. Through qualitative analysis, the creation of a baseline from a random sample of aviation professionals offers insight into their perspectives and how they could be influenced toward a more sustainable pathway. Additionally, the paper …

Nebraska Test #2302: Claas Xerion 12.650 Terra Trac, Nebraska Tractor Test Lab

Nebraska Tractor Tests

ABOUT THE TEST REPORT AND USE OF THE DATA The test data contained in this report are a tabulation of the results of a series of tests. Due to the restricted format of these pages, only a limited amount of data and not all of the tractor specifications are included. The full OECD report contains usually about 30 pages of data and specifications. The test data were obtained for each tractor under similar conditions and therefore, provide a means of comparison of performance based on a limited set of reported data. EXPLANATION OF THE TEST PROCEDURES Purpose The purpose of …

Nebraska Test #2300: Claas Xerion 12.590 Terra Trac, Nebraska Tractor Test Lab

Nebraska Tractor Tests

ABOUT THE TEST REPORT AND USE OF THE DATA The test data contained in this report are a tabulation of the results of a series of tests. Due to the restricted format of these pages, only a limited amount of data and not all of the tractor specifications are included. The full OECD report contains usually about 30 pages of data and specifications. The test data were obtained for each tractor under similar conditions and therefore, provide a means of comparison of performance based on a limited set of reported data. EXPLANATION OF THE TEST PROCEDURES Purpose The purpose of …

Nebraska Test #2268: Case Ih Steiger 595, Nebraska Tractor Test Lab

Nebraska Tractor Tests

ABOUT THE TEST REPORT AND USE OF THE DATA The test data contained in this report are a tabulation of the results of a series of tests. Due to the restricted format of these pages, only a limited amount of data and not all of the tractor specifications are included. The full OECD report contains usually about 30 pages of data and specifications. The test data were obtained for each tractor under similar conditions and therefore, provide a means of comparison of performance based on a limited set of reported data. EXPLANATION OF THE TEST PROCEDURES Purpose The purpose of …

Horizontal Infiltration Of Water Through Porous Snow As A Gravity Current, Anthony Cheng

Dartmouth College Master’s Theses

On the surface of the Greenland ice sheet or around the margins of the Antarctic ice shelf, water infiltrates porous ice. It is important to understand this infiltration process since water populating the pore space of ice directly impacts the density, porosity, and wetness of ice. These properties influence the mechanics and tensile strength of ice, as greater amounts of infiltration result in faster or more widespread deformation events, which may lead to adverse climatic effects such as sea level rise and ocean current disruption. While studies have considered the thermodynamics and fluid mechanics of water vertically percolating through snow …

Time Series Forecasting With Lstm: An Extensive Content Analysis, Andri Pranolo, Xiaofeng Zhou, Yingchi Mao

Knowledge Engineering and Data Science

This paper presents a comprehensive bibliometric and content review of the trend, architecture, and application of long short-term memory (LSTM) models for time series forecasting. The study aims to provide insights into the overall statistics and distribution of papers focused on LSTM for forecasting. Additionally, the research questions address the most highly cited papers based on LSTM approaches in forecasting, the most productive journals in this field, and identifying trends, gaps, summary tasks and their performance, datasets availability, and future research directions for LSTM in forecasting. This paper is a comprehensive review of LSTM for forecasting from 2017 to 2023 …

Prediction Of Audit Findings Using Deep Learning With Financial And Non-Financial Data: A Case Study In Province X, Fery Yohan Setiawan, Eko Mulyanto Yuniarno, Reza Fuad Rachmadi

Knowledge Engineering and Data Science

The implementation of the audit from the local government financial statements by The Audit Board of The Republic of Indonesia (BPK RI), especially for the Province X representative, are frequently faced by the various limitations, one of them being the required audit time. At this moment, the BPK RI representative of Province X doesn’t have the tools that are able to help the accurate of sample determination for the pick test, which resulted in this study proposing the application of multi-label classification to predict the findings of financial statement (Laporan Keuangan, LK) audits based on financial and non …

A Comparative Study Of Machine Learning Models For Javanese Wuku Classification: Exploring Svm, Naïve Bayes, And Cnn For Cultural Texts, Danang Arbian Sulistyo, Aji Prasetya Wibawa, Didik Dwi Prasetya, Fadhli Almu'iini Ahda, Agung Bella Putra Utama

Knowledge Engineering and Data Science

This study rigorously evaluates machine learning models for classifying culturally significant Javanese Wuku texts from the “Keagamaan atau Spiritual” category, a domain challenged by unique linguistic nuances and limited digitized resources. We compared Support Vector Machine (SVM), Naïve Bayes, and Convolutional Neural Network (CNN) on texts from five pivotal Wuku types (Sinta, Galungan, Kuningan, Sungsang, Warigalit) sourced from sastra.org, aiming to identify the most effective computational approach. The dataset comprises N = 1419 documents (T = 751.290 tokens), with per-class document counts reported for all five Wuku types. Our evaluation uses accuracy, precision, recall, F1-score, and …

Mapping Of Product Sales Potential Based On Brands In The East Kalimantan Region Using Hybrid Analytical Framework, Achmad F O Gaffar Mr, Mulyanto Mulyanto Mr, Arief Bw Putra Mr, Muhammad Taufiq Sumadi Mr, Emmilya Umma Aziza Gaffar

Knowledge Engineering and Data Science

In geographically dispersed markets, operational costs should be reflected in sales planning to support accurate performance evaluation. However, such considerations are often neglected in practice. This study proposes a hybrid analytical framework to map brand-based product sales potential, with and without operational cost consideration, using historical sales data from PT Karya Inti Total Anugerah (PT KITA) in East Kalimantan. The framework integrates spatial, statistical, and machine learning techniques. Principal Component Analysis (PCA) is used to reduce the dimensionality of variables related to travel distance, total sales, and units sold, where travel distance represents the primary contributor to operational costs. K-Means …

Cognitive Eeg Differentiation With Hypnosis-Based Noise Reduction And K-Harmonic Means For Personalized Brainwave Modeling, Ahmad Azhari, Dimas Chaerul Ekty Saputra

Knowledge Engineering and Data Science

This study investigates the integration of hypnosis-based noise reduction and K-Harmonic Means (KHM) clustering for personalized brainwave modeling using Electroencephalography (EEG) data. EEG signals were collected from 100 participants using a Neurosky Mindset sensor at the FP1 (prefrontal) location, with each subject performing nine standardized cognitive tasks such as breathing, memory recall, and mathematical problem-solving. Hypnosis was applied not as a filtering method but as a behavioral protocol to standardize subject conditions and minimize physiological and environmental noise. The EEG signals were sampled at 128 Hz and analyzed using KHM clustering with K=4K = 4K=4, resulting in a Silhouette Score …

Ahp–Python Framework For Multicriteria Modeling Of Rice Production In Asean, Mayang Anglingsari Putri, Risqy Siwi Pradini, Anuraga Jayanegara, Alexander Dimas Yonanta Putra

Knowledge Engineering and Data Science

Rice production is a key indicator of food security and agricultural stability in Southeast Asia, especially among Association of Southeast Asian Nations (ASEAN) countries. Despite shared regional goals, disparities in rice production remain, and previous studies mainly rely on descriptive statistics, lacking structured multicriteria decision-making frameworks and computational tools for cross-country comparisons. This study addresses these gaps by proposing an integrated Analytic Hierarchy Process (AHP)–Python framework to evaluate and rank ASEAN rice production from 2013 to 2022. Three criteria are used: Total Production Volume (K1), Production Growth Trend (K2), and Recent Year Performance (K3), capturing both long-term consistency and short-term …

Stable Numerical Solution Of An Elliptic Pde Inverse Problem Subject To Incomplete Boundary Conditions, Qasim Abd Ali Tayyeh

Knowledge Engineering and Data Science

This study addresses the challenging problem of solving inverse elliptic Partial Differential Equations (PDE) with incomplete boundary data, data available only on a part of the domain boundary. The aim is to develop a robust, effective numerical framework that consistently recovers parameters and/or sources from incomplete, ill-posed data. In the case of a variational problem discretized by the Finite Element Method (FEM) and solved by an adjoint-based optimization strategy, the framework uses Tikhonov regularization. Morozov's Discrepancy Principle is used to determine regularization parameters that achieve the best balance between accuracy and stability. Even with 5% noise in the measurement data, …

Assessing Deep Learning Models And Hyperparameter Optimization For Stable Time-Series Electricity Load Forecasting, Sukma Patrya, Aji Prasetya Wibawa, Aripriharta Aripriharta

Knowledge Engineering and Data Science

Long-term electricity load forecasting plays an important role in ensuring system reliability, optimizing energy management, and making operational plans in face of continuously rising electricity demands. This study suggests a complete deep learning method for univariate forecasting of future electricity loads based on climatology and electricity consumption data for the period between 2019 and 2023. The initial dataset was cleaned, normalized, and partitioned chronologically into train/test datasets. Four train/test split cases (20/80, 40/60, 60/40, 80/20) were considered to explore the impact of different levels of historical data availability on the performance of the suggested framework from data-poor to data-rich situations. …

Video Comprehension Score (Vcs): A Metric For Long-Form Video Description Evaluation, Harsh Dubey

Electronic Theses and Dissertations

Existing video description evaluation metrics fail to capture the long-range chronology and semantic alignment essential for long-form descriptions. An effective evaluation metric for long-form descriptions must (i) assess global thematic alignment, (ii) measure local semantic alignment, and (iii) evaluate chronological alignment while detecting corrupted content. We introduce Video Comprehension Score (VCS), a reference-based metric, which directly addresses these evaluation requirements through three components: Global Alignment Score for thematic alignment, Local Alignment Score for local semantic alignment, and Narrative Alignment Score for chronological alignment with adjustable tolerance. We evaluate VCS on two large-scale synthetic datasets designed to test corruption detection and …

Unwritten Rules And Oral Transmission In Architectural Proportion Systems: Case Study Of Bubungan Tinggi House, Huzairin. Muhammad Deddy, Dila Nadya Andini, Rudi Hartono, Anna Oktaviana, Dahliani Dahliani

ASEAN Journal on Science and Technology for Development

The proportional systems in vernacular architecture often exist without formal written codification, raising questions about their transmission across generations. Bubungan Tinggi House which is a replica of the Banjar Kingdom palace was built by Banjarese merchants and aristocrats from the 16th to the 19th centuries, showing a uniform aesthetic quality, which indicates a regularity in the proportions of its form. However, no historical written manuals detailing these proportions are known to exist. To prove the existence of regularity in the Bubungan Tinggi House proportion system, research was conducted by taking 7 Bubungan Tinggi House samples spread across South Kalimantan province, …

Artificial Intelligence To Transform Lifelong Learning And Workforce Development In Southeast Asia: A Call To Action, Shyh Poh Teo, Khadizah H. Abdul-Mumin

ASEAN Journal on Science and Technology for Development

No abstract for this article type.

Classification Of Indonesian Sign Language (Sibi) Using Data Mining Algorithms K-Nearest Neighbor And Random Forest, Muhammad Zaki Wirawan, Achmad Afif, Anik Nur Handayani, Imanuel Hitipeuw, Osamu Fukuda

Knowledge Engineering and Data Science

This study aims to address the communication hallenges faced by the Indonesian deaf community by developing an automatic classification model for Sistem Bahasa Isyarat Indonesia (SIBI) using data mining techniques. The main objective is to identify a practical algorithm for recognizing SIBI hand gestures to enhance accessibility and inclusiveness in digital communication. A comprehensive dataset consisting of 32,850 gesture samples representing SIBI alphabet signs was collected and processed through feature extraction, data cleaning, and normalization using Z-Transform and Min-Max methods. Two classification algorithms, K-Nearest Neighbor (KNN) and Random Forest, were implemented and evaluated using metrics such as accuracy, precision, recall, …

Generalizing Medical Image Segmentation Task With Efficient Deep Learning Models, Abel A. Reyes-Angulo

Dissertations, Master's Theses and Master's Reports

Medical Image Segmentation is a critical task in the field of medical imaging, playing a crucial role in diagnostics, treatment planning, and disease monitoring. The emergence of Deep Learning (DL) has ushered in a new era in Artificial Intelligence (AI), propelling remarkable advancements in key domains like language translation, object recognition, and recommendation systems. This evolution has been accompanied by continuous enhancements in computational efficiency and improvements in predictive accuracy. The introduction of sophisticated algorithms, such as convolutional neural networks (CNNs) and transformers, exemplifies these advancements. DL algorithms have demonstrated exceptional efficacy in medical image segmentation tasks, showcasing the potential …

Dam It All: A Multi-Scalar Investigation Into The Ecological Role And Function Of Beaver Dams, Kenneth Larsen

Dissertations, Master's Theses and Master's Reports

The central theme of this dissertation is ecological scaling, which examines how small, localized features, such as beaver ponds, contribute to large-scale watershed processes and how different modeling approaches at various scales reveal distinct insights. Through a combination of probabilistic modeling and high-resolution empirical research, this work demonstrates that small ponded systems, particularly those created by beavers (Castor canadensis), serve as critical biogeochemical control points, whose contributions to sediment and nutrient dynamics have been historically underestimated.

In Chapter 1, I contextualize this research within the broader fields of freshwater ecology, watershed modeling, and ecological restoration. I introduce the …

Old, Flat, And Slow: Interior Greenland Snow And Ice Dynamics Revealed With Gnss, Derek James Pickell

Dartmouth College Ph.D Dissertations

The interior dry snow zone region of the Greenland Ice Sheet can no longer be confidently considered a reliably melt-free region, yet our ability to investigate and quantify the dynamic nature of this landscape is hindered by its remoteness. To overcome this challenge, this work describes a novel, low-cost, low-power GNSS (positioning) instrument that enables simultaneous measurements of (1) ice accumulation/ablation changes and (2) 3D ice flow. Deployed in a dense array, these GNSS instruments achieve similar performance to scientific-grade, commercial options (cm- to mm- precision), yet operate at < 60% of the power and < 34% of the hardware cost. Over a three year campaign, we analyze spatial and temporal patterns of accumulation in this region, using a technique called GNSS interferometric reflectometry (GNSS-IR). Observations with this technique show low bias and high precision relative to a validation study (-2.1 ± 2.9 cm), while we also demonstrate for the first time how GNSS-IR can reveal cm- to m- scale surface roughness, a critical yet often neglected measurement due to longstanding observational challenges. Patterns of accumulation show a spatial dependence linked to surface slope (~+0.7 mm w.e. km^-1 westward away from the divide) while surface roughness has a temporal dependence likely driven by wintertime high winds. Next, we combine GNSS-IR surface heights with the geodetic position time series of the antenna to derive surface elevation changes, which are compared to coincident ICESat-2 laser altimetry elevations. Observations of the surface show a millimeter-level relative bias and cm-level precision (-0.9 ± 3.8 cm) compared with the satellite altimeter, demonstrating for the first time that this technique is a viable ground-truthing method, while ICESat-2 performance has continued to exceed mission performance requirements. Finally, we examine station positioning through time to show a sensitivity to dynamic ice thinning and firn densification, two parameters than cannot be finely observed with space-based methods in this region. Together, these results provide the first ground‑based, high‑resolution picture of interior ice‑sheet change—capturing accumulation, roughness, surface elevation, and strain in one unified dataset. Our approach dramatically lowers logistical barriers, opening the interior of Greenland (and other remote regions) to sustained, quantitative monitoring at unprecedented spatiotemporal resolution.

Predicting Biomechanical Risk Factors For Division - I Women’S Basketball Athletes, Aayushi Shah, Vanaja Agarwal, Dhairya Shah, Harman Jani, Sristi Sharma, Kaya Tolga, Christopher Taber, Mehul Raval

School of Computer Science & Engineering Faculty Publications

Collegiate basketball is characterized by high-impact movements such as jump landings, making athletes more susceptible to injuries. Critical biomechanical factors like knee flexion, lateral trunk flexion, and foot landing asymmetry are strongly associated with injury risk. This study aims to predict six biomechanical risk factors in the landing error scoring system (LESS). The dataset comprises 8600 video frames of counter-movement jumps (CMJs) from 17 NCAA Division I female basketball athletes, recorded from frontal and lateral perspectives and annotated using a customized error annotation algorithm. The study uses the You Only Look Once (YOLOv5nu) model to analyze the basketball athletes’ CMJ …

Valorizing Municipal Solid Waste For Sustainable Aviation Fuel And Polyhydroxyalkanoate Bioplastics: Pyrolysis And Microbial Pathways, Emon Das

Theses and Dissertations--Biosystems and Agricultural Engineering

The escalating global burden of municipal solid waste (MSW), projected to reach 3.88 billion tons annually by 2050, calls for innovative valorization strategies to mitigate environmental impacts and promote a circular bioeconomy. This thesis investigates the conversion of MSW into two high-value products: sustainable aviation fuel (SAF) and polyhydroxyalkanoate (PHA) bioplastics. Chapter one presents comprehensive physicochemical characterization and pyrolysis-GC/MS analysis of MSW feedstocks. The physicochemical results reveal that densification enhances handling and storage properties, while pyrolysis-GC/MS analysis indicates that plastic-rich MSW streams produce bio-oils with favorable hydrocarbon profiles suitable for SAF production, potentially contributing to decarbonization efforts in the aviation …

Enhancement Of Mechanical, Structural, And Electrical Properties In Advanced Composites And Vat Photopolymerized 3d Printing Nanocomposites, Poom Narongdej

CGU Theses & Dissertations

Advanced composites have gained significant attention across various industries, including aerospace, automotive, clean energy, and healthcare, owing to their exceptional mechanical properties and versatility. Fiber-reinforced polymer (FRP) composites, particularly those reinforced with carbon fibers, are extensively used as structural materials in spacecraft, aircraft, high-performance vehicles, and wind turbines due to their high strength-to-weight ratios, stiffness, durability, and tailorable mechanical characteristics. In healthcare, the advent of additive manufacturing (3D printing) has expanded the utility of advanced composites, enabling precise customization of components to meet patient-specific needs while offering design flexibility and ease of fabrication. Despite these advantages, several challenges hinder the …

Mangroves: A Lesson On Modeling Changing Shorelines, Willa Skye

ENGS 15.11: Design and Education

This lesson is an overview of storm barriers, specifically mangroves and how they maintain shorelines. It is meant to offer a visual experience of coastline protection and provide a background for deeper understanding about intertidal zones and their conservation. Students will spend time creating a solution to a flooding problem by making a mock coast and storm barrier. To wrap-up the lesson, students will pair up, then reflect on their model and then individually write or draw their takeaways.

Sogar: Self-Supervised Spatiotemporal Attention-Based Social Group Activity Recognition, Naga Venkata Sai Raviteja Chappa, Pha Nguyen, Alexander H. Nelson, Han-Seok Seo, Xin Li, Page Daniels Dobbs, Khoa Luu

Electrical Engineering and Computer Science Faculty Publications and Presentations

Social group activity recognition is crucial for various applications including surveillance, human-robot interaction, and behavioral analysis. Current approaches often require extensive manual annotations and rely heavily on pre-trained detectors, limiting their practical applications. Additionally, existing methods struggle to effectively model long-term spatiotemporal relationships in group activities. This paper introduces a novel approach to Social Group Activity Recognition (SoGAR) using Self-supervised Transformers network that can effectively utilize unlabeled video data. To extract spatio-temporal information, we create local and global views with varying frame rates. Our self-supervised objective ensures that features extracted from contrasting views of the same video are consistent across …